fix(dub): classify EINVAL transcribe failures so they stop dead-ending (#763) (#936)

A per-chunk temp-WAV write that fails with OSError EINVAL ("[Errno 22]
Invalid argument") — a missing/read-only/full temp dir, a removed drive,
or antivirus — collapsed into "Transcription produced no segments.
[Errno 22] Invalid argument" with no next step. classify() now names the
class (OS_INVALID_ARGUMENT) so build_failure attaches an actionable
temp-dir/disk/AV hint at the exact surface the streaming dub path already
feeds it (dub_core.py:672) — same treatment the ffmpeg and compute-type
classes get. Fail-before/pass-after regression added; the errno-22 token
keeps it from colliding with the errno-2 transformers-import class.

Also stamps the [0.3.9] CHANGELOG section with today's release date
(2026-07-04) ahead of tagging.

Co-authored-by: mergetest <test@local>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>

.github/FUNDING.yml

@@ -1,6 +1,9 @@
 # These are supported funding model platforms
+# GitHub Sponsors isn't set up for this account — fund via Ko-fi or PayPal.
 
-github: [debpalash]
-# ko_fi: omnivoice
+ko_fi: debpalash
+custom:
+  - "https://paypal.me/palashCoder"
+  - "https://github.com/debpalash/OmniVoice-Studio/blob/main/SPONSORS.md"
+# github: [debpalash]            # not available
 # open_collective: omnivoice-studio
-# custom: ["https://omnivoice.palash.dev/sponsor"]

.github/ISSUE_TEMPLATE/sponsor.yml

@@ -0,0 +1,78 @@
+name: 🤝 Sponsorship inquiry
+description: Support OmniVoice and (optionally) claim a logo slot. Not for bugs or feature requests.
+title: "Sponsorship inquiry: "
+labels: ["sponsor"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for considering sponsoring **OmniVoice Studio** 💛
+
+        OmniVoice is free, local-first, and AGPL-3.0 — sponsorship keeps development going.
+        See **[SPONSORS.md](https://github.com/debpalash/OmniVoice-Studio/blob/main/SPONSORS.md)** for tiers, placements, and logo guidelines.
+        Prefer to just donate? [Ko-fi](https://ko-fi.com/debpalash) (recurring) or [PayPal](https://paypal.me/palashCoder) (one-time) — you don't need this form for that.
+  - type: input
+    id: name
+    attributes:
+      label: Name or organization
+      description: How you'd like to be credited (person or company).
+    validations:
+      required: true
+  - type: input
+    id: website
+    attributes:
+      label: Website / link
+      description: The URL your name or logo should link to (homepage, product page, profile…).
+      placeholder: https://example.com
+  - type: input
+    id: logo
+    attributes:
+      label: Logo URL (optional)
+      description: Link to your logo (SVG preferred, else 2× PNG, transparent background). You can also attach it in the description below.
+      placeholder: https://example.com/logo.svg
+  - type: dropdown
+    id: tier
+    attributes:
+      label: Tier you're interested in
+      description: See SPONSORS.md for what each tier includes. Not sure? Pick "Not sure yet".
+      options:
+        - Backer
+        - Bronze
+        - Silver
+        - Gold
+        - Not sure yet — let's talk
+        - Custom / annual arrangement
+    validations:
+      required: true
+  - type: dropdown
+    id: method
+    attributes:
+      label: How you'd like to support
+      options:
+        - Ko-fi (recurring)
+        - Ko-fi (one-time)
+        - PayPal (one-time)
+        - Not sure yet — let's discuss
+    validations:
+      required: true
+  - type: input
+    id: contact
+    attributes:
+      label: How should we reach you?
+      description: Email or another contact. (GitHub will also notify you on this issue.)
+    validations:
+      required: true
+  - type: textarea
+    id: notes
+    attributes:
+      label: Anything else?
+      description: Questions, constraints, timeline, or context. Attach your logo here if you didn't link it above.
+  - type: checkboxes
+    id: ack
+    attributes:
+      label: Acknowledgements
+      options:
+        - label: I understand sponsorship is a thank-you, not a paywall — OmniVoice stays fully free and AGPL-3.0, and sponsors don't get gated features.
+          required: true
+        - label: If I provide a logo, I have the right to use it and grant OmniVoice permission to display it in the README, the app, and the project website.
+          required: false

.github/workflows/ci.yml

@@ -105,6 +105,19 @@ jobs:
         working-directory: frontend
         run: bun run typecheck:ci
 
+      # oxlint gate — fast Rust linter, blocks on errors so lint debt can't
+      # re-accumulate (warnings, incl. the react-compiler advisories in
+      # `lint:hooks`, are non-blocking). See frontend/.oxlintrc.json.
+      - name: Frontend lint (oxlint)
+        working-directory: frontend
+        run: bun run lint
+
+      # oxfmt format gate — JS/TS/JSX only (CSS/JSON/Tauri excluded; see
+      # frontend/.oxfmtrc.json). `bun run format` fixes locally.
+      - name: Frontend format check (oxfmt)
+        working-directory: frontend
+        run: bun run format:check
+
       - name: Run Vitest (frontend)
         working-directory: frontend
         run: bunx vitest run

.github/workflows/release.yml

@@ -4,12 +4,16 @@
 #   - push of a tag matching `v*` (e.g. `v0.2.0`) → full STABLE release,
 #     publishes artifacts + signed updater manifest (`latest.json`) to the
 #     tag's GH Release. This is the default Stable updater channel.
-#   - workflow_dispatch (publish_preview=true) → builds the selected branch and
-#     publishes a rolling `preview` PRERELEASE with its own signed
-#     `latest.json` at releases/download/preview/. This feeds the opt-in
-#     Preview updater channel (Settings → About → Update channel). The stable
-#     `latest` release is untouched. Run this manually whenever you want to cut
-#     a preview from `main`.
+#   - schedule (nightly, 07:00 UTC) → rolling `preview` PRERELEASE built from
+#     `main` with its own signed `latest.json` at releases/download/preview/.
+#     Feeds the opt-in Preview updater channel (Settings → About → Update
+#     channel). The `preview-gate` job skips the matrix on nights when `main`
+#     didn't move, so an idle day costs only a ~30s gate job — keeping Preview
+#     ≤24h behind `main` at a predictable ~1-matrix/day cost. The stable
+#     `latest` release is untouched.
+#   - workflow_dispatch (publish_preview=true) → the same preview build on
+#     demand from the selected branch (e.g. to preview a feature branch, or to
+#     refresh immediately without waiting for the nightly).
 #   - workflow_dispatch (publish_preview=false) → on-demand build (prior
 #     behavior; draft release named after the branch).
 #
@@ -28,6 +32,10 @@ name: Desktop Release
 on:
   push:
     tags: ['v*']
+  schedule:
+    # 07:00 UTC daily — rolling `preview` prerelease from `main`. The
+    # preview-gate job no-ops the matrix when main hasn't moved in a day.
+    - cron: '0 7 * * *'
   workflow_dispatch:
     inputs:
       draft:
@@ -121,8 +129,41 @@ jobs:
         working-directory: frontend
         run: node --experimental-strip-types --no-warnings --test ../tests/frontend/*.test.mjs
 
+  # Decide preview-vs-stable, and for nightly runs whether `main` actually
+  # moved in the last day. Outputs gate the expensive matrix (`build`) and the
+  # `preview-notes` job, so a no-commit night costs only this ~30s job.
+  preview-gate:
+    name: Preview gate
+    runs-on: ubuntu-22.04
+    outputs:
+      is_preview: ${{ steps.decide.outputs.is_preview }}
+      proceed: ${{ steps.decide.outputs.proceed }}
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 50
+      - id: decide
+        shell: bash
+        run: |
+          set -euo pipefail
+          event="${{ github.event_name }}"
+          if [ "$event" = "schedule" ] || { [ "$event" = "workflow_dispatch" ] && [ "${{ inputs.publish_preview }}" = "true" ]; }; then
+            echo "is_preview=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "is_preview=false" >> "$GITHUB_OUTPUT"
+          fi
+          # Nightly: skip the matrix when main hasn't moved in the last day.
+          if [ "$event" = "schedule" ] && [ -z "$(git log --since='25 hours ago' --oneline)" ]; then
+            echo "No new commits on main in the last day — skipping nightly preview."
+            echo "proceed=false" >> "$GITHUB_OUTPUT"
+          else
+            echo "proceed=true" >> "$GITHUB_OUTPUT"
+          fi
+
   build:
-    needs: test
+    needs: [test, preview-gate]
+    # Nightly runs with no new commits on main skip the 4-platform matrix.
+    if: needs.preview-gate.outputs.proceed == 'true'
     strategy:
       fail-fast: false
       matrix:
@@ -149,6 +190,14 @@ jobs:
           # backlog that motivated the original drop is contained by
           # fail-fast:false — a slow Intel leg can delay the release run but
           # can't fail the other targets.
+          #
+          # #889 (2026-07): Intel macOS is now UNSUPPORTED for the local
+          # backend — torch ≥2.3 ships no macOS x86_64 wheels, so the venv
+          # bootstrap can never succeed on Intel. The shipped x64 artifact is
+          # effectively UI-only (usable with a remote backend); the app now
+          # pre-fails first-run bootstrap with an honest message on Intel.
+          # Whether to keep shipping this x64 leg (UI-only) or drop it is an
+          # OWNER CALL — deliberately not changed in the #889 PR.
           - os: macos-15-intel
             arch: x86_64-apple-darwin
             label: "macOS Intel"
@@ -427,11 +476,14 @@ jobs:
       # the Windows MSI ProductVersion (which strips the prerelease → 0.3.6)
       # is also correctly above the last stable.
       - name: Stamp preview version
-        if: github.event_name == 'workflow_dispatch' && inputs.publish_preview
+        if: needs.preview-gate.outputs.is_preview == 'true'
         shell: bash
         run: |
           set -euo pipefail
-          CONF=frontend/src-tauri/tauri.conf.json
+          # package.json is the single source of truth; tauri.conf.json reads its
+          # version from it ("version": "../package.json"), so stamping
+          # package.json restamps the whole bundle.
+          CONF=frontend/package.json
           BASE=$(jq -r .version "$CONF")
           # MSI/WiX requires the semver pre-release identifier to be numeric-only
           # (and <= 65535). "preview.N" hard-fails the Windows bundler, so the
@@ -471,11 +523,13 @@ jobs:
           # rolling `preview` prerelease for the updater's Preview channel.
           # Every other invocation — crucially the `v*` tag-push stable release
           # — evaluates these expressions to exactly their prior values.
-          tagName: ${{ (github.event_name == 'workflow_dispatch' && inputs.publish_preview) && 'preview' || github.ref_name }}
-          releaseName: ${{ (github.event_name == 'workflow_dispatch' && inputs.publish_preview) && 'OmniVoice Studio (Preview)' || format('OmniVoice Studio {0}', github.ref_name) }}
+          tagName: ${{ (needs.preview-gate.outputs.is_preview == 'true') && 'preview' || github.ref_name }}
+          # Version-first so the tag is readable in GitHub's truncated
+          # release-list sidebar (which clips the title mid-string).
+          releaseName: ${{ (needs.preview-gate.outputs.is_preview == 'true') && 'Preview — OmniVoice Studio' || format('{0} — OmniVoice Studio', github.ref_name) }}
           releaseBody: ${{ steps.changelog.outputs.body }}
-          releaseDraft: ${{ (github.event_name == 'workflow_dispatch' && inputs.publish_preview) && 'false' || (inputs.draft || 'true') }}
-          prerelease: ${{ (github.event_name == 'workflow_dispatch' && inputs.publish_preview) || false }}
+          releaseDraft: ${{ (needs.preview-gate.outputs.is_preview == 'true') && 'false' || (inputs.draft || 'true') }}
+          prerelease: ${{ needs.preview-gate.outputs.is_preview == 'true' }}
           updaterJsonPreferNsis: false
           includeUpdaterJson: true
 
@@ -661,8 +715,8 @@ jobs:
   # preview-only — stable `v*` releases keep their CHANGELOG section + the
   # appended checksums.
   preview-notes:
-    needs: build
-    if: github.event_name == 'workflow_dispatch' && inputs.publish_preview
+    needs: [build, preview-gate]
+    if: needs.preview-gate.outputs.is_preview == 'true'
     runs-on: ubuntu-22.04
     permissions:
       contents: write
@@ -693,16 +747,51 @@ jobs:
             echo ""
             echo "$CONTRIB"
           } > /tmp/preview-notes.md
-          gh release edit preview --repo "$REPO" --notes-file /tmp/preview-notes.md
+          # --prerelease re-asserts the flag every run: a non-prerelease
+          # `preview` release is eligible to become GitHub's "Latest", which is
+          # the exact URL the Stable updater channel reads — so it must never
+          # flip off.
+          gh release edit preview --repo "$REPO" --prerelease --notes-file /tmp/preview-notes.md
           echo "Applied auto-generated release notes + contributors to the preview release."
 
-  # ── Post-release version bump (versioning hard rule, owner-set 2026-06-11) ──
-  # main is always last-release + 1 patch. The moment a stable v* tag is
-  # released, bump the three version sources on main to the next patch so every
-  # PR and preview build identifies as the next version. Pushes directly to
-  # main with the workflow token (a metadata-only commit; CI runs on PRs).
+      - name: Verify preview updater manifest (prerelease + platform parity)
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          REPO: ${{ github.repository }}
+        run: |
+          set -euo pipefail
+          # The preview release must stay a prerelease (or it can hijack the
+          # Stable channel's releases/latest endpoint), and its updater manifest
+          # must cover every platform stable does (else those users — e.g. Intel
+          # Mac — silently get no preview updates).
+          is_pre=$(gh release view preview --repo "$REPO" --json isPrerelease -q .isPrerelease)
+          test "$is_pre" = "true" || { echo "::error::preview release is not a prerelease"; exit 1; }
+          curl -fsSL "https://github.com/$REPO/releases/download/preview/latest.json" -o /tmp/preview-latest.json
+          curl -fsSL "https://github.com/$REPO/releases/latest/download/latest.json" -o /tmp/stable-latest.json
+          python3 - <<'PY'
+          import json, re
+          prev = json.load(open("/tmp/preview-latest.json"))
+          stab = json.load(open("/tmp/stable-latest.json"))
+          v = prev.get("version", "")
+          assert re.fullmatch(r"\d+\.\d+\.\d+-\d+", v), f"preview version not X.Y.Z-N: {v!r}"
+          pk, sk = set(prev.get("platforms", {})), set(stab.get("platforms", {}))
+          missing = sk - pk
+          assert not missing, f"preview manifest missing platforms vs stable: {sorted(missing)}"
+          print(f"preview manifest OK: {v} platforms={sorted(pk)}")
+          PY
+
+  # ── Post-release version bump (OWNER-GATED as of 2026-07-01) ──────────────
+  # Previously auto-ran after every stable v* tag to keep main = release + 1.
+  # The owner now controls bumps manually ("keep 0.3.8; I say when to bump"), so
+  # this job is OPT-IN: it runs ONLY when the repo variable AUTO_VERSION_BUMP is
+  # set to 'true' (Settings → Secrets and variables → Actions → Variables).
+  # Unset/anything-else → main stays at whatever it is after release. Re-enable
+  # by setting the variable; disable again by unsetting it.
   version-bump:
-    if: github.event_name == 'push' && github.ref_type == 'tag' && !contains(github.ref, '-')
+    if: >-
+      github.event_name == 'push' && github.ref_type == 'tag'
+      && !contains(github.ref, '-')
+      && vars.AUTO_VERSION_BUMP == 'true'
     runs-on: ubuntu-22.04
     permissions:
       contents: write
@@ -718,23 +807,26 @@ jobs:
           RELEASED="${GITHUB_REF_NAME#v}"
           IFS=. read -r MAJ MIN PAT <<< "$RELEASED"
           NEXT="$MAJ.$MIN.$((PAT + 1))"
-          CURRENT=$(jq -r .version frontend/src-tauri/tauri.conf.json)
+          # frontend/package.json is the SINGLE SOURCE OF TRUTH: vite injects
+          # __APP_VERSION__ from it, and tauri.conf.json reads its bundle version
+          # from it ("version": "../package.json"). Read CURRENT from it.
+          CURRENT=$(jq -r .version frontend/package.json)
           if [ "$(printf '%s\n' "$NEXT" "$CURRENT" | sort -V | tail -1)" = "$CURRENT" ] && [ "$NEXT" != "$CURRENT" ]; then
             echo "main is already at $CURRENT (>= $NEXT) — nothing to bump"; exit 0
           fi
-          tmp=$(mktemp)
-          jq --arg v "$NEXT" '.version = $v' frontend/src-tauri/tauri.conf.json > "$tmp"
-          mv "$tmp" frontend/src-tauri/tauri.conf.json
-          # frontend/package.json drives __APP_VERSION__ (vite.config.js) — the
-          # first-run footer + every auto bug report. Keep it in lockstep too,
-          # set absolutely (jq) so any prior drift self-heals. (#248-sweep finding)
+          # Bump the canonical (package.json), set absolutely so any prior drift
+          # self-heals. tauri.conf.json needs no edit — it derives from this.
           tmp=$(mktemp)
           jq --arg v "$NEXT" '.version = $v' frontend/package.json > "$tmp"
           mv "$tmp" frontend/package.json
+          # The remaining files are CI-guarded mirrors (cargo/uv require a
+          # literal; the version.py literal is the frozen-backend last resort) —
+          # bump them in lockstep with the canonical.
           sed -i "0,/^version = \"$CURRENT\"/s//version = \"$NEXT\"/" frontend/src-tauri/Cargo.toml
           sed -i "0,/^version = \"$CURRENT\"/s//version = \"$NEXT\"/" pyproject.toml
+          sed -i "0,/_FALLBACK_VERSION = \"$CURRENT\"/s//_FALLBACK_VERSION = \"$NEXT\"/" backend/core/version.py
           git config user.name "github-actions[bot]"
           git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
-          git add frontend/src-tauri/tauri.conf.json frontend/package.json frontend/src-tauri/Cargo.toml pyproject.toml
+          git add frontend/package.json frontend/src-tauri/Cargo.toml pyproject.toml backend/core/version.py
           git commit -m "chore(version): main -> $NEXT after $GITHUB_REF_NAME release"
           git push origin main

CHANGELOG.md

@@ -6,9 +6,753 @@ The format is loosely based on [Keep a Changelog](https://keepachangelog.com/).
 Versions track the desktop app (`tauri.conf.json` + `frontend/src-tauri/Cargo.toml`).
 The bundled TTS model package (`pyproject.toml`) is versioned independently.
 
-## [Unreleased]
+## [0.3.9] — 2026-07-04
+
+The dictation release — and a deep reliability pass driven by live-testing the entire app. **Dictation is rebuilt end-to-end**: instant feedback with a live waveform, words that commit about half a second after you stop speaking, clean punctuation, and text insertion that never lies about success. **LLM providers get one-click connection testing** with real diagnostics and model discovery, in all 21 languages. The app now **always opens maximized**, bottom buttons **can't hide under the footer** at small window sizes, and a wave of "out of memory / can't reach the backend / stuck at preparing" reports were traced to their real causes and fixed — including the silent VRAM crash on 8 GB cards, dead-IPC startup hangs after a Windows BSOD, and misleading error labels. Intel-Mac support status is now stated honestly, Confucius4-TTS is validated end-to-end, and Parakeet — roughly 20× faster than the default transcriber on CPU — is unlocked for every machine.
 
 ### Added
+
+- **Sponsor OmniVoice.** A new `SPONSORS.md` (tiers, logo guidelines, how to sponsor), a README Sponsors section, and an in-app Sponsors area (Support page + a footer link) let people back the project — with a one-click "Become a sponsor" that opens a structured GitHub issue form, no account or token needed. Sponsorship is a thank-you, not a paywall: OmniVoice stays free and AGPL-3.0. (#923, #924)
+- **OpenAPI reference in Settings.** A new Settings → OpenAPI page embeds an interactive Scalar reference for OmniVoice's local backend API, with a one-click footer button. Fully local — Scalar is bundled, not loaded from a CDN, and phones home to nothing. (#928)
+- **Engine Self-test.** The Engines matrix gains a "Self-test" button for in-process TTS engines that runs a tiny real synthesis and reports duration + sample rate — proving an engine actually makes audio, not just imports — plus a copy-paste `export OMNIVOICE_*_DIR=…` setup line for opt-in engines right in the "Why unavailable?" panel. (#930)
+- **One canonical HuggingFace-token store + incomplete-download visibility.** The Model Store token field now saves to and is cleared from the same encrypted store as Settings → Credentials (no more two-stores split), and a truncated model cache shows an "incomplete · N MB" state with one-click Repair and Delete instead of masquerading as "not installed". (#927)
+- **Launchpad, reimagined as a deck of cards.** The seven feature cards now fan out with animated waveform faces in each card's accent color; hover or keyboard-focus any card and it comes forward while the rest tuck underneath, and the layout stays usable down to the minimum window size. (#904)
+- **See exactly what OmniVoice keeps on disk — and get warned before space runs out.** Settings → Storage shows real usage for the model cache (with your largest models), app data, engine environments and temp files, plus a free-space gauge and low-disk / near-full-volume warnings with one-click paths to open folders or reclaim space. (#906)
+- **A "What's new" changelog reader in Settings → Updates.** The available update's real release notes now render in-app, alongside an offline changelog viewer and a one-time "what's new" note after each update. (#909)
+- **Route each AI feature to its own LLM — or switch it off.** A new Settings → LLM Skills panel lists every LLM-powered capability (Cinematic/Autofit translation, slot fitting, glossary auto-extract, direction parsing, dictation cleanup) with a per-skill toggle and provider picker, so sensitive work can stay on a local model while heavier jobs use a remote one. Disabled skills fall back to the exact non-LLM behavior. (#912)
+- **A small thank-you moment, done right.** After a successful export, dub, audiobook, or batch run, OmniVoice may — rarely — show a friendly, dismissible note by the footer heart about supporting development: never more than once a session, at most every 7 days, never for brand-new users, with a permanent "don't ask again". The logs bar also gained an icon and the footer icons now share one size. (#898)
+
+- **Dictation, rebuilt.** The dictation pill now shows a live waveform the moment the mic opens, streams words as you speak with real download/loading progress on first use, and finishes what you say in about half a second of silence instead of two-and-a-half. Transcripts come out properly capitalized and punctuated. Text insertion is now honest and safe: your clipboard is preserved and restored, failures show what to do (including a one-click jump to macOS Accessibility settings when permission is missing) instead of a false "Pasted", and Esc cancels cleanly at any point. The dictation model also pre-warms in the background after launch, so the first press of the hotkey no longer sits on a cold model load.
+
+- **LLM Providers: one-click connection testing with real diagnostics.** The Test button in Settings → LLM Providers now measures round-trip latency and turns failures into plain-language guidance — bad key (401/403), wrong model or URL (404), rate-limited (429), or unreachable server — instead of a raw exception dump. A new "Fetch models" button lists every model your key can access so you pick from real names instead of guessing. The whole panel is now translated into all 21 languages, provider error messages never echo your API key, and the settings API gained full test coverage.
+
+### Changed
+
+- **A "Get in touch" page that actually guides you.** The Contact page is now clearly-labelled cards (report a bug, request a feature, get community help, support the project, report a security issue) with a sentence each on when to use them, instead of a flat link list. (#925)
+- **Release titles are version-first.** GitHub's release-list sidebar truncates the title, so "OmniVoice Studio v0.3.8" hid the version; releases are now named "vX.Y.Z — OmniVoice Studio" so the version is always visible. (#922)
+- **Launchpad feature cards now fill the window.** The seven cards (Voice Clone, Voice Design, Video Dubbing, Stories, Audiobook, Voice Gallery, Transcripts) span the full content width on a maximized display instead of a fixed ~780px fan, and reflow responsively (7→3→1 columns) down to the 900×600 minimum — driven by the shell's own width, keeping the animated card faces, hover/keyboard-focus raise, and reduced-motion fallback. (#915)
+- **LLM Providers settings, de-confused.** The old inline "LLM endpoint" box in Translation is gone — LLM Providers is now the one place that owns it. Fields pinned by an environment variable are shown disabled with an explainer instead of silently reverting, the make-active button explains when a provider is env-pinned, and the Cloudflare Account ID is remembered and editable. (#907)
+- **Intel Macs: honestly unsupported for the local backend.** PyTorch no longer ships Intel-Mac builds, so the backend cannot run there; instead of a cryptic dependency error, Intel users now get a clear explanation up front (with the remote-backend option), and the README/docs say so plainly. (#889, #891)
+
+- **The app now always opens maximized (not fullscreen).** Window size and position are no longer carried over from the previous session — one manual resize used to make every later launch reopen at that smaller size, overriding the intended maximized default. Same behavior on macOS (zoomed window, not a fullscreen Space), Windows, and Linux.
+
+### Fixed
+
+- **Sherpa-ONNX "model not set" now reads as a setup problem, not out-of-memory.** Selecting the sherpa-onnx engine without `OMNIVOICE_SHERPA_MODEL` configured used to fail with a misleading "ran out of memory — press Flush" 500; it now names the exact variable, points at Settings → Engines, and the engine is marked unavailable-with-a-reason in the picker (with a copy-paste setup line) instead of selectable-but-broken. Generalized so any env-gated engine surfaces actionable setup guidance. (#919)
+- **Cinematic & Autofit now actually run on every translation engine.** Picking Cinematic or Autofit on the default Argos engine (or NLLB) used to silently fall back to Fast with a success toast; it now runs the full LLM refine + fit pass, the Autofit fit pass is bounded by the same wall-clock budget as Cinematic, and provider errors are scrubbed of keys/user-ids. (#910)
+- **Dictation no longer freezes on a slow or dead LLM.** Transcript refinement is now hard-bounded (default 4s): a placeholder key or unreachable endpoint falls back to clean unrefined text instead of stalling the paste ~51 seconds. The dictation model is genuinely pre-warmed and reused across sessions, REST transcription is polished like live dictation, and Settings flags a configured-but-failing LLM. (#911)
+- **Model installs fail loudly, not silently.** Failed downloads keep their mirror-aware reason on the row with Retry/Dismiss instead of vanishing after a moment; installs check free disk space up front before overrunning it; in-progress installs get a Cancel button; and the HF-mirror setting only asks for a restart when it actually changed. (#908)
+- **Engines settings, sharper and honest.** The Supertonic license "Accept" button works again (it was inert since it shipped), the engine matrix refreshes the instant you pick an engine, picking a GPU engine that lands on CPU now warns you with the reason, CPU-only engines stop being mislabelled "CPU fallback", and an in-process "Test engine" pass reads as a dependency check instead of a fake "0 ms" latency. (#905)
+- **Updates can no longer cost you data.** Before any database migration runs on first launch of a new version, the database is snapshotted next to itself (newest three kept), and a failed migration stops with the backup path named instead of silently running on a half-upgraded database; the environment self-heal now verifies it's actually broken before rebuilding. (#909)
+- **CUDA transcription now works on packaged NVIDIA installs — the cuDNN 8 compat libraries install automatically at launch.** The install step only existed in the dev-loop `scripts/setup.py`, which isn't bundled into the packaged app, so real installs never got the libs and WhisperX / faster-whisper failed with `Could not locate cudnn_ops_infer64_8.dll`. The Rust bootstrap now side-loads them on CUDA machines; CPU/AMD/ROCm boxes skip the download and cache the result so their launches stay instant. (#827, #869)
+- **`scripts/setup.py` no longer fails with `No module named pip` when installing the cuDNN 8 libs in the dev loop.** `uv venv` doesn't seed pip into the venv, so `python -m pip install` always broke; the script now uses `uv pip install --python` instead. (#869)
+- **Generation timeouts now give device-honest advice.** A CPU-only machine is no longer told the GPU is "VRAM-starved" or to "set the engine to CPU" — CPU hosts get compute-bound guidance (shorter text, the CPU-tuned GGUF/Supertonic-3 engines, the OMNIVOICE_GENERATE_TIMEOUT_S knob) while GPU hosts keep the VRAM-contention explanation. (#896)
+- **Model-download failures now name the mirror that failed.** When a Hugging Face mirror is configured and unreachable, every affected surface (generate, dub, Model Store installs) names the mirror and points at the exact setting instead of leaking a raw network error; auto-repair failures now say *why* the repair failed. (#874, #890)
+- **No more infinite "preparing" after an unclean shutdown.** If Windows corrupts the WebView cache (e.g. after a BSOD), the splash detects the dead IPC channel, proceeds via a direct backend health check, and — if truly stuck — offers a one-click "Repair and restart". (#879, #892)
+- **"Out of memory" is no longer the default excuse.** A failed model download mid-generation was mislabeled as OOM with useless "flush VRAM" advice; network failures are now classified honestly, only real OOM signatures get the OOM treatment, and first-use engine downloads retry once with a fresh connection. (#880, #893)
+- **Hung transcriptions recover the same way everywhere.** Chunked dub transcription now shares the same guarded-timeout + GPU-pool reset as the rest of the app, and repeated timeouts recommend the crash-isolated ASR engine — now properly selectable in Settings. (#730, #895)
+- **A raw `[Errno 22]` transcribe error now tells you what to fix.** When the OS rejects the temporary WAV write during dub transcription (a missing, read-only, or full temp directory, or antivirus interference), the stream used to dead-end as *"Transcription produced no segments. [Errno 22] Invalid argument"* with no next step; it now classifies the EINVAL and appends an actionable temp-dir/disk/AV hint — the same treatment the ffmpeg and compute-type failure classes already get. (#763)
+
+- **Buttons can no longer hide under the logs footer on small windows.** The bottom status/logs bar was a fixed overlay that pages had to compensate for with padding — any view that missed it (voice-card grids in Gallery and Community, bottom action rows) clipped under the bar at small window sizes, a class previously patched one page at a time (#476, #504). The footer is now a real row of the app shell, so content physically ends at its top edge at every window size, collapsed or expanded — guarded by a new layout test plus a 900×600 Playwright check at the app's minimum window size.
+
+- **Confucius4-TTS is now validated end-to-end — and actually loads.** The opt-in engine's first live run (Apple Silicon, CPU) caught three scaffold-era faults: the sidecar could never import `confuciustts` (upstream ships no packaging, so the documented `pip install -e` fails — the sidecar and bootstrap probe now put the clone on `sys.path`, like upstream's own example), the assumed 24 kHz sample rate was wrong (confirmed **22 050 Hz**, now regression-tested), and the docs demanded an Amphion/MaskGCT install that doesn't exist (all weights auto-download from HuggingFace). CPU is ~17× realtime, so CUDA stays the recommended path; `gpu_compat` now advertises `("cuda", "cpu")`. (#590)
+
+- **Parakeet TDT transcription now works without an NVIDIA GPU.** The `nemo-parakeet` ASR engine (parakeet-tdt-0.6b-v3, 25 languages, word timestamps) was hard-gated behind CUDA — but a live measurement on an Apple Silicon M2 shows it transcribing at ~10× realtime *on CPU*, roughly 20× faster than the default whisper-large-v3 on the same machine at equal accuracy. The false GPU gate is removed, so Mac and CPU-only users can now pick the dramatically faster engine in Settings → Engines.
+
+- **8 GB GPUs: voice-clone/dub transcription no longer kills the backend.** On cards where the TTS model already held most of the VRAM (e.g. RTX 4060 Ti 8 GB), loading whisper `large-v3` in float16 for a reference-clip or dub transcription died as a *native* CUDA out-of-memory abort — the whole backend process vanished with no error logged, and the app showed "Can't reach the local OmniVoice backend." A new VRAM preflight re-checks free GPU memory right before the ASR load and steps down float16 → int8 → CPU instead of attempting a load that can't fit (opt-out: `OMNIVOICE_ASR_VRAM_PREFLIGHT=0`). (#723)
+
+### CI
+
+- **A migration can no longer silence the app's logs.** Alembic's startup config was disabling every existing logger process-wide (a latent bug the new pre-migration backup logging exposed); fixed, and the migration-safety tests are now immune to full-suite ordering. (#909, #917)
+- **Deterministically green tests + real install proof.** Tests can no longer read the developer's real `.env` or app data (the order-dependent flake class, #878, #894), and a new cross-platform install-test workflow builds all four installers and proves a real first run — model download plus verified synthesis — on macOS, Windows, and Linux runners.
+
+## [0.3.8] — 2026-07-01
+
+A stability-focused release that makes first-run and Windows "just work," ships
+**live, faster-than-real-time local dictation** and a **user pronunciation
+dictionary**, and gives **Settings a full redesign**. It clears the wave of
+**"Can't reach the local backend"** reports at the source — the 8 GB-card OOM
+crash, the slow-load future-scheduling break, a Windows-only WhisperX load
+failure, an ASR engine that couldn't load CTranslate2 on newer Linux/WSL, and
+both transcription **and generation** stalls that *looked* like a dead backend
+(a wedged GPU job now resets the worker pool and returns an actionable timeout)
+are all fixed or now fail with a clear, actionable message. **macOS gets native file drag-and-drop back**
+(including macOS 26 Tahoe). Downloads are faster out of the box (parallel
+segmented transfer on by default) and the Hugging Face token that speeds them up
+is front-and-center on setup. Plus multi-voice story casting, faster long-form
+previews on Windows, and a friendlier, more honest batch of error messages
+across dub, generate, and design (a corrupt-binary failure no longer poses as
+"out of memory," a bad model id self-heals, and a stale dub job resets cleanly).
+
+### Added
+
+- **"Autofit" translation quality — the dub keeps the video's timing.** A new
+  quality alongside Fast and Cinematic: the LLM rewrites each translated line so
+  its target-language reading time fits *within* the segment's slot (a strict
+  "never overrun" bound, per-language pronunciation-speed aware), so long
+  translations no longer force the audio into a stressed >1.3× time-stretch.
+  Cinematic still applies its reflect/adapt polish; Autofit adds the hard
+  fit-to-slot pass on top. Needs an LLM (below); falls back to Fast with a clear
+  notice if none is set. (#838)
+- **A new LLM Providers settings page — bring your own high-quality LLM.**
+  Settings → System → **LLM Providers** configures the LLM that powers Cinematic
+  and Autofit translation. One page for **16 providers** — OpenAI, OpenRouter,
+  Groq, Cerebras, Google AI (Gemini), Mistral, Cohere, NVIDIA, GitHub Models,
+  Cloudflare, Hugging Face, SambaNova, SiliconFlow, plus **local Ollama / LM
+  Studio** (fully offline, no key) and a **Custom** OpenAI-compatible endpoint.
+  Paste a key, pick a model, **Test** the connection in one click, and "use for
+  translation" to make it active. Keys are stored **encrypted** (the same
+  at-rest protection as the HF token) and never leave the machine unless you
+  choose a cloud provider; env vars still override for power users. The dub
+  translate menu now routes you straight here when you pick a high-quality
+  style without an LLM, instead of dead-ending on a toast. (#838)
+- **A dedicated Network pane.** The HTTP/SOCKS proxy and FFmpeg-path controls
+  (previously buried in General → Advanced) are promoted to their own category.
+- **Factory reset in Storage.** A confirm-dialog-guarded action that clears the
+  locally-saved UI preferences and reloads — without touching your voices,
+  projects, or generated audio on disk.
+- **Proactive, highlighted "Install" affordance for translation engines.** When
+  you pick a Dub translation engine whose optional package isn't installed yet
+  (e.g. Google / DeepL via `deep_translator`), the Engine selector now surfaces a
+  bright accent **Install** button *before* you hit Translate — no more
+  discovering the missing package only via a translate-time 400. On a from-source
+  install it one-click installs into the backend's own interpreter; on a
+  read-only **packaged build** it opens a popover with the exact `uv pip install …`
+  command (copy-to-clipboard), a one-click **Switch to Argos (bundled, offline)**
+  escape hatch, and a docs link. The install command is single-sourced in the
+  backend registry, so the button and the 400 error can never disagree. New guide:
+  `docs/dubbing/translation-engines.md`.
+
+- **A user pronunciation dictionary that actually changes the audio.** Settings →
+  General → Pronunciation lets you teach the engine how to say tricky words —
+  each entry replaces a term with a respelling (`GIF` → `jiff`) right before
+  synthesis, so it works on **every** engine, not just one. Scope an entry
+  Global or to a single language (a German rule never fires on an English
+  render), with longest-match-first, word-boundary-aware, case-insensitive
+  substitution. For one-offs, write `[[word|respelling]]` inline in your text —
+  it overrides the dictionary for that occurrence and never persists. A built-in
+  Test field previews the substitution with no model call. Pure text transform,
+  identical on macOS/Windows/Linux; plain text stays byte-identical, existing
+  data upgrades cleanly via an additive migration. (Expressive-TTS Spec 01)
+
+- **Live, faster-than-real-time dictation via a new sherpa-onnx ASR engine.**
+  Pick one of seven small ONNX speech-to-text models (Parakeet TDT v3/v2,
+  streaming Zipformer EN/ZH/bilingual, streaming Paraformer, multilingual
+  Whisper Tiny) for dictation, and watch text appear *as you speak*. Streaming
+  models emit partials frame-by-frame and commit a sentence on natural silence;
+  offline models surface live partials too by re-decoding a growing buffer.
+  Runs CPU-only and identically on macOS, Windows, and Linux — no GPU, no cloud,
+  no extra setup beyond a ~75–180 MB one-time model download. Parakeet TDT v3 is
+  the recommended default; existing Whisper/MLX/NeMo dictation engines are
+  untouched and still the fallback.
+
+- **New "Voice" settings panel for live dictation.** Settings → Capture now
+  leads with a Voice card: an Enable Voice Dictation toggle (showing your real
+  registered shortcut), a Toggle/Hold mode switch, and a Speech Model dropdown
+  that lists all seven models with offline/streaming + recommended badges, size,
+  one-line descriptions, the installed checkmark, and inline download/delete —
+  reusing the model-store download progress. Picking an uninstalled model starts
+  its download and switches to it once ready. **Toggle vs Hold** is wired for
+  both the desktop global hotkey and the in-app Ctrl/Cmd+Shift+Space fallback, so
+  the behaviour is identical on macOS, Windows, and Linux. While you speak, the
+  dictation pill shows the transcript building **live**, and words type straight
+  into the focused field *as you speak* — self-correcting with backspaces as the
+  streaming recognizer refines, with clipboard-paste as an automatic fallback.
+
+- **Tagged scripts auto-cast into a multi-voice podcast/audiobook.** Paste a
+  `[Alice] … [Bob] …` script into Stories and hit Auto-cast: it now recognizes
+  the `[Name]` tag format (alongside the existing `NAME:` screenplay and quoted
+  prose), builds the cast, and assigns a voice per character automatically.
+  Editing one line only re-synthesizes that line on export (the chapter cache
+  is content-addressed), and inline markers like `[pause]` / `[voice:…]` are
+  never mistaken for speakers. (#487)
+- **A dedicated Contact page.** Discord, email, GitHub issues, and the project
+  website (palash.dev) as clean one-tap rows, reachable from the footer — so
+  reaching the maker is never more than a click away.
+- **Live download speed, remaining size, and ETA on first-run setup.** The
+  Models & Engines step now shows `38% · 5.2 MB/s · 1.2 GB left · ~3m` while a
+  model downloads, instead of a bare "downloading…". (#657)
+- **Turn off auto-play of the preview after a render.** New Settings →
+  Appearance toggle, "Auto-play preview" (on by default) — switch it off so a
+  finished clip doesn't start playing on its own, ideal when batch-generating
+  segments. (#666)
+- **App version in the status bar, one click from updates.** A `v<version>`
+  badge sits by the network icon in the bottom bar; clicking it opens Settings →
+  Updates, and it grows a pulsing dot the moment a new version is ready to
+  install. (#671)
+
+### Changed
+
+- **Settings is now a sidebar-nav hub instead of an 11-tab strip.** The whole
+  page was rebuilt from scratch as a grouped left-rail navigator (with a
+  search/filter box) plus a scrollable content pane — the macOS System Settings /
+  VS Code layout. Settings are organized into four groups and sixteen
+  categories: **General** (Appearance · General), **Voice & Engines** (Engines ·
+  Models · Dictation · Pronunciation · Translation), **System** (Performance &
+  Device · Storage · Network · Sharing & Remote · Credentials), and **App**
+  (Updates · Privacy & Reporting · Logs · About). Every existing control keeps
+  its behavior and store/API bindings — this is a reorganization, not a rewrite.
+  Typing in the search box filters the category list and jumps to the first
+  match, and the rail collapses to a dropdown navigator below 760px so the full
+  IA stays reachable on a narrow window. Categories whose changes need a backend
+  restart (Models, Performance & Device, Sharing & Remote) carry a "restart
+  required" badge.
+
+- **The Settings pages got a full redesign — cleaner, denser, responsive.** A
+  shared design system replaces the old patchwork: a left icon nav-rail,
+  sentence-case section titles (no more debug-log uppercase), exactly one muted
+  description per row, unified toggles/inputs, full-width content with proper
+  padding, and horizontal font/theme pickers. Premium and compact instead of
+  sparse and cluttered, and it adapts cleanly to window width. (#686, #690, #696)
+- **Adding a Hugging Face token on first-run is now a one-line input right by
+  Continue.** Was a bulky card buried at the bottom of the model list; it's now a
+  compact "paste a token, Save" bar pinned next to the "Waiting for required
+  models…" button, so you can add it (for faster, authenticated downloads)
+  without scrolling. (#687, #688)
+- **First-run setup is calmer and surfaces the best models for your machine.**
+  Dimmed and tightened the setup descriptions (less wordy, more compact). The
+  "Models & engines" step now shows the **platform-tuned** optional models up-front
+  with a green "recommended" tag and their catalog note — e.g. MLX Whisper on
+  Apple Silicon, CUDA-tuned variants on NVIDIA — instead of burying every optional
+  model behind the fold (the universal long tail still folds).
+
+- **Donations now go through Ko-fi or PayPal (GitHub Sponsors removed).** GitHub
+  Sponsors isn't available, so the Support page no longer routes there: pick an
+  amount (now $10 / $20 / $50) and then choose Ko-fi or PayPal — PayPal carries
+  the amount straight into checkout. `.github/FUNDING.yml` and the README badges
+  were updated to match.
+- **Simplified the Commercial License page.** Trimmed the six-tile benefit grid
+  and FAQ down to the three things that actually drive the decision (you own the
+  output, no per-minute cost, direct support) plus one clear "request a quote"
+  contact — less wall-of-text, faster to act on.
+- **Model downloads are faster out of the box.** The built-in multi-connection
+  (segmented) downloader — parallel byte-ranges with live speed/ETA — is now on
+  by default, so the legacy-LFS path is no longer single-stream and slow. It
+  falls back to the normal download on any error, so it can never compromise a
+  correct install (`OMNIVOICE_SEGMENTED_DOWNLOAD=0` to disable). (#669)
+- **The Hugging Face token is now front-and-center on first-run.** Was a
+  collapsed "advanced" fold almost nobody opened; it's now a prominent card right
+  above Continue, framed around what it actually buys you — authenticated, faster,
+  more reliable downloads (higher rate limits, fewer stalls) — with a one-click
+  "get a free token" link. (#657, #669)
+### Fixed
+
+- **Bug reports redact more secrets and every Windows username casing.** The
+  opt-in bug-report scrubber now catches more credential shapes (JWT/Bearer,
+  Google, Slack, AWS keys, and `?token=`/`?api_key=` URL secrets), redacts
+  Windows home paths regardless of `Users`/`users` casing, and stops a superstring
+  username (`/Users/john` vs `/Users/johnny`) from leaking a fragment. The
+  prefilled-issue URL is now bounded by its *encoded* length so a large report
+  can't silently truncate. Nothing new leaves the machine — this only makes the
+  existing local-first, user-reviewed report stricter. (#856)
+
+- **A hung TTS generate can no longer brick the backend ("Can't reach the local
+  backend").** A GPU job that wedges on some Windows + CUDA setups occupies its
+  worker forever — Python can't cancel the thread — so on the 1–2 worker pools we
+  ship, one stuck job starved every other request and the next action surfaced as
+  the misleading "Can't reach the local backend" even though the process was
+  alive. ASR/dub/model-load already bounded and reset the pool on hang (#730); but
+  **every generate path** — Studio synthesis, the streaming path, batch, the dub
+  per-segment + preview render, archetype previews, and the OpenAI-compatible
+  `/v1/audio/speech` API — was still an unguarded GPU dispatch, and the residual
+  reports all failed on `generate:start (audio)`. Every one is now bounded by the
+  same wall-clock guard (`OMNIVOICE_GENERATE_TIMEOUT_S`, default 300s) that
+  abandons the wedged worker and rebuilds the pool, so capacity is restored
+  automatically and you get an actionable timeout instead of a dead backend.
+  Closes the whole class of GPU-job-hang reports (#851 — #850, #802, #755, #723,
+  #721, and the 0.3.7 cohort, all tracked in #730).
+
+- **An unsupported GPU now falls back to CPU instead of 500-ing every generate.**
+  When the installed PyTorch build has no kernels for your GPU's compute
+  capability — a too-old card (Pascal / GTX 10-series) or a too-new one
+  (Blackwell RTX 50-series on pre-cu128 wheels) — CUDA failed at launch with the
+  cryptic `CUDA error: no kernel image is available for execution`. The backend
+  now detects that up front and runs on CPU (slower, but it works), and any raw
+  occurrence is reported as "your GPU isn't supported — switch to CPU or install a
+  matching PyTorch," not a Flush-the-memory dead end. Force the GPU anyway with
+  `OMNIVOICE_FORCE_CUDA=1`. (#756)
+
+- **The "TRANSLATION FAILED" banner now dismisses and clears itself.** The Dub
+  translation-error banner used to be sticky — it survived a successful re-try and
+  never went away. It now has a close (×), auto-clears on the next corrective
+  action (re-translating, changing the engine, or installing the package), and
+  self-clears after a short timeout — fixing the whole class of translate/pipeline
+  banners that outlived the state that caused them.
+
+- **Dubbing a video URL no longer fails with "ffmpeg is not installed."** yt-dlp
+  downloads video and audio as separate streams and muxes them with ffmpeg, but
+  it only looked on PATH — so on Windows (where OmniVoice's ffmpeg is a bundled
+  sidecar / `imageio-ffmpeg` binary off PATH) the merge aborted before the dub
+  could start. yt-dlp is now pointed at the same ffmpeg OmniVoice resolves. (#712)
+- **A synth that succeeded no longer 500s because of a history-logging hiccup.**
+  If the local database somehow missed schema init, recording the clip to
+  generation history failed with *"no such table: generation_history"* and
+  surfaced as a 500 — even though the audio had already been generated and saved.
+  The write now self-heals the schema and retries, and a history-logging failure
+  never fails the generation: you get your audio regardless. (#710)
+- **Long-video dubs no longer spike RAM during assembly.** Dub generation used
+  to hold every segment's audio in memory until the whole track was mixed, so a
+  50-video batch or a single feature-length dub could exhaust RAM and crash. Each
+  segment now streams to disk as it's rendered and the final track is assembled
+  from those files via a 30s-chunk memmap writer, keeping memory flat regardless
+  of video length. Per-segment download WAVs and the final track stay correctly
+  watermarked (marked once at synthesis, no double-mark), and zero/negative-length
+  segments no longer crash the run. (#639)
+- **A corrupt or wrong-architecture native component no longer masquerades as
+  "out of memory."** A synth failure caused by a bad `.dll`/`.pyd`/`.exe` on
+  Windows (`[WinError 193] %1 is not a valid Win32 application` — e.g. torch,
+  ffmpeg, or an engine binary) was labelled *"ran out of memory — try Flush,"*
+  sending users down the wrong path. It now says the component is corrupt or
+  built for the wrong architecture and to reinstall/repair it. (#705)
+- **A "[Errno 32] Broken pipe" mid-generation no longer poses as "out of
+  memory."** When the desktop app that launched the backend closes or relaunches,
+  the backend's output pipe breaks and a synth can fail with `[Errno 32] Broken
+  pipe`. That was labelled *"ran out of memory — try Flush,"* which never helps;
+  it now tells you the backend lost its pipe and to restart the app. (#715)
+- **Settings content no longer sprawls or spills out of view.** The content
+  column capped at 1280px, so on wide windows rows stretched edge-to-edge with a
+  big empty gap between each label and its control ("too spread out"), and a few
+  panels (API keys, the shared button rows, appearance scale) used rigid pixel
+  widths that pushed controls past the card's padding on narrow content. Now the
+  content sits at a readable measure (a single `--settings-measure` token), the
+  shared button/badge rows wrap instead of overflowing, rigid widths can shrink,
+  and rows decide whether to sit side-by-side or stack based on their **actual**
+  width (a container query) — not the viewport, which the 168px nav rail skews.
+  Everything stays inside its padding, edge to edge, on every width. (#696)
+- **File drag-and-drop works on macOS again.** The app's drop zones use HTML5
+  file drops, but Tauri intercepts OS drag-and-drop by default (`dragDropEnabled`)
+  and swallowed the files before the webview saw them — most visibly on macOS
+  WKWebView, and fully broken on macOS 26 (Tahoe), where dropping a file did
+  nothing. Disabled the interception so the webview handles native HTML5 drops
+  on every platform. (#700)
+- **A misconfigured `OMNIVOICE_MODEL` no longer bricks model load with a 500.**
+  A stale or leaked TTS *engine id* (e.g. `omnivoice`) reaching the model loader
+  used to fail every launch with *"omnivoice is not a local folder and is not a
+  valid model identifier."* It now self-heals — only a real HF repo id
+  (`org/repo`) or an explicit local path is honored; anything else falls back to
+  the default with a logged warning. Every consumer of the setting routes through
+  the same resolver, so a bad value also can't silently disable model warm-up,
+  mislabel the Settings checkpoint, or get baked into an exported persona bundle.
+  (#693)
+- **ASR no longer crashes the dub/transcribe preflight when CTranslate2's native
+  library can't load.** On hardened kernels / newer glibc (e.g. WSL2) the
+  CTranslate2 `.so` is rejected with *"cannot enable executable stack"* — an
+  OSError the WhisperX/faster-whisper checks didn't catch, so it took down the
+  whole preflight. They now report the engine as unavailable and auto-detect
+  falls back to PyTorch-Whisper instead of dead-ending. (#692)
+- **A wedged transcription can no longer take the whole backend offline ("Can't
+  reach the local backend").** On some Windows + CUDA setups a whisperx/CTranslate2
+  transcribe hangs hard and never returns. Because ASR shares a small (1–2 worker)
+  GPU pool with TTS, one stuck worker starved every other request — so the next
+  thing you did (often a TTS *generate*) failed with "can't reach backend" even
+  though the process was alive. Two fixes: every transcribe path — whole-file
+  (dub whole-file, batch, live dictation) **and** the chunked dub stream — is now
+  wall-clock **bounded** like the dub QC / dictation / OpenAI paths already were;
+  and on timeout the poisoned GPU worker is **abandoned and the pool rebuilt**, so
+  capacity is restored without restarting the app. You still get an actionable
+  message (Flush VRAM / pick a smaller ASR model) for the durable fix. (#730)
+- **The stale-dub-session recovery now also covers the first upload/ingest, not
+  just retry/import.** A dubbing job that vanished server-side during the initial
+  transcribe flow showed the scary *"Job not found … report a bug"* toast; it
+  now resets gracefully and invites a fresh upload, like the other paths. (#695)
+- **In-app preview of finished audiobooks/stories now plays on Windows.**
+  The preview decoded the entire render into one in-memory PCM buffer via Web
+  Audio `decodeAudioData`, which fails on long-form `.m4b`/AAC under WebView2
+  (`EncodingError: Unable to decode audio data`), and the blob-URL fallback can't
+  play in a Tauri `<audio>` element — so nothing played. The fallback now uploads
+  to the preview endpoint (ffmpeg-extracts a streamable WAV) and plays the HTTP
+  URL, the same path video previews use. Short TTS previews are unchanged. (#653)
+
+- **First-run setup splash no longer shows a raw `bootstrap.lines` key in English.**
+  The log-line counter string was present in 4 locales but missing from the `en`
+  reference, so English (and 16 other locales falling back to it) rendered the
+  literal key instead of "{{count}} lines". Added it to `en`. Also removed 160
+  dead `gallery.cat_*` keys (renamed to `archetypes.use_*` long ago) orphaned
+  across 20 non-English locales, clearing the i18n orphan-key advisory.
+
+- **Backend no longer hangs on startup (unreachable, no error) on Apple-Silicon Macs.**
+  The MCP session manager could hang on its anyio task group during lifespan
+  startup (observed on M1, #632); because that start was awaited before the server
+  began serving, "Application startup complete" never fired and the whole backend
+  was unreachable. The MCP start is now timeout-bounded (`OMNIVOICE_MCP_START_TIMEOUT_S`,
+  default 30s) — a hang becomes a logged warning and the backend serves normally
+  without MCP, instead of wedging. (#632)
+
+- **Dubbing a URL no longer fails with `[Errno 22] Invalid argument` on Windows.**
+  yt-dlp stamps the downloaded file's modified-time with the video's upload
+  date; an out-of-range/invalid timestamp makes the `os.utime` call raise
+  `[Errno 22]` and aborts the whole URL ingest. OmniVoice downloads to a throwaway
+  file and never uses its mtime, so it now skips the stamp entirely
+  (`updatetime=False`). (#642)
+
+- **Dubbing a YouTube link that 403s now retries with a different player
+  client.** Some videos serve their formats signature-protected to the default
+  player client, so the media download fails with `HTTP Error 403: Forbidden`
+  even though extraction worked — and a plain retry keeps 403ing. The URL
+  download now escalates the YouTube player client (tv → android → web_safari)
+  on a 403, which commonly bypasses it, before surfacing the actionable error.
+  (#625)
+- **A synth glitch that produced unreadable audio is now caught instead of a
+  misleading "out of memory".** A numerical glitch in the model (seen on Apple
+  Silicon/MPS) could leave NaN/∞ samples, which wrote a WAV that then failed
+  decoding with an opaque `ffmpeg returned error code: 183 / Invalid data` — and
+  the generic error handler labelled it "ran out of memory". Non-finite samples
+  are now sanitized to silence before any encode (so the WAV is always
+  decodable), and a genuine decode failure is reported as "unreadable audio —
+  Flush and regenerate", not OOM. (#629)
+- **A silent startup hang now leaves a diagnostic instead of nothing.** On some
+  setups the backend could load all model weights and then hang forever before
+  "Application startup complete" — no error, no crash, an unusable app (reported
+  as a Mac M1 hang after `Loading weights: 527/527`, #632). A startup watchdog
+  now dumps every thread's stack to the error log if startup stalls past a
+  window (default 5 min, `OMNIVOICE_STARTUP_WATCHDOG_S` to tune, `0` to disable),
+  so the deadlock is captured rather than invisible. It's disarmed the instant
+  startup finishes, so a normal (even slow-first-download) boot never trips it.
+  (#632)
+- **First-run demo voice is back.** The bundled demo clip
+  (`backend/assets/samples/demo_voice.wav`) was a build artifact that never got
+  committed, so it shipped absent — onboarding logged "Demo audio not found" and
+  seeded nothing, leaving a brand-new install with an empty Launchpad and no
+  `/demo_audio` route. The clip is now committed (it's already un-ignored and
+  bundled via the Tauri `backend` resource), so first-run seeds the demo voice
+  on every platform; onboarding still degrades gracefully (with a regenerate
+  hint) if it's ever absent. (#621)
+- **Multi-speaker dubbing: two speakers' turns merged onto one line are now
+  split apart.** Segmentation groups words into sentences *before* diarization
+  runs, so a back-and-forth exchange could land in a single segment; the speaker
+  pass then only *relabelled* that segment with its majority speaker, losing the
+  turn boundary (the second half of #486; the per-speaker voice auto-assign was
+  fixed earlier in #490). A new post-diarization pass re-splits any segment whose
+  words span more than one speaker at the word-level boundary, assigning each
+  piece its own speaker. Single-speaker segments pass through **byte-for-byte
+  unchanged**, so single-speaker dubs and their timing never move, and a lone
+  mis-attributed word (diarization noise) is smoothed rather than causing a
+  spurious split. (#486)
+- **Designed voices saved with a bad style no longer render wrong or crash
+  generation.** A designed voice could persist an `instruct` the engine
+  validator rejects — either the literal `"[object Object]"` from an old build,
+  or freeform prose typed into the style field — which made every generation or
+  dub that used the voice fail with `Unsupported instruct items found in …`
+  (surfacing to users as a 400/500 and, when it tore down mid-render, "Can't
+  reach the local backend"). The previous fix only *blanked* `"[object Object]"`,
+  which silently dropped the design — so an Indonesian **female** voice came out
+  **male**. Now the stored instruct is sanitized down to valid tags at every
+  seam (save, edit, and when a profile drives Generate or Dub), and when the
+  stored value is unusable the tags are **rebuilt from the design's saved
+  category picks (`vd_states`)** so the intended gender/age/pitch/accent survive.
+  A migration (0007) heals existing poisoned profiles in place — no reinstall,
+  no manual fix. (#550 #571 #594 #596)
+- **"Transcribe stream dropped … Likely ASR backend failed to load" now shows
+  the *real* reason.** When transcription failed to load its ASR model (the
+  reported case was WhisperX on Windows — typically a faster-whisper /
+  CTranslate2-cuDNN mismatch, a missing model download, or the torch-2.6
+  weights-only VAD regression), the UI dead-ended on a generic "stream dropped"
+  message with no actionable cause. Two root causes: (1) WhisperX loads lazily
+  *inside* transcription, so the load failure was buried in per-chunk errors and
+  retried on every chunk; the transcribe pre-flight now eagerly loads the ASR
+  model (new `ASRBackend.ensure_loaded()`), surfacing the genuine cause once, up
+  front, as a structured error. (2) Pre-flight and audio-load errors closed the
+  SSE stream with a bare `error` and no terminal `done`, so the browser's native
+  EventSource connection-drop could race and win against the structured error —
+  discarding the real cause and falling back to the generic message; every
+  terminal error now emits `done`, and the frontend latches the structured cause
+  so a connection drop can't overwrite it. Net: WhisperX load failures are
+  diagnosable instead of a silent dead-end. Fail-before/pass-after regression
+  test included. (#578)
+- **Dubbing: the PLAY button on the dubbed-video preview did nothing.** Same
+  autoplay-policy trap that #510 fixed for the standalone audio player, but the
+  dub editor's timeline player was missed. WaveSurfer builds its `AudioContext`
+  at mount — before any user gesture — so on Windows WebView2 (and Linux
+  Firefox/Chrome, Android Chrome) it stays `"suspended"`; `playPause()` then
+  resolves with no sound and the preview just sits there. Every playback entry
+  point in the dub timeline (the toolbar Play button and the per-segment "play
+  this slot") now resumes the context via the shared `unlockAudio()` on the
+  click before starting playback, and swallowed play() rejections are logged
+  instead of hidden. A source-contract regression test pins the invariant so a
+  future refactor can't quietly reintroduce a silent play path. macOS is
+  unaffected (its context was never blocked). (#595)
+- **Voice design: the script text field couldn't be expanded.** The Script
+  textarea was a `flex: 1` item inside a flex column, so flex-grow recomputed
+  its height on every reflow and snapped the user's drag back — `resize:
+  vertical` is silently ignored on a flex-grown item in Chromium/WebView2. The
+  field now owns its own height (starts taller, and the corner grip grows it
+  reliably on every platform). (#595)
+- **An interrupted model download now self-repairs instead of dead-ending.**
+  When the OmniVoice TTS cache was missing weight shards (the usual aftermath of
+  an interrupted first download), the next synthesize failed with a 500 and a
+  "delete the model and install it again" instruction — a manual dead-end. The
+  backend now detects the truncated-cache error on load, re-fetches just the
+  missing files via `snapshot_download` (already-present blobs are skipped, so a
+  near-complete cache repairs in seconds and a healthy cache is never touched),
+  and retries the load automatically. Offline mode (`HF_HUB_OFFLINE`) is
+  respected — repair never makes a network call the user opted out of — and if
+  the re-fetch still can't fix it, the actionable delete-and-reinstall message
+  is preserved as the fallback. (#581) The repair now also **retries** the
+  re-fetch (3 attempts, resuming each time) so a single transient blip — the very
+  thing that interrupts a download in the first place — doesn't bounce you back
+  to a manual reinstall; tune with `OMNIVOICE_MODEL_REPAIR_RETRIES`. And if a
+  resume-repair still won't load — the signature of a *corrupt* file that kept
+  its size, which a resume trusts and never re-fetches — it now **force
+  re-downloads** the model files once before giving up, so even a bit-rotted
+  cache self-heals without a manual reinstall. (#739)
+- **Dubbing a YouTube URL no longer dies on a transient "Broken pipe."**
+  Pasting a video link could fail outright with `download: Unable to download
+  video: [Errno 32] Broken pipe` — a broken pipe raised while the write side of
+  a pipe closes mid-stream (a killed ffmpeg merge child, a CDN reset during
+  muxing). yt-dlp's own per-fragment retries don't cover that case, so a single
+  transient blip aborted the whole ingest. The URL download now retries up to
+  twice on broken-pipe / network-drop failures, wiping the partial download
+  between attempts, and only surfaces the (already-actionable) "connection
+  dropped — just retry" hint after the retries are exhausted. Unsupported links
+  still fail fast with their own hint — no wasted retries. (#579, #598)
+- **`No module named 'omnivoice'` on installs whose venv lost its editable
+  record.** An interrupted or offline `uv sync` (common during an in-place
+  upgrade) could install all dependencies yet never lay the editable install of
+  the project's own `omnivoice` package — or an antivirus quarantine could
+  remove it. The venv still started uvicorn, so the bootstrap's health gate
+  passed it through, and the app only failed at the first generate/dub with
+  `No module named 'omnivoice'`. The bootstrap now also verifies `omnivoice` is
+  importable (via a cheap `find_spec`, no torch load) and forces a repair
+  `uv sync` that re-lays the editable install when it isn't; the backend also
+  resolves `omnivoice` from its bundled source tree at runtime as a safety net.
+  No reinstall needed — relaunch and it self-repairs. (#564)
+- **"cannot schedule new futures after shutdown" no longer breaks generate/dub
+  after a slow first load.** When a model load timed out, the backend reset its
+  GPU worker pool to recover — but several request handlers had captured the old
+  pool object at import time and kept submitting to it, so every subsequent
+  generate, dub, transcribe, or translate failed with `cannot schedule new
+  futures after shutdown` (a 500, or "Can't reach the local backend" when it
+  took the worker down). The GPU pool is now a single self-healing handle whose
+  worker pool is rebuilt on demand, so a reset can never strand an in-flight or
+  later request. No settings change; the recovery is automatic. (#589 #599)
+- **Transcription / dubbing works on Windows again.** WhisperX failed to load on
+  Windows because speechbrain's guard that suppresses stray optional-integration
+  imports used a POSIX-only path check, so a `k2_fsa` import error aborted the
+  whole transcription. Fixed cross-platform — covers the entire class of optional
+  integrations, not just k2. (#630 #611 #647)
+- **A slow transcription no longer looks like a dead backend.** Whole-file
+  transcribe paths (dub QC, dictation, OpenAI-compat) ran unbounded, so a
+  VRAM-starved `large-v3` could spin for minutes and hold a GPU worker — surfacing
+  as "Can't reach the local backend". They're now time-bounded and return a clear,
+  actionable 504 (free VRAM / pick a smaller ASR model / use CPU) instead of
+  hanging. New troubleshooting section documents it. (#656)
+- **Windows preview playback fixed.** The audiobook/clone preview's streaming
+  fallback fetched `localhost`, which on Windows resolves to IPv6 and missed the
+  IPv4-only backend — so previews failed with "decode error" / "no supported
+  sources". The preview API now targets `127.0.0.1` (matching the main client),
+  and the expected decode→stream fallback is logged calmly instead of as a scary
+  error. (#653 #659)
+- **A stale dub session resets cleanly instead of erroring.** Reopening the Dub
+  tab after the backend restarted tried to resume a job that no longer existed and
+  surfaced "Job not found" as a bug-report error. It now quietly clears the dead
+  session and invites a fresh upload. (#660)
+- **A bad voice-style instruct is a clear 400, not a scary 500.** Typing free-form
+  prose (or a non-English description) into the style/instruct field returned a
+  500 telling you to Flush for memory you never ran out of; it now returns a clean
+  400 that lists the valid style tags. The Voice Clone UI also drops unrecognized
+  style text locally and generates anyway. (#664 #612)
+- **The ⊕ Insert token popover stays on screen.** On Voice Clone it could grow
+  tall enough to clip off the top of the window; it's now a compact, scrollable
+  box anchored above the button. (#672)
+- **First-run no longer hangs on Apple Silicon.** The MCP session-manager startup
+  is now timeout-bounded so a slow/stuck mount can't wedge the whole backend boot
+  on M1. (#632)
+
+### CI
+
+- **Feature-coverage test system.** A backend route-inventory test diffs all 213
+  HTTP/WebSocket endpoints against a committed snapshot (plus a critical-endpoint
+  guard and a route-count floor), and a frontend feature-coverage test asserts
+  every app mode is wired to a page and every feature has its i18n namespace — so
+  an endpoint or page silently disappearing now fails CI on every PR.
+- **`bun desktop` no longer kills its own dev backend.** The dev launcher runs the
+  API and the Tauri app side-by-side, but the app's backend manager would "take
+  ownership" of port 3900 and kill the API the moment it booted (before it was
+  healthy), tearing the whole session down. The dev app now sets
+  `TAURI_SKIP_BACKEND` so it attaches to the running API instead of fighting it —
+  production launch is unaffected. (#745)
+
+## [0.3.7] — 2026-06-20
+
+A stabilization release that clears the wave of issues reported on the 0.3.6
+line — across voice design, dubbing, transcription, install, and the Linux/web
+UI — and lands two more opt-in cloning engines. The throughline is **non-English
+correctness and cross-platform playback**: cloned and designed voices now hold
+their language end-to-end, and audio plays inline in Linux/Android browsers,
+not just macOS. It also carries the v0.3.6 startup-crash fixes, so anyone still
+hitting "Can't reach the local backend" on v0.3.5/v0.3.6 only needs to update.
+
+### Added
+
+- **Two opt-in heavyweight TTS engines: MOSS-TTS-v1.5 (8B) and dots.tts (2B).**
+  Both are zero-shot voice-cloning engines, each running in its own isolated
+  subprocess venv (they pin a `transformers` version that conflicts with the
+  parent's `>=5.3` — MOSS `==5.0`, dots.tts `==4.57`) via the same dedicated-venv
+  pattern as IndexTTS-2, so they can't disturb the default install or its
+  lockfile. Point `OMNIVOICE_MOSS_TTS_V15_DIR` / `OMNIVOICE_DOTS_TTS_DIR` at a
+  local clone to enable. CUDA/CPU only — neither claims Apple-Silicon MPS, and
+  dots.tts is gated off on Windows (upstream is Linux/macOS only). See
+  [docs/engines/moss-tts-v15.md](docs/engines/moss-tts-v15.md) and
+  [docs/engines/dots-tts.md](docs/engines/dots-tts.md). (#498)
+
+### Fixed
+
+- **Non-English voices drifted to English / the wrong language.** Three
+  independent root causes, all in the language path: (1) a voice profile's
+  stored language was never read back into generation, so a German archetype
+  that *previewed* in German *generated* in English (the preview passed the
+  language; the user's Generate call didn't); (2) the audiobook/longform synth
+  hardcoded `language=None`, letting the engine re-autodetect per chunk so a
+  non-English clone could flip language mid-render on short/ambiguous lines; and
+  (3) the duration estimator weighted Unicode combining marks at zero, so
+  decomposed (NFD) diacritic text — common for Vietnamese — under-allocated
+  frames and came out rushed. The profile/request language is now threaded
+  through both the single-shot and longform paths (request wins, profile fills
+  the gap), and text is NFC-normalized before duration estimation. Each fix has
+  a fail-before/pass-after regression test. (#533, #505, #502)
+- **Audio playback on Linux Firefox/Chrome and Android Chrome.** Two separate
+  root causes both masquerade as "the play button doesn't work" on non-macOS
+  browsers — and both are invisible when developing on macOS, which is why they
+  shipped. (1) The backend served `.wav` / `.flac` with Python's default
+  `audio/x-wav` / `audio/x-flac` (vendor-experimental, never IANA-registered);
+  macOS CoreAudio MIME-sniffs leniently and plays anyway, but Linux FFmpeg and
+  Android ExoPlayer strictly honor the declared type and prompt to download.
+  Fixed by registering the canonical `audio/wav` / `audio/flac` types before
+  any `StaticFiles` mount. (2) WaveSurfer's `AudioContext` is constructed at
+  component-mount time — i.e. before any user gesture — so on Linux FF/Chrome
+  and Android Chrome it stays `suspended`, `decodeAudioData` hangs, the
+  `ready` event never fires, and the play button never enables. macOS
+  Safari/Chrome auto-resume on first interaction. Fixed by patching
+  `window.AudioContext` to track every instance and resuming them on the first
+  `pointerdown` / `keydown` / `touchstart`, plus resuming inline on the play
+  click itself. The MIME fix has a backend regression test; the unlock path
+  has a Vitest unit test covering idempotency, post-unlock contexts, and
+  error isolation. (#510)
+- **Voice Studio "Save design as profile" poisoned the profile with
+  "[object Object]" and then 400'd every generation** ("Unsupported instruct
+  items found in [object Object]"). The save passed the instruct *builder
+  object* to the form instead of its string. Fixed at the source + defended with
+  a coercion helper; the engine now tolerates the sentinel, and a migration
+  heals already-saved profiles. (#550, #545, #542, #537, #530, #525)
+- **Profile / persona / consent endpoints 500'd with `no such column:
+  consent_audio_path`** (and the same class for `kind`/`vd_states`/…) after an
+  in-place upgrade. The alembic migration existed but couldn't always apply
+  (stamped at a removed revision, or alembic not importable) and the failure was
+  swallowed. The runtime schema now self-heals — it ADDs any missing additive
+  column from the canonical schema on startup. (#552, #547)
+- **Stories: the global reading-speed slider was ignored by preview and stem
+  export.** The #415 global speed only flowed through the full longform export;
+  per-segment preview and stem export still resolved a hardcoded `track.speed ||
+  1.0`, so audio played at 1.0× even with the global set to e.g. 0.70×. A shared
+  `effectiveSpeed(track, global)` helper (per-line override → global → engine
+  default) now drives all three generation paths. (#508)
+- **Generate / Settings / Clone buttons were missing / unpressable on Linux.**
+  The UI-scale fix round-trips correctly on Chromium, but older WebKitGTK treats
+  `zoom` as a layout no-op, leaving a ~23% black band that pushed the bottom CTAs
+  off-screen. The shell now probes the engine and fills the window when `zoom`
+  doesn't lay out. (#523, #524)
+- **Settings tabs with little content rendered as a stunted box in a black
+  void** (reported on Appearance). The page is now a flex column with a
+  min-height floor — short tabs fill the panel, tall tabs grow and scroll
+  exactly as before. The Appearance panel's previously hardcoded English
+  strings ("UI scale", "Color theme", "Font") were also routed through i18n,
+  per the localization rule. (#507)
+- **The engine "Install" button 500'd with "No virtual environment found."**
+  `uv pip install` now targets the running interpreter (`--python
+  sys.executable`) instead of relying on a venv it couldn't auto-discover.
+  (#529, #527)
+- **Transcription failed with "no segments" on GPUs without efficient float16.**
+  Both CTranslate2 ASR backends now fall back float16 → int8 instead of crashing
+  at model load; a transcribe stream can no longer close without a terminal
+  error event; and an incomplete `transformers` install reports an actionable
+  message instead of "Could not import module 'AutoFeatureExtractor'".
+  (#551, #549, #516)
+- **Audiobook import 500'd** with `'AudiobookPlan' object has no attribute
+  'chapter_count'` for every format (.txt/.md/.epub/.pdf). (#543)
+- **Windows: generated audio auto-played in a separate, un-closeable black
+  window.** Renders now play in-app through the shared playback manager. (#532)
+- **Cryptic video-download errors** now carry actionable hints: an unsupported
+  link shape ("paste a direct video page, not a share/feed link") vs a transient
+  network drop ("just retry — the partial download was cleaned up"). (#554, #536)
+- **A relocated, copied, or restored backend venv ("No module named
+  'encodings'") now self-heals** (rebuilds once) instead of failing on every
+  launch.
+- **The donate goal bar showed fabricated progress** ($137.50 / $200, 23
+  sponsors). It now reflects the real figures ($10 / $200, 1 sponsor) in both the
+  runtime JSON and the TypeScript fallback. (#513)
+- The **"Can't reach the local backend" startup-crash wave** (pkg_resources
+  #248, `scalar_fastapi` #307, exit-106 broken venv) was fixed in v0.3.6 — this
+  release carries those fixes, so updating from v0.3.5/older resolves them.
+
+### Changed
+
+- **Version is now single-sourced from `frontend/package.json`.** Five
+  hand-maintained literals drifting is exactly what shipped a 0.3.6 build that
+  called itself 0.3.5. `package.json` is canonical (vite already injects it as
+  `__APP_VERSION__`), `tauri.conf.json` reads its bundle version from it
+  (`"version": "../package.json"`), and the remaining toolchain-required mirrors
+  (Cargo.toml, pyproject.toml, the frozen-backend fallback) are CI-guarded to
+  stay in lockstep. (#503)
+- **Updater: the Preview channel actually tracks `main` again.** It was stuck at
+  `0.3.5-41` because its only build trigger was a manual dispatch; a nightly
+  rebuild now enforces "preview = main" (no-opping on days `main` didn't move).
+  Two latent hazards are closed: the `preview` release is re-asserted as a
+  prerelease every run (a non-prerelease preview could hijack the Stable
+  channel's "Latest"), and its manifest can no longer silently drop the
+  Intel-Mac (darwin-x86_64) target. (#500)
+
+### Internal
+
+- **The frozen desktop backend reported `0.3.5` regardless of its real version.**
+  In a synced env, `core.version.APP_VERSION` resolves from package metadata
+  (correct, so CI stayed green), but the PyInstaller-frozen build has no
+  `.dist-info`, hit `PackageNotFoundError`, and fell back to a hardcoded literal.
+  The spec now bundles `omnivoice` metadata so the primary path works frozen too,
+  and the resolution chain is metadata → pyproject → named fallback. This also
+  fixes **About → Version rendering blank** in the web/Pinokio build (no Tauri,
+  backend idle), which now falls back to the build-time version. (#501)
+
+## [0.3.6] — 2026-06-16
+
+A large release (168 commits since v0.3.5). The headline is the **Longform
+suite** — produce full audiobooks and multi-voice stories from text, EPUB, or
+PDF — alongside a real **engine-routing** layer that tells you up front when an
+engine will fall back to CPU instead of finding out mid-synth. Dubbing,
+first-run, and install reliability all get a pass too.
+
+### Added
+
+- **Longform: Stories + Audiobook editors.** Two new tabs turn long text into
+  finished audio. **Audiobook** takes a script (or imports plain text / EPUB /
+  PDF), auto-splits it into chapters, and renders a chaptered `.m4b` with
+  metadata, cover art, and per-chapter preview/resume. **Stories** is a
+  multi-voice editor — assign a different voice per line, preview, and export
+  the whole thing through the same server-side renderer. Both share one render
+  core (loudness, metadata, cover art) and one live SSE progress stream, and
+  you can convert a project between Story and Audiobook in place.
+  (#402, #403, #404, #408, #409, #411, #412, #413, #426, #435, #436, #447)
+- **Longform: PDF & EPUB ingest.** "Import" on the Audiobook tab accepts EPUB
+  and PDF (not just plain text) and auto-chapters the result, so an existing
+  ebook becomes an audiobook without manual copy-paste. (#412, #459)
+- **Longform: two-pass loudnorm mastering.** Audiobook/Story exports now run a
+  measure-then-normalize loudnorm pass for accurate ACX/podcast loudness
+  targets. A slow or broken measure pass degrades gracefully to single-pass
+  rather than aborting the render. (#449, #455)
+- **Longform: crash-resume.** An interrupted render is resumable without
+  re-submitting the original input — the compiled plan is persisted to the job
+  dir and finished chapters are reused, so a crash mid-book doesn't cost you the
+  whole render. (#470)
+- **Longform: pronunciation control + SSML-lite prosody.** A per-render
+  pronunciation lexicon (word respelling) plus an in-app pronunciation editor
+  and markup reference, and inline prosody markers — `[slow]` / `[fast]` /
+  `[emphasis]` / `[spell]` — for fine-grained delivery. (#419, #421, #422)
+- **Stories: global reading-speed control.** A toolbar slider (0.5–2.0×) sets
+  one speed for every line that doesn't have its own per-line override; the
+  per-line slider still wins. Persisted as a UI preference. (#415, #416)
+- **Unified LongformProject store.** Audiobook metadata, scripts, and prefs
+  persist in a single project store (with a `v4→v5` migration), and finished
+  books/stories now show up alongside other work in **Projects**. (#417, #443,
+  #444)
 - **Portable personas (`.ovsvoice`).** Export any voice as a self-contained,
   fully-local persona bundle — identity, optional reference clip, consent
   attestation, SPDX license, and a watermarked preview — and import it back into
@@ -17,6 +761,183 @@ The bundled TTS model package (`pyproject.toml`) is versioned independently.
   be forged by hand-editing a bundle (real recording + consent text + attestation
   required). Legacy `.omnivoice` files still import. See
   [docs/persona-format.md](docs/persona-format.md). (#29)
+- **Engine routing — no more silent CPU fallback.** A host device probe and
+  routing resolver now decide where each engine actually runs, and the verdict
+  is surfaced before you hit Synthesize: the **Settings → Engines** picker shows
+  a per-engine compatibility matrix, and **preflight** / **diagnose** report the
+  active engine's GPU verdict (accelerated / caveat / CPU-fallback /
+  unavailable). At synth time every TTS entry point (`/generate`,
+  `/v1/audio/speech`) enforces the same routing — an engine that can't use this
+  host's GPU returns an explicit error or an `X-OmniVoice-Routing` header instead
+  of silently dropping to CPU or dying mid-synth. (#21)
+- **Diagnostics suite.** New self-check tooling for when something's wrong: a
+  `/system/diagnose` report (and matching backend `--diagnose`), a persistent
+  **error journal** surfaced in Settings, and a scrubbed **diagnostic bundle**
+  (home dirs stripped to `~/`, no tokens/keys) you can attach to a bug report.
+  Paired with structured GitHub **Issue Forms** (bug / install / feature) for
+  cleaner reports. (#433, #456)
+- **Dubbing: multi-speaker per-speaker voice assignment.** When diarization
+  detects multiple speakers, each segment is now bound to its speaker's cloned
+  voice automatically instead of landing on "Default" and needing manual fixes;
+  per-segment reference clips are still preferred for quality where present. Also
+  adds an optional speaker-count hint for diarization. (#275, #486, #490)
+- **Dubbing: Smart Fit timing + second-pass QC.** A Smart Fit timing strategy
+  (planner, fingerprints, per-segment video retime + drift absorption + fitted
+  subtitles) plus a second-pass ASR QC that flags lines whose dub drifts from the
+  target timing — wired into the dub editor UI. Includes a timeline segment
+  editor (drag, snap-to-onset, keyboard a11y), speech-onset alignment, regional
+  dialect targeting, and per-segment clone references. (#280, #347, #350, #369,
+  #370, #458)
+- **Dubbing: dedicated Dub home.** A projects/history landing for dubbing with
+  project rename. (#435)
+- **Voice Console workspace.** Clone and Design are consolidated into one Voice
+  workspace with right-side panels, a shared waveform player, an identity recipe
+  line / Active-voice card, and a free-text "describe your voice" field that maps
+  natural language to design parameters. (#317, #374, #376, #378, #395, #396,
+  #397)
+- **Unified first-run setup.** Nothing installs until you confirm a plan: pick an
+  install mode (installed / portable), a storage location, and (on restricted
+  networks) custom PyPI/HF/python-build-standalone mirrors — with a
+  minimum-free-space gate before anything downloads. Followed by a guided
+  studio-console wizard with platform-aware hints, resume reassurance, and
+  download ETAs. (#286, #295, #297, #298)
+- **Dictation: local-LLM refinement.** Opt-in local-LLM cleanup of final
+  transcripts (collapsing Whisper hallucination loops), available on both live
+  dictation and the REST `/transcribe` path; plus opt-in NLMS acoustic echo
+  cancellation for dictating over playback. Configure a remote LLM endpoint
+  (Ollama / vLLM / LM Studio) in Settings. (#356, #357, #363, #399, #400, #457)
+- **Unlimited-length TTS + streaming.** Sentence-boundary chunking with
+  crossfade removes the per-generation length cap, and a new sentence-by-sentence
+  `/ws/tts` streams audio as it's produced. An inline `[pause Nms]` marker
+  inserts measured silence in generated speech. (#276, #357, #358)
+- **MCP server v1.** OmniVoice mounts an MCP server on `/mcp` (with a stdio shim
+  and per-agent voice binding) so it can act as a local TTS/STT provider for
+  agentic pipelines. (#368)
+- **Remote-backend access.** Point the desktop UI at a remote backend URL with a
+  bearer key (Tailscale-documented), and an opt-in Hugging Face token field in
+  the setup flow. (#303, #364)
+- **"Fund Claude Max" support experience.** The donate page gets a real goal bar
+  with a "Join N supporters" social-proof line and suggested amounts, plus Pip
+  the mascot and a non-blocking "postcard" toast that appears only *after* a
+  success (a finished dub, a saved clone, a longform export) — never on errors,
+  setup, or first run — with escalating cooldowns and a one-click "don't ask
+  again". (#494)
+
+### Fixed
+
+- **Transcription/dubbing failed when ffmpeg wasn't on `PATH`** (notably on
+  Windows). WhisperX now decodes audio through OmniVoice's own validated ffmpeg
+  binary instead of a bare `PATH` lookup, so ASR works without a system ffmpeg
+  install. (#479)
+- **Translation defaulted the source language to English.** Dubbing/translation
+  now guesses the source language from the text instead of assuming `en`,
+  fixing wrong-direction translations. (#478)
+- **Cinematic / LLM dubbing features failed out of the box** because `openai`
+  wasn't bundled. The client is now a runtime dependency, so those paths work on
+  a fresh install. (#484)
+- **`pkg_resources missing` install dead-end (#248).** The auto-repair ran
+  `uv pip install setuptools`, which `uv` treated as a no-op when setuptools
+  *metadata* was present but its files had been removed (commonly by Windows
+  Defender quarantine or a partial extract). Both repair sites now use
+  `--reinstall` to force re-extraction, and the error/hint text suggests the
+  working command plus an antivirus-exclusion note. (#248)
+- **A stuck backend trapped users on a buttonless splash (#474).** The bootstrap
+  splash now has a per-stage stall watchdog: if a non-terminal stage sits past
+  its budget (20 min for dep install, 120 s otherwise), it flips to the failed
+  state with actionable hints, the live log, and Retry / Clean-&-Retry — instead
+  of polling forever with no way out. (#474)
+- **Changing the model-download location in Settings had no effect (#480).** The
+  desktop launcher injected a stale models dir that overrode the per-user value,
+  so new downloads kept going to the old folder and "Effective location" stayed
+  wrong. The per-user env file now wins, so the in-app Settings path is
+  authoritative. (#480)
+- **Backend crashed on app upgrade with a stale venv (#307).** Dependencies are
+  now synced on upgrade, and a structurally broken venv self-heals instead of
+  exiting `106`. `scalar_fastapi` is now optional so its absence can't break
+  startup. (#307, #314)
+- **`/generate` ignored the selected TTS engine (#312)** and GGUF speech-control
+  parameters weren't forwarded — both now honored. (#306, #312)
+- **TTS generation failed on some GPUs.** `torch.compile` failures now fall back
+  to eager execution so generation never hard-fails on unsupported GPUs, and
+  cudagraph-compiled inference is pinned to one dedicated thread to avoid
+  crashes. (#278, #315)
+- **Re-dub ignored transcript edits (#281).** Fingerprints are canonicalized, the
+  preview cache is busted, and the mux is atomic, so editing the transcript and
+  re-dubbing actually reflects your changes. Translated subtitles now burn in
+  correctly and subtitle save no longer throws a JSON error. (#281, #309)
+- **macOS: app wouldn't open without using Terminal.** Builds are now ad-hoc
+  signed (with signing/notarization verification), so the app launches normally.
+  (#290)
+- **macOS dictation auto-paste stole focus**; it now writes the clipboard
+  natively without grabbing focus, and microphone-permission handling adds OS
+  usage descriptions, a WebView grant handler, and an actionable denied-state UI.
+  (#287, #323)
+- **Clone-reference transcription was broken** (it used a removed transformers
+  pipeline); it now routes through the ASR registry. A crash-isolated
+  faster-whisper subprocess backend keeps an ASR crash from taking down the app.
+  (#308, #393)
+- **Realtime status probe hit a gated route.** It now probes the auth-exempt
+  `/health` instead of the gated `/model/status`, and the UI polls the backend
+  over HTTP before opening the WebSocket to avoid startup `ECONNREFUSED`. (#439,
+  #450)
+- **Non-executable or unreachable engine binaries showed cryptic errors** — these
+  now produce actionable messages. (#437, #438, #454, #466)
+- **Design-profile save was coupled to a TTS render (#476)**, so saving a profile
+  needlessly triggered synthesis; the two are now decoupled. (#476)
+- **UI scale / black bands.** The app shell now scales via `transform: scale` and
+  always fills the viewport, fixing the WebKitGTK black-band issue on Linux and
+  cramped/black layouts at narrow widths — a permanent fix across platforms.
+  (#445, #452)
+- **Clone popover/CTA clipping and a non-resizable textarea** are fixed, the
+  WaveformPlayer no longer pauses itself on play or ignores clicks, and several
+  layout/history-display issues (phantom sidebar gap, title clamping, flicker)
+  are cleaned up. (#379, #384, #398, #481)
+- **Windows: `desktop-prod` now runs from cmd/PowerShell** via a cross-platform
+  launcher, `tqdm` is disabled on non-TTY to avoid an `OSError`, and ffmpeg
+  validation guards against `WinError 193`. (#282, #305, #377)
+- **MLX import hardened** against PyInstaller dylib failures, with a proper
+  platform gate so it's only loaded where it works. (#390)
+
+### Changed
+
+- **Restricted-network support.** A Hugging Face mirror (`HF_ENDPOINT`) setting,
+  custom PyPI / HF / python-build-standalone mirrors in first-run setup, and
+  region presets help installs complete behind restrictive networks. (#286, #391)
+- **Engine memory management.** Subprocess-engine sidecars now unload on demand
+  and idle-reap to free VRAM. (#401, #406)
+- **Faster, more accurate model downloads** via a Xet fast path with accurate
+  progress reporting, plus a model-management cleanup pass. (#424, #428)
+- **Voice profiles unified** under one model with a `kind` discriminator and
+  stored design params, and consent-locked profiles (`verified_own_voice` +
+  spoken-consent flow). (#354, #376)
+- **Updater** preview channel now offers the newest build across channels, and
+  preview versions carry an MSI-legal numeric pre-release stamp. (#293, #326)
+- **Performance.** Voice-clone prompt embeddings are cached, and dub retime
+  batches seek to their window instead of decoding from frame 0. (#387, #427)
+
+### License
+
+- **Relicensed from FSL-1.1-ALv2 to AGPL-3.0 (open-core).** The project is now
+  under the GNU Affero General Public License v3, with a paid commercial license
+  retained for proprietary/closed-source use without AGPL obligations. The
+  bundled `omnivoice/` TTS model package stays Apache-2.0 upstream
+  (AGPL-compatible). Manifests declare `AGPL-3.0-only`; the in-app Commercial
+  License copy and README are updated, and the old "converts to Apache 2.0 after
+  two years" FAQ is removed. In-app commercial-license strings are translated
+  across all 20 locales. (#292)
+
+### CI
+
+- **macOS Intel (x86_64) build target reinstated** on `macos-15-intel`, so Intel
+  Mac users get installers again. (#342)
+- **Docker Hub publishing.** Images now also publish to Docker Hub
+  (`palashdeb/omnivoice-studio`), with the Docker Hub overview maintained in-repo
+  and auto-synced from `main` (sync is non-fatal so it can't redden a build).
+  (#375, #410, #414)
+- **Docs-drift guard.** A daily job compares the canonical feature inventory
+  against README / docs / registries to catch stale docs. (#353)
+- **Security scans never cancel on `main`,** so merge trains no longer leave red
+  ✗ on intermediate commits. (#340)
 
 ## [0.3.5] — 2026-06-03
 

CLAUDE.md

@@ -190,14 +190,16 @@ Everything else (new engines, fancy features) is downstream of "the thing instal
 <!-- GSD:conventions-start source:CONVENTIONS.md -->
 ## Conventions
 
-**Versioning (hard rule, owner-set 2026-06-11):** main is always **latest release + 1 patch**. The moment `vX.Y.Z` is released, main's version files (`frontend/src-tauri/tauri.conf.json`, `frontend/src-tauri/Cargo.toml`, `pyproject.toml`, **and `frontend/package.json`** — keep all **four** in lockstep; `package.json` drives the runtime `__APP_VERSION__` via vite, shown in the first-run footer + every auto bug report, so a drift ships a build that misreports its own version — guarded by `tests/test_app_version.py::test_all_version_files_in_lockstep`) bump to `X.Y.(Z+1)`. Consequences:
+**Versioning (hard rule, owner-set 2026-06-11; single-source 2026-06-16):** main is always **latest release + 1 patch**. **`frontend/package.json` is the SINGLE SOURCE OF TRUTH for the app version** — vite injects `__APP_VERSION__` from it (first-run footer + every auto bug report), and `frontend/src-tauri/tauri.conf.json` reads its bundle version from it (`"version": "../package.json"`, so the MSI/dmg/updater version can't drift from the UI). Three toolchain-required **mirrors** are kept equal to it and bumped in lockstep — `frontend/src-tauri/Cargo.toml` + `pyproject.toml` (cargo/uv need a literal) and `backend/core/version.py`'s `_FALLBACK_VERSION` (the frozen-backend last resort; at runtime the backend reads its version from package metadata via `importlib.metadata`, which `backend.spec`'s `copy_metadata('omnivoice')` makes work in the frozen build too). Never hand-edit any mirror or re-hardcode a literal in `tauri.conf.json`. Guarded by `tests/test_app_version.py` (`test_all_version_files_in_lockstep` + `test_tauri_version_derives_from_package_json`). The moment `vX.Y.Z` is released, bump `package.json` (+ the mirrors) to `X.Y.(Z+1)`. Consequences:
 - Every PR and preview build identifies as the **next** version. Preview builds stamp `X.Y.(Z+1)-N` (run number), which semver-sorts **above** the last stable `X.Y.Z` — the updater ordering is natural, no comparator tricks needed.
-- Releasing = tag `vX.Y.(Z+1)` from main (version files already match), then immediately bump main to `X.Y.(Z+2)`. The post-release bump is automated by the `version-bump` job in release.yml; if it fails, do it manually in the same day.
+- Releasing = tag `vX.Y.(Z+1)` from main (version files already match), then immediately bump main to `X.Y.(Z+2)`. **Owner override (2026-07-01): the post-release bump is now MANUAL — the `version-bump` job in release.yml is opt-in behind the `AUTO_VERSION_BUMP` repo variable (default off), so `main` stays at the released version until the owner explicitly asks to bump.** (Historically the bump auto-ran; re-enable that by setting `AUTO_VERSION_BUMP=true`.) When pinned, `main` == the released tag; preview-build ordering and "release + 1" only resume once a bump is requested.
 - Docker: `ghcr.io/debpalash/omnivoice-studio:latest` = **main** (rolling preview); `:X.Y.Z` + `:X.Y` + `:stable` = tagged releases. `:latest` is the preview channel by design — stable users pin `:stable` or a version tag.
 - Do not bump minor/major or invent RCs/codenames without the owner asking. No "defer to next version" labels — scope is absorbed or declined, never re-versioned.
 
 **Docs-sync (hard rule, owner-set 2026-06-11):** any change that alters something these docs describe — README.md, CONTRIBUTING.md, SECURITY.md, SUPPORT.md, LICENSE, or `docs/**` (install flows, Docker tag semantics, platform support, versioning/release behavior, review process, supported versions) — must update those docs **in the same PR** as the change. If a doc impact is discovered after merge, the docs fix is the immediate next commit, not backlog. Stale docs are treated as bugs.
 
+**Release notes / changelog (hard rule, owner-set 2026-06-16):** every tagged release gets a **high-quality, user-facing `## [X.Y.Z] — DATE` section in `CHANGELOG.md`** before (or in the same hour as) the tag — never the "Auto-generated release for vX.Y.Z…" fallback. `release.yml` extracts that section verbatim as the GitHub Release body (the `Extract CHANGELOG section for tag` step), so a missing/empty section ships a bare release. Quality bar = the existing house style: a one-paragraph headline, then `### Added` / `### Fixed` / `### Changed` / `### License` / `### CI` subsections; each entry is a **bold one-line lead** (what the user gets), 1–3 lines of plain-English why, and the `(#NNN)` issue/PR ref — grouped by theme, written for users, **not** raw commit dumps. This applies to **preview builds too**: preview release notes summarize what's new on `main` since the last stable, in the same style. Workflow: as features merge, keep `## [Unreleased]` current; at release time rename it to the version + date. If a release was already cut with the fallback body, the next action is to backfill `CHANGELOG.md` **and** `gh release edit <tag>` the live body — not backlog.
+
 **Localization (hard rule):** No hardcoded non-English (CJK) **user-facing text** anywhere in the codebase except the translation layer (`frontend/src/i18n/`). All UI strings go through i18n (`t('...')` keys in `locales/*.json`); native language names live in `i18n/index.ts` (`LANGUAGES`). Functional CJK is allowed and tracked via the allowlist in `tests/test_no_hardcoded_cjk.py` — text-processing regexes, model/engine vocabulary & identifiers (e.g. CosyVoice speaker IDs), localized error matching, demo/eval data, and test fixtures. CI fails on any hardcoded CJK outside the allowlist; to add legitimate functional CJK, extend `_ALLOWED_FILES` there with a justification.
 
 **Fix quality (hard rule, owner-set 2026-06-16):** Fix issues *properly* and future-maintenance-proof — don't stop at the symptom. Root-cause fully, fix the whole **class** of the bug (not just the one reported instance), add a fail-before/pass-after regression test, and harden against recurrence (e.g. if a lockfile drift only fails in Docker, also make CI catch it). Go the extra mile where it durably pays off. Be token-efficient about it — extra **effort**, not extra **verbosity**: no padding, no redundant re-checks, the smallest correct change that is also recurrence-proof. Don't be shy to spend the effort a proper fix needs; do be shy about wasting tokens.

CONTRIBUTING.md

@@ -159,7 +159,7 @@ class MyEngineBackend(TTSBackend):
 
 - **Components**: Functional components with hooks
 - **State**: Zustand stores in `src/stores/`, organized by slice
-- **CSS**: Vanilla CSS in component-level files — no Tailwind
+- **CSS**: **Utilities-first + shadcn/ui, one stylesheet.** UI is built on the shadcn/ui primitives in `src/components/ui/` (wrapped by the `src/ui/` barrel, themed to the OmniVoice palette), composed with Tailwind v4 utility classes. **All styling now lives in a single file — `src/index.css`**: the `@theme` / `[data-theme]` token foundation plus the irreducible set utilities can't express (`@keyframes`, glassmorphism/`backdrop-filter`, pseudo-elements, `:has()`, unlayered cascade overrides, and styling hooks on library-generated DOM like virtualized rows / WaveSurfer). The per-component `.css` files were eliminated in the CSS→Tailwind/shadcn migration — **do not create new ones.** Reach for shadcn primitives + utilities; if a rule is genuinely irreducible, add it to `src/index.css` with a provenance comment. (The only other `.css` is the test-only visual harness. See `docs/shadcn-migration.md`.)
 - **Naming**: `PascalCase` for components, `camelCase` for hooks and utils
 
 ### Rust (Tauri)
@@ -169,6 +169,30 @@ class MyEngineBackend(TTSBackend):
 
 ---
 
+## Frontend file structure & size limits
+
+Frontend code stays modular so an edit loads one small file, not a 1900-line
+one. The rules:
+
+- **Size caps:** **soft 300 lines**, **hard 500 lines** per `.jsx` file.
+  Anything over 500 lines must be split. (The cap does **not** apply to
+  `src/index.css` — it is the single, intentional styling foundation and the
+  only app stylesheet; see the CSS rule above.)
+- **Pages are thin orchestrators.** A file in `frontend/src/pages/` is just
+  layout + routing + state wiring that composes feature components — no inline
+  sub-component over ~50 lines.
+- **One component per file.** Co-locate `Foo.jsx` + `Foo.test.jsx` together in a
+  per-page feature folder under `frontend/src/components/` (e.g.
+  `components/settings/`, `components/dub/`). Styling is **not** co-located —
+  it's utilities + shadcn, with any irreducible rules in `src/index.css`.
+- **Shared bits go in a `primitives/` folder** inside the feature folder
+  (`components/settings/primitives/` is the existing example).
+- **Enforced by ESLint `max-lines`** (`max: 500`) — **warn-only for now** so it
+  never breaks CI, with the goal of upgrading to `error` once the backlog of
+  oversized files clears.
+
+---
+
 ## Commit Messages
 
 Write clear, concise messages. The PR title becomes the squash-merge commit.

README.md

@@ -4,34 +4,27 @@
   <h3>The open-source ElevenLabs alternative.</h3>
   <p>Real-time dictation, zero-shot voice cloning, and cinematic video dubbing — all on your desktop.<br/>Open-source, no API keys, fully local. <b>646 languages.</b></p>
 
-  <p>
-    <a href="https://github.com/debpalash/OmniVoice-Studio/stargazers"><img src="https://img.shields.io/github/stars/debpalash/OmniVoice-Studio?style=flat-square&color=f59e0b" alt="Stars" /></a>
-    <a href="https://github.com/debpalash/OmniVoice-Studio/releases/latest"><img src="https://img.shields.io/github/v/release/debpalash/OmniVoice-Studio?style=flat-square&color=10b981" alt="Release" /></a>
-    <a href="LICENSE"><img src="https://img.shields.io/badge/license-AGPL--3.0-blue?style=flat-square" alt="License" /></a>
-    <a href="https://github.com/debpalash/OmniVoice-Studio/issues"><img src="https://img.shields.io/github/issues/debpalash/OmniVoice-Studio?style=flat-square&color=ef4444" alt="Issues" /></a>
-    <a href="https://discord.gg/bzQavDfVV9"><img src="https://img.shields.io/badge/Discord-Join_Community-5865F2?style=flat-square&logo=discord&logoColor=white" alt="Discord" /></a>
-  </p>
-
   <p>
     <a href="#quickstart">Quickstart</a> ·
     <a href="#features">Features</a> ·
-    <a href="#why-omnivoice-studio">Why OmniVoice Studio?</a> ·
+    <a href="#why-ovs">Why OVS</a> ·
     <a href="#tts-engines">TTS Engines</a> ·
     <a href="#asr-engines">ASR Engines</a> ·
+    <a href="#sponsors">Sponsors</a> ·
+    <a href="#sponsor--donate">Donate</a> ·
     <a href="#contributing">Contributing</a> ·
     <a href="https://discord.gg/bzQavDfVV9">Discord</a> ·
     <a href="README_CN.md"><strong>简体中文</strong></a>
   </p>
 
   <p>
-    <a href="https://github.com/debpalash/OmniVoice-Studio/releases/latest"><img src="https://img.shields.io/badge/macOS-DMG_(Apple_Silicon)-000?style=for-the-badge&logo=apple&logoColor=white" alt="Download macOS DMG" /></a>
-    <!-- Pre-built macOS bundle is Apple Silicon. Intel Macs: build from source (docs/install/macos.md); a pre-built Intel target is tracked in #279. -->
-    <a href="https://github.com/debpalash/OmniVoice-Studio/releases/latest"><img src="https://img.shields.io/badge/Windows-MSI_(x64)-0078D4?style=for-the-badge&logo=windows&logoColor=white" alt="Download Windows MSI" /></a>
-    <a href="https://github.com/debpalash/OmniVoice-Studio/releases/latest"><img src="https://img.shields.io/badge/Linux-AppImage_(x64)-FCC624?style=for-the-badge&logo=linux&logoColor=black" alt="Download Linux AppImage" /></a>
-    <a href="https://github.com/debpalash/OmniVoice-Studio/releases/latest"><img src="https://img.shields.io/badge/Debian-.deb-A81D33?style=for-the-badge&logo=debian&logoColor=white" alt="Download Debian .deb" /></a>
-  </p>
-  <p>
-    <sub><b>macOS:</b> first launch needs a one-time approval — right-click → <b>Open</b> (or System Settings → Privacy &amp; Security → <b>"Open Anyway"</b> on macOS 15). No Terminal needed. <a href="docs/install/macos.md#gatekeeper-quarantine">Why?</a></sub>
+    <a href="https://github.com/debpalash/OmniVoice-Studio/stargazers"><img src="https://img.shields.io/github/stars/debpalash/OmniVoice-Studio?style=flat-square&color=f59e0b" alt="Stars" /></a>
+    <a href="https://github.com/debpalash/OmniVoice-Studio/releases/latest"><img src="https://img.shields.io/github/v/release/debpalash/OmniVoice-Studio?style=flat-square&color=10b981" alt="Release" /></a>
+    <a href="LICENSE"><img src="https://img.shields.io/badge/license-AGPL--3.0-blue?style=flat-square" alt="License" /></a>
+    <a href="https://github.com/debpalash/OmniVoice-Studio/issues"><img src="https://img.shields.io/github/issues/debpalash/OmniVoice-Studio?style=flat-square&color=ef4444" alt="Issues" /></a>
+    <a href="https://discord.gg/bzQavDfVV9"><img src="https://img.shields.io/badge/Discord-Join_Community-5865F2?style=flat-square&logo=discord&logoColor=white" alt="Discord" /></a>
+    <a href="https://ko-fi.com/debpalash"><img src="https://img.shields.io/badge/Ko--fi-Support_Us-FF5E5B?style=flat-square&logo=ko-fi&logoColor=white" alt="Ko-fi" /></a>
+    <a href="https://paypal.me/palashCoder"><img src="https://img.shields.io/badge/PayPal-Donate-00457C?style=flat-square&logo=paypal&logoColor=white" alt="PayPal" /></a>
   </p>
 </div>
 
@@ -58,20 +51,28 @@
 
 <table>
 <tr>
-  <td align="center" width="33%">
+  <td align="center" width="25%">
     <h3>🎙️ Voice Cloning</h3>
     <p>3-second clip → mirror any voice.<br/><b>646 languages</b>, zero-shot.</p>
   </td>
-  <td align="center" width="33%">
+  <td align="center" width="25%">
     <h3>🎨 Voice Design</h3>
     <p>Gender, age, accent, pitch, speed,<br/>emotion, dialect — <b>dial it in</b>.</p>
   </td>
-  <td align="center" width="33%">
+  <td align="center" width="25%">
     <h3>🎬 Video Dubbing</h3>
     <p>YouTube URL or file → transcribe →<br/>translate → re-voice → <b>MP4</b>.</p>
   </td>
+  <td align="center" width="25%">
+    <h3>📖 Audiobook Editor</h3>
+    <p>Import text, EPUB, or PDF. Auto-chapter,<br/>loudnorm, metadata. Export <b>.m4b</b>.</p>
+  </td>
 </tr>
 <tr>
+  <td align="center" valign="top">
+    <h3>🎭 Stories</h3>
+    <p>Multi-voice editor. Assign voices<br/>per-line, preview, <b>export full cast</b>.</p>
+  </td>
   <td align="center" valign="top">
     <h3>⌨️ Dictation Widget</h3>
     <p><code>⌘+⇧+Space</code> from <b>any app</b>.<br/>Transcribes, auto-pastes, disappears.</p>
@@ -98,6 +99,10 @@
     <h3>🛡️ AI Watermark</h3>
     <p>AudioSeal (Meta). <b>Invisible</b>,<br/>survives compression.</p>
   </td>
+  <td align="center" valign="top">
+    <h3>🔬 Diagnostics</h3>
+    <p>Self-check, error journal,<br/>scrubbed <b>diagnostic bundle</b>.</p>
+  </td>
 </tr>
 <tr>
   <td align="center" valign="top">
@@ -110,7 +115,29 @@
   </td>
   <td align="center" valign="top">
     <h3>🧩 Extensible</h3>
-    <p>Subclass <code>TTSBackend</code>,<br/>add any engine in <b>~50 lines</b>.</p>
+    <p>Subclass <code>TTSbackend</code>,<br/>add any engine in <b>~50 lines</b>.</p>
+  </td>
+  <td align="center" valign="top">
+    <h3>🧭 Engine Routing</h3>
+    <p>Preflight GPU check per engine.<br/><b>No silent CPU fallback</b>.</p>
+  </td>
+</tr>
+<tr>
+  <td align="center" valign="top">
+    <h3>🎒 Portable Personas</h3>
+    <p>Export voices as <code>.ovsvoice</code><br/>bundles — identity + <b>watermark</b>.</p>
+  </td>
+  <td align="center" valign="top">
+    <h3>♾️ Unlimited TTS</h3>
+    <p>Sentence-chunked generation.<br/><b>No length cap</b>. Streaming via WS.</p>
+  </td>
+  <td align="center" valign="top">
+    <h3>🌐 Remote Backend</h3>
+    <p>Point UI at a remote server.<br/>Tailscale-friendly. <b>Bearer auth</b>.</p>
+  </td>
+  <td align="center" valign="top">
+    <h3>🧠 Dictation + LLM</h3>
+    <p>Local LLM cleanup of transcripts.<br/>Optional echo <b>cancellation</b>.</p>
   </td>
 </tr>
 </table>
@@ -119,6 +146,17 @@
 
 ## Quickstart
 
+<div align="center">
+  <a href="https://github.com/debpalash/OmniVoice-Studio/releases/latest"><img src="https://img.shields.io/badge/macOS-DMG_(Apple_Silicon)-000?style=for-the-badge&logo=apple&logoColor=white" alt="Download macOS DMG" /></a>
+  <a href="https://github.com/debpalash/OmniVoice-Studio/releases/latest"><img src="https://img.shields.io/badge/Windows-MSI_(x64)-0078D4?style=for-the-badge&logo=windows&logoColor=white" alt="Download Windows MSI" /></a>
+  <a href="https://github.com/debpalash/OmniVoice-Studio/releases/latest"><img src="https://img.shields.io/badge/Linux-AppImage_(x64)-FCC624?style=for-the-badge&logo=linux&logoColor=black" alt="Download Linux AppImage" /></a>
+  <a href="https://github.com/debpalash/OmniVoice-Studio/releases/latest"><img src="https://img.shields.io/badge/Debian-.deb-A81D33?style=for-the-badge&logo=debian&logoColor=white" alt="Download Debian .deb" /></a>
+  <br/>
+  <sub><b>macOS:</b> first launch needs a one-time approval — right-click → <b>Open</b> (or System Settings → Privacy &amp; Security → <b>"Open Anyway"</b> on macOS 15). No Terminal needed. <a href="docs/install/macos.md#gatekeeper-quarantine">Why?</a></sub>
+  <br/>
+  <sub><b>Intel Macs are not supported for the local backend:</b> the app UI installs, but the Python backend cannot run because PyTorch no longer ships Intel-Mac (x86_64) wheels (<a href="https://github.com/debpalash/OmniVoice-Studio/issues/889">#889</a>) — see <a href="docs/install/macos.md">docs/install/macos.md</a>.</sub>
+</div>
+
 Per-OS install guides — pick yours and follow it end-to-end:
 
 - **macOS** — [docs/install/macos.md](docs/install/macos.md)
@@ -191,7 +229,7 @@ options, see [docs/downloading-models.md](docs/downloading-models.md).
 
 ---
 
-## Why OmniVoice Studio?
+## Why OVS?
 
 ElevenLabs charges **$5–$330/mo** and processes your audio on their servers. OmniVoice Studio runs **on your hardware, with no usage limits.**
 
@@ -200,12 +238,17 @@ ElevenLabs charges **$5–$330/mo** and processes your audio on their servers. O
 | **Pricing** | $5–$330/mo, per-character billing | Free & open-source (AGPL-3.0) · [Commercial license](#license) for proprietary use |
 | **Voice Cloning** | ✅ 3s clip | ✅ 3s clip, zero-shot |
 | **Voice Design** | ✅ Gender, age | ✅ Gender, age, accent, pitch, style, dialect |
+| **Audiobook / Stories** | ❌ | ✅ Full audiobook editor + multi-voice stories (EPUB/PDF import, .m4b export) |
 | **Languages** | 32 | **646** |
 | **Video Dubbing** | ✅ Cloud-only | ✅ Fully local |
 | **Data Privacy** | Audio sent to cloud | **Nothing leaves your machine** |
 | **API Keys** | Required | Not needed |
 | **GPU Support** | N/A (cloud) | CUDA · Apple Silicon · ROCm · CPU |
 | **Desktop App** | ❌ | ✅ macOS · Windows · Linux |
+| **TTS Engines** | 1 | **11** (OmniVoice, CosyVoice 3, GPT-SoVITS, VoxCPM2, MOSS-TTS-Nano, KittenTTS, MLX-Audio, Sherpa-ONNX, IndexTTS 2, OmniVoice GGUF, Supertonic 3) |
+| **ASR Engines** | 1 | **9** (WhisperX, Faster-Whisper, MLX Whisper, PyTorch Whisper, Parakeet, Moonshine, FunASR, isolated Faster-Whisper, sherpa-onnx live dictation) |
+| **MCP Server** | ❌ | ✅ Use from Claude, Cursor, any MCP client |
+| **Self-check** | ❌ | ✅ Diagnostics suite, error journal, scrubbed debug bundles |
 | **Customizable** | ❌ Closed | ✅ Fork it, extend it, ship it |
 
 OmniVoice Studio gives you professional-grade AI tools without the subscription or the cloud.
@@ -223,7 +266,7 @@ OmniVoice Studio gives you professional-grade AI tools without the subscription
 
 | | **Minimum** | **Recommended** |
 |---|---|---|
-| **OS** | Windows 10, macOS 12+, Ubuntu 20.04+ | Any modern 64-bit OS |
+| **OS** | Windows 10, macOS 12+ (Apple Silicon), Ubuntu 20.04+ | Any modern 64-bit OS |
 | **RAM** | 8 GB | 16 GB+ |
 | **VRAM (GPU)** | 4 GB (auto-offloads TTS to CPU) | 8 GB+ (NVIDIA RTX 3060+) |
 | **Disk** | 10 GB free (models + cache) | 20 GB+ SSD |
@@ -233,6 +276,9 @@ OmniVoice Studio gives you professional-grade AI tools without the subscription
 > [!TIP]
 > On GPUs with **≤8 GB VRAM**, OmniVoice automatically offloads TTS to CPU during transcription — no config needed. A dedicated GPU is not required; the entire pipeline runs on CPU (just slower).
 
+> [!IMPORTANT]
+> **macOS Intel (x86_64) is unsupported for the local backend:** the app UI installs, but the Python backend cannot run because PyTorch no longer ships Intel-Mac wheels ([#889](https://github.com/debpalash/OmniVoice-Studio/issues/889)). Intel-Mac users can still point the UI at a remote backend on another machine — see [docs/install/macos.md](docs/install/macos.md).
+
 ### TTS Engines
 
 OmniVoice ships a multi-engine TTS backend. The default engine (OmniVoice) is always available; additional engines are opt-in and auto-detected. Switch engines in **Settings → TTS Engine** or via the `OMNIVOICE_TTS_BACKEND` env var.
@@ -241,12 +287,22 @@ OmniVoice ships a multi-engine TTS backend. The default engine (OmniVoice) is al
 |--------|:---------:|:-----:|:--------:|:-----:|:---------:|:-------:|:-------:|
 | **OmniVoice** (default) | 600+ | ✅ | ✅ | ✅ CUDA/CPU | ✅ MPS | ✅ CUDA/CPU | Built-in |
 | **CosyVoice 3** | 9 + 18 dialects | ✅ | ✅ | ✅ CUDA/CPU | ✅ MPS | ✅ CUDA/CPU | Apache-2.0 |
-| **MLX-Audio** (Kokoro, Qwen3-TTS, CSM, Dia, …) | Multi | Varies | Varies | ❌ | ✅ Native | ❌ | Varies |
+| **GPT-SoVITS** | 5 | ✅ | — | ✅ CUDA/CPU | — | ✅ CUDA/CPU | MIT |
 | **VoxCPM2** | 30 | ✅ | ✅ | ✅ CUDA/CPU | ✅ MPS | ✅ CUDA/CPU | Apache-2.0 |
-| **MOSS-TTS-Nano** | 20 | ✅ | ❌ | ✅ CUDA/CPU | ✅ CPU | ✅ CUDA/CPU | Apache-2.0 |
-| **KittenTTS** | English | ❌ | ❌ | ✅ CPU | ✅ CPU | ✅ CPU | MIT |
+| **MOSS-TTS-Nano** | 20 | ✅ | — | ✅ CUDA/CPU | ✅ CPU | ✅ CUDA/CPU | Apache-2.0 |
+| **KittenTTS** | English | — | — | ✅ CPU | ✅ CPU | ✅ CPU | MIT |
+| **MLX-Audio** (Kokoro, Qwen3-TTS, CSM, Dia, …) | Multi | Varies | Varies | ❌ | ✅ Native | ❌ | Varies |
+| **Sherpa-ONNX** | 20+ | — | — | ✅ CUDA/CPU | ✅ CPU | ✅ CUDA/CPU | Apache-2.0 |
+| **IndexTTS 2** ⚡ | Multi | ✅ | — | ✅ CUDA | — | ✅ CUDA | Apache-2.0 |
+| **OmniVoice GGUF** ⚡ | 600+ | ✅ | ✅ | ✅ CPU | ✅ CPU | ✅ CPU | Built-in |
+| **Supertonic 3** ⚡ | 31 | — | — | ✅ CPU | ✅ CPU | ✅ CPU | OpenRAIL-M |
+| **MOSS-TTS-v1.5** ⚡ (8B) | 31 | ✅ | — | ✅ CUDA/CPU | ✅ CPU | ✅ CUDA/CPU | Apache-2.0 |
+| **dots.tts** ⚡ (2B) | 24 | ✅ | — | ✅ CUDA/CPU | ✅ CPU | ❌ | Apache-2.0 |
+| **Confucius4-TTS** ⚡ | 14 | ✅ | — | ✅ CUDA/CPU | ✅ CPU | ✅ CUDA/CPU | Apache-2.0 |
 
-> **CUDA** = GPU-accelerated · **MPS** = Apple Silicon Metal · **CPU** = runs everywhere, slower for large models · KittenTTS and MOSS-TTS-Nano run realtime on CPU · MLX-Audio is Apple Silicon only.
+> **CUDA** = GPU-accelerated · **MPS** = Apple Silicon Metal · **CPU** = runs everywhere, slower for large models · KittenTTS and MOSS-TTS-Nano run realtime on CPU · MLX-Audio is Apple Silicon only · ⚡ = lazy-registered (installed on first use)
+>
+> **MOSS-TTS-v1.5** (8B, ~16 GB weights) and **dots.tts** (2B, ~9 GB weights) are heavyweight opt-in engines that run in their own isolated venv from a local clone — see [MOSS-TTS-v1.5](docs/engines/moss-tts-v15.md) and [dots.tts](docs/engines/dots-tts.md). Neither claims Apple-Silicon **MPS** (upstream is CUDA/CPU only; on a Mac they run on CPU). dots.tts upstream is Linux/macOS only — no Windows path. **Confucius4-TTS** (14-language cross-lingual zero-shot cloning) is similar — its own Python 3.10 venv from a clone; CUDA recommended, CPU validated end-to-end (slow, ~17× realtime; no MPS — tested slower than CPU); see [Confucius4-TTS](docs/engines/confucius4-tts.md).
 
 ### ASR Engines
 
@@ -256,31 +312,36 @@ OmniVoice ships a multi-engine ASR (speech-to-text) backend that powers dictatio
 |--------|-------------------------|:---------:|----------|
 | **WhisperX** (default) | `whisperx` | ~100 | Dubbing & subtitles — word-level timing via wav2vec2 forced alignment |
 | **Faster-Whisper** | `faster-whisper` | ~100 | Fast transcription on Linux / macOS / Windows (CTranslate2) |
+| **Faster-Whisper (isolated)** | `faster-whisper-isolated` | ~100 | Same as Faster-Whisper but crash-isolated in a subprocess — an ASR crash won't take down the app |
 | **MLX Whisper** | `mlx-whisper` | ~100 | Native Apple Silicon speed (Apple MLX / Metal) |
-| **PyTorch Whisper** | `pytorch-whisper` | ~100 | CUDA / CPU fallback via 🤗 Transformers |
-| **Parakeet TDT** | `nemo-parakeet` | English + 25 EU | SOTA English accuracy, auto language detection (NVIDIA NeMo, GPU only) |
+| **PyTorch Whisper** | `pytorch-whisper` | ~100 | CUDA / CPU fallback via 🤗 Transformers (no cuDNN 8 needed) |
+| **Parakeet TDT** | `nemo-parakeet` | English + 25 EU | SOTA accuracy at ~10× realtime even on CPU, auto language detection (NVIDIA NeMo, CUDA/CPU) |
 | **Moonshine** | `moonshine` | English | Edge / low-latency, ONNX |
 | **FunASR** | `funasr` | 50+ | All-in-one multilingual — built-in VAD + inline speaker diarization (SenseVoice) |
+| **sherpa-onnx** (live dictation) | `sherpa-onnx-asr` | 25 EU + 90+ | Live, faster-than-real-time dictation — small streaming/offline ONNX models (Parakeet TDT v3/v2, streaming Zipformer & Paraformer, Whisper Tiny), CPU, identical on macOS / Windows / Linux. Picked per-model in **Settings → Voice**. |
 
-> Whisper-family engines cover ~100 languages; **FunASR / SenseVoice** adds an all-in-one multilingual path with built-in voice-activity detection and inline speaker diarization. Every engine runs on-device — no API keys, no cloud.
+> Whisper-family engines cover ~100 languages; **FunASR / SenseVoice** adds an all-in-one multilingual path with built-in voice-activity detection and inline speaker diarization. **sherpa-onnx** powers the live dictation model picker — you talk and text appears as you speak. Every engine runs on-device — no API keys, no cloud.
+
+> **GPU without efficient float16?** On older NVIDIA GPUs (Maxwell/Pascal, GTX 16xx) or after a CTranslate2/cuDNN mismatch, the CTranslate2 ASR engines (WhisperX, Faster-Whisper) can't run `float16` and OmniVoice automatically retries on `int8` — no config needed. If transcription still fails, pin the compute type with the `ASR_COMPUTE_TYPE` env var (escape hatch): `ASR_COMPUTE_TYPE=int8` (or `float32` for CPU). Set it to `int8` and restart the backend.
 
 ---
 
 ## Architecture
 
 ```
-┌─────────────────────────────────────────────────┐
-│                  Frontend (React)                │
-│  DubTab · VoicePreview · BatchQueue · Gallery    │
-├─────────────────────────────────────────────────┤
-│                Backend (FastAPI)                  │
-│  97 API endpoints · SSE streaming · SQLite       │
-├──────────┬──────────┬──────────┬────────────────┤
-│ WhisperX │  Demucs  │OmniVoice │   Pyannote     │
-│   ASR    │  Source  │   TTS    │  Diarization   │
-│          │  Sep.    │          │                │
-└──────────┴──────────┴──────────┴────────────────┘
-        CUDA / MPS / ROCm / CPU (auto-detected)
+┌─────────────────────────────────────────────────────────────┐
+│                    Frontend (React)                          │
+│  DubTab · VoiceConsole · Stories · Audiobook · Gallery     │
+│  Dictation · BatchQueue · Diagnostics · MCP Client          │
+├─────────────────────────────────────────────────────────────┤
+│                  Backend (FastAPI)                           │
+│  100+ API endpoints · SSE+WSS streaming · SQLite            │
+├──────────┬──────────┬──────────┬──────────┬────────────────┤
+│ WhisperX │  Demucs  │OmniVoice │ Pyannote │ Engine Routing  │
+│  (+7 ASR │  Source  │  (+10    │ Diariz-  │ ↳ GPU preflight │
+│ engines) │  Sep.    │  TTS)    │ ation    │ ↳ No silent CPU │
+└──────────┴──────────┴──────────┴──────────┴────────────────┘
+         CUDA / MPS / ROCm / CPU (auto-detected + routed)
 ```
 
 ---
@@ -291,27 +352,71 @@ OmniVoice ships a multi-engine ASR (speech-to-text) backend that powers dictatio
 
 | Category | Features |
 |----------|----------|
-| **Dubbing** | Full pipeline (transcribe→translate→synthesize→mux), scene-aware splitting, lip-sync scoring, streaming TTS |
-| **Voice** | Zero-shot cloning, voice design, A/B comparison, voice preview widget, gallery with favorites/tags |
-| **Audio** | Demucs vocal isolation, per-segment gain, selective track export, stem/SRT/VTT/MP3 export |
+| **Longform** | Audiobook editor (text/EPUB/PDF → chaptered .m4b), Stories multi-voice editor, two-pass loudnorm mastering, crash-resume for interrupted renders, pronunciation control + SSML-lite prosody |
+| **Dubbing** | Full pipeline (transcribe→translate→synthesize→mux), scene-aware splitting, lip-sync scoring, streaming TTS, per-speaker voice assignment, Smart Fit timing + second-pass QC, dedicated Dub home |
+| **Voice** | Zero-shot cloning, voice design, A/B comparison, voice preview widget, gallery with favorites/tags, portable persona bundles (`.ovsvoice`), voice console workspace |
+| **Audio** | Demucs vocal isolation, per-segment gain, selective track export, stem/SRT/VTT/MP3 export, unlimited-length TTS via sentence-chunked generation |
 | **Multi-Lang** | Multi-language batch picker, batch dubbing queue with sequential GPU execution |
 | **Diarization** | Pyannote ML diarization, auto speaker clone extraction, per-speaker voice assignment |
-| **Infra** | Docker deployment, CUDA/MPS/ROCm auto-detect, cuDNN 8 compat, VRAM-aware model offloading |
+| **ASR** | 9 engines (WhisperX, Faster-Whisper, isolated Faster-Whisper, MLX Whisper, PyTorch Whisper, Parakeet TDT, Moonshine, FunASR/SenseVoice, sherpa-onnx live dictation), crash-isolated subprocess backend |
+| **TTS** | 11 engines (OmniVoice, CosyVoice 3, GPT-SoVITS, VoxCPM2, MOSS-TTS-Nano, KittenTTS, MLX-Audio, Sherpa-ONNX, + lazy: IndexTTS 2, OmniVoice GGUF, Supertonic 3), engine routing with GPU preflight |
+| **Infra** | Docker deployment, CUDA/MPS/ROCm auto-detect, cuDNN 8 compat, VRAM-aware model offloading, engine routing (no silent CPU fallback), diagnostics suite & error journal, restricted-network mirror support |
 | **AI Provenance** | AudioSeal invisible watermarking (SynthID-like), video logo overlay, watermark detection API |
-| **UX** | Undo/redo, keyboard shortcuts, drag-and-drop, session persistence, glassmorphism design system |
+| **UX** | Undo/redo, keyboard shortcuts, drag-and-drop, session persistence, glassmorphism design system, UI scale fix for Linux/WebKitGTK |
 | **Real-time Events** | WebSocket event bus — instant sidebar refresh on data mutations, exponential backoff reconnect |
 | **State Management** | Zustand store migration — `uiSlice`, `pillSlice`, `dubSlice`, `generateSlice`, `prefsSlice`, `glossarySlice` |
-| **Desktop** | Cross-platform Tauri installers (macOS DMG, Windows MSI, Linux deb/AppImage), auto-update infrastructure |
-| **Windows Hardening** | Cross-platform log paths, Triton workaround, HF symlink bypass, 300s health check timeout |
-| **Dictation** | Global system-wide hotkey (`⌘+⇧+Space`), frameless floating widget, streaming ASR via WebSocket, auto-paste |
+| **Desktop** | Cross-platform Tauri installers (macOS DMG — Apple Silicon; Intel unsupported for the local backend, #889 — Windows MSI, Linux deb/AppImage), auto-update infrastructure, single-instance enforcement, close-to-tray, macOS Gatekeeper fix |
+| **Dictation** | Global system-wide hotkey (`⌘+⇧+Space`), frameless floating widget, streaming ASR via WebSocket, auto-paste, customizable hotkey, local-LLM transcript refinement |
 | **Batch Pipeline** | Full batch TTS: extract → transcribe → translate → generate → mix → export, with live progress tracking |
+| **MCP Server** | OmniVoice as a local TTS/STT provider for Claude, Cursor, and any MCP client |
+| **Remote Backend** | Point the desktop UI at a remote backend URL with bearer auth (Tailscale-documented) |
+| **Reliability** | Stall watchdog on bootstrap splash, per-engine GPU compatibility matrix, actionable errors for non-executable engine binaries, setuptools auto-repair |
 
 ### 🔜 Up Next
 
 - 🎬 **Lip-sync v2** — visual speech timing with wav2lip
-- 📖 **Audiobook Editor** — chapter-aware long-form narration
 - 🌐 **Hosted Demo** — try OmniVoice without installing anything
 - 🔌 **Plugin Marketplace** — community-contributed TTS engines and effects
+- 🎵 **Real-time Voice Changer** — live microphone transformation during calls
+
+---
+
+## Sponsor / Donate
+
+OmniVoice Studio is built by one developer using Claude Code and AI agents — and the agent bills are real. Over the last three months I've spent thousands of dollars on Claude subscriptions to keep the features shipping, the bugs fixed, and your issues answered. If OmniVoice has created value for you, helping cover those bills means I can keep developing full-time.
+
+<div align="center">
+
+**This month's agent bill fund**
+
+<img src="https://img.shields.io/badge/raised_%2410_of_%24200-5%25-EAB308?style=for-the-badge" alt="$10 / $200 raised" />
+
+<br/><br/>
+
+<a href="https://ko-fi.com/debpalash"><img src="https://img.shields.io/badge/Ko--fi-Support_❤️-FF5E5B?style=for-the-badge&logo=ko-fi&logoColor=white" alt="Ko-fi" /></a>
+&nbsp;&nbsp;
+<a href="https://paypal.me/palashCoder"><img src="https://img.shields.io/badge/PayPal-Donate-00457C?style=for-the-badge&logo=paypal&logoColor=white" alt="PayPal" /></a>
+
+<br/>
+<sub>Every dollar goes directly to agent bills — keeping OmniVoice development continuous.</sub>
+
+</div>
+
+### Sponsors
+
+OmniVoice is **free** and **AGPL-3.0** — no paid tier, no SaaS revenue. Sponsors keep development going, and in return get a logo slot here, in the app, and (for top tiers) on the project website. It's a thank-you, never a paywall. **[See tiers & become a sponsor →](SPONSORS.md)**
+
+<div align="center">
+
+<!-- SPONSORS:START — logo slots are filled here as sponsors come aboard; see SPONSORS.md -->
+
+**Your logo here** — [become a sponsor](SPONSORS.md)
+
+<!-- SPONSORS:END -->
+
+</div>
+
+<sub>💡 GitHub also shows a **Sponsor** button at the top of this repo, wired to the same links via <a href=".github/FUNDING.yml"><code>.github/FUNDING.yml</code></a>.</sub>
 
 ---
 
@@ -356,7 +461,7 @@ For voice cloning and dubbing, yes — OmniVoice uses a state-of-the-art diffusi
 <details>
 <summary><b>Does it work on Apple Silicon (M1/M2/M3/M4)?</b></summary>
 <br/>
-Yes. MPS acceleration is auto-detected. MLX-optimized Whisper models are available for faster transcription on Apple hardware.
+Yes. MPS acceleration is auto-detected. MLX-optimized Whisper models are available for faster transcription on Apple hardware. <b>Intel Macs are not supported</b>: the app UI installs, but the local Python backend cannot run because PyTorch no longer ships Intel-Mac wheels (<a href="https://github.com/debpalash/OmniVoice-Studio/issues/889">#889</a>) — an Intel Mac can only be used with a remote backend.
 </details>
 
 <details>
@@ -380,7 +485,7 @@ Yes. MPS acceleration is auto-detected. MLX-optimized Whisper models are availab
 <details>
 <summary><b>Can I add my own TTS engine?</b></summary>
 <br/>
-Yes. OmniVoice uses a <b>built-in backend registry</b>. To add an engine in ~50 lines, subclass <code>TTSBackend</code> in <code>backend/services/tts_backend.py</code> and add it to the <code>_REGISTRY</code> dictionary at the bottom. Six engines are built in: OmniVoice, CosyVoice, MLX-Audio (14+ sub-engines), VoxCPM2, MOSS-TTS-Nano, and KittenTTS. See the <a href="#tts-engines">TTS Engines</a> section for details.
+Yes. OmniVoice uses a <b>built-in backend registry</b>. To add an engine in ~50 lines, subclass <code>TTSBackend</code> in <code>backend/services/tts_backend.py</code> and add it to the <code>_REGISTRY</code> dictionary. Eleven engines are built in: OmniVoice, CosyVoice 3, GPT-SoVITS, MLX-Audio (14+ sub-engines), VoxCPM2, MOSS-TTS-Nano, KittenTTS, Sherpa-ONNX, plus lazy-registered IndexTTS 2, OmniVoice GGUF, and Supertonic 3. See the <a href="#tts-engines">TTS Engines</a> section for details.
 </details>
 
 ---
@@ -410,6 +515,9 @@ OmniVoice Studio is built on the shoulders of exceptional open-source work:
 | [**CTranslate2**](https://github.com/OpenNMT/CTranslate2) | Optimized Transformer inference on CPU and GPU |
 | [**AudioSeal (Meta)**](https://github.com/facebookresearch/audioseal) | Invisible neural audio watermarking for AI provenance |
 | [**Tauri**](https://tauri.app) | Native desktop app framework |
+| [**Supertone / Supertonic 3**](https://huggingface.co/Supertone/supertonic-3) | ONNX TTS engine — 31 languages, CPU-efficient |
+| [**Sherpa-ONNX**](https://github.com/k2-fsa/sherpa-onnx) | WASM-ready universal TTS/ASR runtime |
+| [**GPT-SoVITS**](https://github.com/RVC-Boss/GPT-SoVITS) | Zero-shot TTS engine — 5 languages, RTF 0.014 |
 
 ---
 
@@ -419,7 +527,8 @@ OmniVoice Studio is built on the shoulders of exceptional open-source work:
 
 If you read this far, you're our kind of person.<br/>
 **[⭐ Star this repo](https://github.com/debpalash/OmniVoice-Studio)** so others can find it too.<br/>
-**[💬 Join the Discord](https://discord.gg/bzQavDfVV9)** to share what you build.
+**[💬 Join the Discord](https://discord.gg/bzQavDfVV9)** to share what you build.<br/>
+**[❤️ Support development](https://ko-fi.com/debpalash)** — fund the AI agent bills that keep OmniVoice shipping.
 
 <br/>
 

README_CN.md

@@ -372,9 +372,13 @@ OmniVoice 配备多引擎 TTS 后端。默认引擎（OmniVoice）始终可用
 | **MLX-Audio**（Kokoro, Qwen3-TTS, CSM, Dia 等） | 多语言 | 因引擎而异 | 因引擎而异 | ❌ | ✅ 原生 | ❌ | 因引擎而异 |
 | **VoxCPM2** | 30 | ✅ | ✅ | ✅ CUDA/CPU | ✅ MPS | ✅ CUDA/CPU | Apache-2.0 |
 | **MOSS-TTS-Nano** | 20 | ✅ | ❌ | ✅ CUDA/CPU | ✅ CPU | ✅ CUDA/CPU | Apache-2.0 |
+| **MOSS-TTS-v1.5**（8B，可选装） | 31 | ✅ | ❌ | ✅ CUDA/CPU | ✅ CPU | ✅ CUDA/CPU | Apache-2.0 |
+| **dots.tts**（2B，可选装） | 24 | ✅ | ❌ | ✅ CUDA/CPU | ✅ CPU | ❌ | Apache-2.0 |
 | **KittenTTS** | 英语 | ❌ | ❌ | ✅ CPU | ✅ CPU | ✅ CPU | MIT |
 
 > **CUDA** = GPU 加速 · **MPS** = Apple Silicon Metal · **CPU** = 随处可运行，大模型较慢 · KittenTTS 和 MOSS-TTS-Nano 可在 CPU 上实时运行 · MLX-Audio 仅限 Apple Silicon。
+>
+> **MOSS-TTS-v1.5**（8B，约 16 GB 权重）和 **dots.tts**（2B，约 9 GB 权重）是重量级可选引擎，从本地克隆在独立 venv 中运行——参见 [MOSS-TTS-v1.5](docs/engines/moss-tts-v15.md) 和 [dots.tts](docs/engines/dots-tts.md)。两者均不支持 Apple Silicon **MPS**（上游仅支持 CUDA/CPU；在 Mac 上以 CPU 运行）。dots.tts 上游仅支持 Linux/macOS——无 Windows 路径。
 
 ---
 

SPONSORS.md

@@ -0,0 +1,119 @@
+<div align="center">
+  <img src="docs/logo.png" alt="OmniVoice Logo" width="96" />
+  <h1>Sponsor OmniVoice Studio</h1>
+  <p><b>Keep the open-source ElevenLabs alternative free, local, and shipping.</b></p>
+</div>
+
+---
+
+## Why sponsor?
+
+OmniVoice Studio is built by one developer, in the open, using Claude Code and AI agents — and the agent bills are real. Over the last few months I've spent thousands of dollars on Claude subscriptions to keep features shipping, bugs fixed, and your issues answered.
+
+OmniVoice is **free**, **fully local**, and **AGPL-3.0**. There's no paid tier, no accounts, no cloud, and no SaaS revenue — nothing runs on a server we bill you for, because nothing runs on a server at all. That's the whole point, and it's also why there's no recurring revenue to fund development. Sponsorship is what makes continued full-time work possible.
+
+If OmniVoice has created value for you or your company, sponsoring means the next release keeps coming — and you get a thank-you (and, at most tiers, a logo slot) in return.
+
+### Where your money goes
+
+Every dollar goes to the cost of building OmniVoice — chiefly the **AI agent bills that keep it shipping** (Claude subscriptions and API usage), plus the occasional signing certificate, test hardware, and model-hosting costs. It is not a salary top-up; it's what keeps the lights on for continuous development.
+
+---
+
+## Sponsorship tiers
+
+Tiers are about **visibility and gratitude** — what you get is placement, not gated features (see [Not a paywall](#not-a-paywall)). Higher tiers include everything in the tiers below them.
+
+| Tier | Suggested monthly | What you get |
+|------|-------------------|--------------|
+| **🥉 Backer** | _set by owner_ <!-- OWNER: set amounts --> | Your name or handle listed in the **Backers** section of this file, with a link of your choice. |
+| **🟫 Bronze** | _set by owner_ <!-- OWNER: set amounts --> | Everything above, **plus** a small logo in `SPONSORS.md` **and** in the README [Sponsors section](README.md#sponsors). |
+| **🥈 Silver** | _set by owner_ <!-- OWNER: set amounts --> | Everything above, **plus** your logo in the **README** and in the app's **in-app Sponsors page footer** (as that page ships). |
+| **🥇 Gold** | _set by owner_ <!-- OWNER: set amounts --> | Everything above, **plus** a **prominent logo slot** and link on the project **website / landing page**. |
+
+> **Amounts are set by the maintainer** — look for the `<!-- OWNER: set amounts -->` markers in this file's source. If you don't see a price that fits, say so in your inquiry; custom and annual arrangements are welcome.
+
+Placements marked "as that page ships" (the in-app Sponsors page and the project website) are on the near-term roadmap. Until they exist, Silver/Gold logos live in `SPONSORS.md` and the README, and are added to the app and site the moment those land — no re-application needed.
+
+---
+
+## How to become a sponsor
+
+**1. Open a sponsorship inquiry (recommended).** This opens a short GitHub form (name/org, logo, tier, contact) so we can get you set up:
+
+> **[→ Open a sponsorship inquiry](https://github.com/debpalash/OmniVoice-Studio/issues/new?template=sponsor.yml)**
+
+**2. Or start recurring support directly:**
+
+- **Ko-fi (recurring or one-time):** [ko-fi.com/debpalash](https://ko-fi.com/debpalash)
+- **PayPal (one-time):** [paypal.me/palashCoder](https://paypal.me/palashCoder)
+
+If you sponsor via Ko-fi/PayPal and want a logo slot, still open an inquiry (or drop a note there) so we know who to credit and where to link.
+
+**3. Prefer to talk first?** Reach out directly:
+
+- Email: <!-- OWNER: add your sponsor contact email here if you want one public -->
+- Or ask in the `#dev` / `#announcements` channels on [Discord](https://discord.gg/bzQavDfVV9).
+
+---
+
+## Logo & asset guidelines
+
+To make your logo look sharp everywhere (README on GitHub, the in-app page, the website), please send:
+
+- **Format:** **SVG preferred** (scales cleanly); otherwise **PNG at 2× resolution**.
+- **Background:** **transparent** — no baked-in white/black box.
+- **Contrast:** send a variant that stays legible on **both light and dark** backgrounds, or one light-mode and one dark-mode file (GitHub and the app both render in either theme).
+- **Dimensions:** legible at **~40px tall**; keep the wordmark within roughly **480px wide**. Landscape/wordmark shapes work best in the README row.
+- **File size:** keep SVGs under ~50 KB and PNGs under ~100 KB.
+- **Link target:** the destination URL you want the logo to point to (usually your homepage).
+
+**How your logo gets added:**
+
+- **Easiest:** attach the asset and link in your [sponsorship inquiry](https://github.com/debpalash/OmniVoice-Studio/issues/new?template=sponsor.yml) — the maintainer places it.
+- **Or open a PR:** add your asset under `docs/sponsors/` and an entry to the tables in this file. Silver/Gold logos are also wired into the app's in-app Sponsors page (via the `sponsors.js` manifest) and the project website as those surfaces ship.
+
+By sponsoring you confirm you have the right to use the submitted logo and grant OmniVoice permission to display it in the contexts above. We won't alter your logo beyond scaling, and we'll remove it promptly on request.
+
+---
+
+## Current sponsors
+
+OmniVoice doesn't have any sponsors yet — **you could be the first.** These slots fill in as sponsors come aboard.
+
+### 🥇 Gold
+
+_Be the first Gold sponsor — [claim this slot](#how-to-become-a-sponsor)._
+
+### 🥈 Silver
+
+_Open — [become a Silver sponsor](#how-to-become-a-sponsor)._
+
+### 🟫 Bronze
+
+_Open — [become a Bronze sponsor](#how-to-become-a-sponsor)._
+
+### 🥉 Backers
+
+_Open — [become a Backer](#how-to-become-a-sponsor)._
+
+<!-- When a sponsor joins, add them to the matching section above:
+     - Logo tiers (Bronze+):  <a href="https://sponsor.example"><img src="docs/sponsors/name.svg" alt="Name" height="48" /></a>
+     - Backers:               - [Name / handle](https://link)  -->
+
+---
+
+## Not a paywall
+
+Sponsorship is a **thank-you, never a paywall.**
+
+Every feature of OmniVoice Studio is and will remain **free** and **open-source under [AGPL-3.0](LICENSE)**. Sponsors do **not** get private builds, gated features, license exceptions, or anything that degrades the experience for people who don't (or can't) pay. What sponsors get is **visibility and our gratitude** — and the knowledge that they're directly funding the next release.
+
+OmniVoice stays local-first and fully functional with zero dollars spent. Sponsoring just helps it keep getting better, faster.
+
+---
+
+<div align="center">
+<sub>Thank you for keeping local-first voice AI alive and free. ❤️</sub><br/>
+<sub>Questions? <a href="https://github.com/debpalash/OmniVoice-Studio/issues/new?template=sponsor.yml">Open an inquiry</a> · <a href="https://discord.gg/bzQavDfVV9">Discord</a></sub>
+</div>

backend.spec

@@ -13,12 +13,18 @@
 # Run:  uv run pyinstaller backend.spec --noconfirm --clean
 import platform
 import sys
-from PyInstaller.utils.hooks import collect_data_files, collect_all, collect_submodules
+from PyInstaller.utils.hooks import collect_data_files, collect_all, collect_submodules, copy_metadata
 
 IS_MAC_ARM = sys.platform == "darwin" and platform.machine() == "arm64"
 
 datas = []
 binaries = []
+
+# Bundle the omnivoice package's .dist-info so importlib.metadata.version()
+# resolves inside the frozen build. Without it the backend can't read its own
+# version and falls back to the literal in backend/core/version.py — which is
+# how a 0.3.6 desktop build shipped reporting "0.3.5" in About + bug reports.
+datas += copy_metadata('omnivoice')
 hiddenimports = [
     # Web stack
     'uvicorn', 'uvicorn.logging', 'uvicorn.loops', 'uvicorn.loops.auto',

backend/api/routers/archetypes.py

@@ -18,7 +18,6 @@ Design notes
 """
 from __future__ import annotations
 
-import asyncio
 import hashlib
 import logging
 import os
@@ -137,7 +136,7 @@ async def _render_archetype_wav(a: dict, out_path: Path) -> None:
     from api.routers.generation import (  # noqa: WPS433 — intentional lazy import
         get_model,
         _run_inference,
-        _gpu_pool,
+        run_on_gpu_pool_guarded,
         _safe_torchaudio_save,
     )
 
@@ -147,8 +146,6 @@ async def _render_archetype_wav(a: dict, out_path: Path) -> None:
         language = None
     text = (a.get("sample_script") or "").strip() or _FALLBACK_SCRIPT
 
-    loop = asyncio.get_running_loop()
-
     def _infer(seed: int):
         return _run_inference(
             model,          # _model
@@ -171,14 +168,18 @@ async def _render_archetype_wav(a: dict, out_path: Path) -> None:
             "broadcast",    # effect_preset
         )
 
-    audio_tensor = await loop.run_in_executor(_gpu_pool, _infer, _PREVIEW_SEED)
+    # Bounded + pool-reset on hang so a wedged preview render can't starve the
+    # GPU pool and brick the backend (#730 class).
+    audio_tensor = await run_on_gpu_pool_guarded(
+        lambda: _infer(_PREVIEW_SEED), what="Archetype preview generate")
     if _is_unusable_audio(audio_tensor):
         # Blank OR a degenerate tonal buzz — retry once on a different seed to
         # step off the bad diffusion trajectory. Static message only: the
         # archetype id is request-derived (CodeQL log-injection); the seed is a
         # module constant, safe to log.
         logger.warning("Archetype rendered unusable at seed %d — retrying once", _PREVIEW_SEED)
-        audio_tensor = await loop.run_in_executor(_gpu_pool, _infer, _PREVIEW_SEED + 1)
+        audio_tensor = await run_on_gpu_pool_guarded(
+            lambda: _infer(_PREVIEW_SEED + 1), what="Archetype preview generate")
     if _is_unusable_audio(audio_tensor):
         raise RuntimeError("the voice engine returned no audible audio for this archetype")
 

backend/api/routers/audiobook.py

@@ -164,6 +164,7 @@ async def audiobook_cover(cover: UploadFile = File(...)) -> dict:
 class AudiobookRequest(BaseModel):
     text: str
     default_voice: str | None = None   # voice profile id; None = engine default
+    language: str | None = None        # None/"Auto" → profile language, else autodetect (#505)
     bitrate: str = "128k"
     format: str = "m4b"                 # "m4b" | "mp3"
     loudness: str | None = None         # None/"off" | "acx" | "podcast" (opt-in)
@@ -215,7 +216,35 @@ def _resolve_voice(profile_id: str | None) -> dict:
     return out
 
 
-def _build_synth(default_voice: str | None) -> dict:
+def _resolve_default_language(language: str | None, default_voice: str | None) -> str | None:
+    """Pick the language to thread into the longform synth callable.
+
+    Priority (mirrors the single-shot /generate path, #533): an explicit
+    non-Auto request ``language`` wins; otherwise the selected profile's stored
+    language drives it; otherwise ``None`` (genuine Auto — the engine
+    autodetects, exactly as before). Hardcoding ``None`` here (#505 B2) let the
+    engine re-autodetect per chunk, so a non-English clone flipped to the wrong
+    language on short/ambiguous chapters.
+    """
+    if language and language != "Auto":
+        return language
+    if default_voice:
+        from core.db import db_conn
+        with db_conn() as conn:
+            row = conn.execute(
+                "SELECT language FROM voice_profiles WHERE id=?", (default_voice,)
+            ).fetchone()
+        if row:
+            try:
+                prof_lang = row["language"]
+            except (KeyError, IndexError):
+                prof_lang = None
+            if prof_lang and prof_lang != "Auto":
+                return prof_lang
+    return None
+
+
+def _build_synth(default_voice: str | None, language: str | None = None) -> dict:
     """Describe how to synthesize for the active TTS engine.
 
     Returns a dict with ``mode``, ``resolve`` (voice-id → resolved refs, cached
@@ -223,6 +252,11 @@ def _build_synth(default_voice: str | None) -> dict:
     ``get_model``; other engines carry a ready ``synth`` + ``sample_rate``.
     :func:`_prepare_synth` turns this into a uniform ``(synth, sr, resolve,
     engine_id)`` once the (async) model is in hand.
+
+    ``language`` (already resolved by :func:`_resolve_default_language`) is
+    threaded into every chunk's ``generate`` so a non-English clone stays in its
+    language instead of re-autodetecting per chunk (#505 B2). ``None`` keeps the
+    engine's autodetect behavior unchanged.
     """
     from services.tts_backend import OmniVoiceBackend, active_backend_id, get_backend_class
 
@@ -239,14 +273,14 @@ def _build_synth(default_voice: str | None) -> dict:
     if cls is OmniVoiceBackend:
         from services.model_manager import get_model
         return {"mode": "omnivoice", "resolve": resolve,
-                "engine_id": engine_id, "get_model": get_model}
+                "engine_id": engine_id, "get_model": get_model, "language": language}
 
     backend = cls()
 
     def synth(text, voice_id, speed=None):
         v = resolve(voice_id)
         return backend.generate(
-            text, language=None, ref_audio=v["ref_audio"],
+            text, language=language, ref_audio=v["ref_audio"],
             ref_text=v["ref_text"], instruct=v["instruct"], duration=None,
             speed=float(speed) if speed else 1.0,
         )
@@ -254,20 +288,22 @@ def _build_synth(default_voice: str | None) -> dict:
             "synth": synth, "sample_rate": backend.sample_rate}
 
 
-async def _prepare_synth(default_voice: str | None):
+async def _prepare_synth(default_voice: str | None, language: str | None = None):
     """Resolve :func:`_build_synth` into ``(synth, sample_rate, resolve,
     engine_id)`` — awaiting the OmniVoice model load when needed. Shared by the
-    full job and the per-chapter preview."""
-    info = _build_synth(default_voice)
+    full job and the per-chapter preview. ``language`` is threaded into every
+    chunk so a non-English clone holds its language (#505 B2)."""
+    info = _build_synth(default_voice, language=language)
     resolve, engine_id = info["resolve"], info["engine_id"]
     if info["mode"] == "omnivoice":
+        lang = info["language"]
         model = await info["get_model"]()
         sr = getattr(model, "sampling_rate", 24000)
 
         def synth(text, voice_id, speed=None):
             v = resolve(voice_id)
             return model.generate(
-                text=text, language=None, ref_audio=v["ref_audio"],
+                text=text, language=lang, ref_audio=v["ref_audio"],
                 ref_text=v["ref_text"], instruct=v["instruct"], duration=None,
                 speed=float(speed) if speed else 1.0,
             )[0]
@@ -323,6 +359,7 @@ class AudiobookPreviewRequest(BaseModel):
     text: str
     chapter_index: int = 0
     default_voice: str | None = None
+    language: str | None = None   # None/"Auto" → profile language, else autodetect
     lexicon: dict | None = None
 
 
@@ -346,7 +383,10 @@ async def audiobook_preview(req: AudiobookPreviewRequest) -> dict:
     chapter = plan.chapters[req.chapter_index]
     cache_dir = os.path.join(OUTPUTS_DIR, "longform_cache")  # shared with _render_longform_sse
     os.makedirs(cache_dir, exist_ok=True)
-    synth, sr, resolve, engine_id = await _prepare_synth(req.default_voice)
+    synth, sr, resolve, engine_id = await _prepare_synth(
+        req.default_voice,
+        language=_resolve_default_language(req.language, req.default_voice),
+    )
     loop = asyncio.get_running_loop()
     wav_path, dur, was_cached = await loop.run_in_executor(
         _gpu_pool, _render_chapter_cached, chapter, synth, sr, engine_id, resolve, cache_dir,
@@ -364,6 +404,7 @@ async def _render_longform_sse(
     plan,
     *,
     default_voice: str | None,
+    language: str | None = None,
     fmt: str = "m4b",
     bitrate: str = "128k",
     loudness: str | None = None,
@@ -412,7 +453,8 @@ async def _render_longform_sse(
                 for c in plan.chapters
             ],
             params={
-                "default_voice": default_voice, "fmt": fmt, "bitrate": bitrate,
+                "default_voice": default_voice, "language": language,
+                "fmt": fmt, "bitrate": bitrate,
                 "loudness": loudness, "cover_path": cover_path,
                 "metadata": metadata, "lexicon": lexicon,
             },
@@ -453,7 +495,9 @@ async def _render_longform_sse(
     loop = asyncio.get_running_loop()
 
     try:
-        synth, sr, resolve, engine_id = await _prepare_synth(default_voice)
+        synth, sr, resolve, engine_id = await _prepare_synth(
+            default_voice, language=_resolve_default_language(language, default_voice)
+        )
 
         total = len(plan.chapters)
         chapter_files: list[str] = []
@@ -557,7 +601,8 @@ async def audiobook_synthesize(req: AudiobookRequest):
     plan = parse_audiobook_script(req.text, default_voice=req.default_voice)
     return StreamingResponse(
         _render_longform_sse(
-            plan, default_voice=req.default_voice, fmt=req.format, bitrate=req.bitrate,
+            plan, default_voice=req.default_voice, language=req.language,
+            fmt=req.format, bitrate=req.bitrate,
             loudness=req.loudness, cover_path=req.cover_path, metadata=req.metadata,
             lexicon=req.lexicon, job_type="audiobook",
         ),
@@ -582,6 +627,7 @@ class LongformChapter(BaseModel):
 class LongformRenderRequest(BaseModel):
     chapters: list[LongformChapter] = []
     default_voice: str | None = None
+    language: str | None = None        # None/"Auto" → profile language, else autodetect (#505)
     bitrate: str = "128k"
     format: str = "m4b"
     loudness: str | None = None
@@ -612,7 +658,8 @@ async def longform_render(req: LongformRenderRequest):
     plan = AudiobookPlan(chapters=chapters)
     return StreamingResponse(
         _render_longform_sse(
-            plan, default_voice=req.default_voice, fmt=req.format, bitrate=req.bitrate,
+            plan, default_voice=req.default_voice, language=req.language,
+            fmt=req.format, bitrate=req.bitrate,
             loudness=req.loudness, cover_path=req.cover_path, metadata=req.metadata,
             lexicon=req.lexicon, job_type="story",
         ),
@@ -702,7 +749,7 @@ async def resume_longform(job_id: str):
     # never names a work dir / output file (defence-in-depth path-injection).
     return StreamingResponse(
         _render_longform_sse(
-            plan, default_voice=p.get("default_voice"),
+            plan, default_voice=p.get("default_voice"), language=p.get("language"),
             fmt=p.get("fmt", "m4b"), bitrate=p.get("bitrate", "128k"),
             loudness=p.get("loudness"), cover_path=p.get("cover_path"),
             metadata=p.get("metadata"), lexicon=p.get("lexicon"),

backend/api/routers/batch.py

@@ -142,7 +142,7 @@ async def _run_batch_pipeline(job_id: str, job: dict):
     _set_progress(job, "transcribe", 0)
 
     from services.asr_backend import get_active_asr_backend
-    from services.model_manager import _gpu_pool, _cpu_pool
+    from services.model_manager import _gpu_pool, _cpu_pool, run_on_gpu_pool_guarded
     from services.segmentation import (
         segment_transcript, assign_speakers_heuristic,
     )
@@ -162,7 +162,12 @@ async def _run_batch_pipeline(job_id: str, job: dict):
             pass
         return segments, detected_lang
 
-    segments, source_lang = await loop.run_in_executor(_gpu_pool, _transcribe)
+    # Bound the batch transcribe (#730) so a wedged whisperx/CTranslate2 call
+    # can't hold its GPU-pool worker forever and starve the rest of the backend
+    # ("can't reach backend"); run_transcribe_guarded also resets the pool on
+    # timeout to restore capacity.
+    from services.asr_backend import run_transcribe_guarded
+    segments, source_lang = await run_transcribe_guarded(_gpu_pool, _transcribe, what="Batch")
     source_lang = (source_lang or "en").split("_")[0][:2].lower()
     job["segments"] = segments
     job["source_lang"] = source_lang
@@ -311,7 +316,9 @@ async def _run_batch_pipeline(job_id: str, job: dict):
                     return torch.zeros(1, int(dur * sr))
 
             try:
-                audio_tensor = await loop.run_in_executor(_gpu_pool, _gen)
+                # Bounded + pool-reset on hang so a wedged batch segment can't
+                # starve the GPU pool and brick the backend (#730 class).
+                audio_tensor = await run_on_gpu_pool_guarded(_gen, what="Batch generate")
 
                 # Fit to slot
                 target_samples_seg = int(seg_duration * sr)

backend/api/routers/capture.py

@@ -18,7 +18,7 @@ import os
 import tempfile
 import time
 
-from fastapi import APIRouter, File, Form, UploadFile
+from fastapi import APIRouter, File, Form, HTTPException, UploadFile
 from typing import Optional
 
 router = APIRouter()
@@ -96,9 +96,17 @@ async def transcribe_audio(
             return result, backend.id
 
         from services.model_manager import _gpu_pool
-        loop = asyncio.get_running_loop()
+        from services.asr_backend import ASRTimeoutError, run_transcribe_guarded
         t0 = time.perf_counter()
-        result, engine_id = await loop.run_in_executor(_gpu_pool, _run)
+        try:
+            result, engine_id = await run_transcribe_guarded(
+                _gpu_pool, _run, what="Dictation",
+            )
+        except ASRTimeoutError as e:
+            # Backend is alive — ASR couldn't finish. 504 with guidance, not a
+            # silent hang the UI reads as "can't reach the local backend".
+            logger.warning("Capture transcription timed out: %s", e)
+            raise HTTPException(status_code=504, detail=str(e))
         elapsed = round(time.perf_counter() - t0, 2)
 
         # Normalize result shape
@@ -112,6 +120,15 @@ async def transcribe_audio(
         from services.refinement import collapse_repetitive_artifacts
         full_text = collapse_repetitive_artifacts(full_text)
 
+        # Cross-transport parity: deterministically polish the final text
+        # (leading capital + terminal punctuation) exactly like the live
+        # dictation socket (capture_ws) does, so the widget's POST fallback and
+        # MCP/CLI callers get the same typed-looking result the WS returns —
+        # not the raw "...test" the REST path used to leak. Segments stay raw
+        # (their timings/verbatim recognition are the contract).
+        from services.text_polish import polish_text
+        full_text = polish_text(full_text)
+
         # Calculate audio duration from segments if available
         duration = 0.0
         if segments:
@@ -127,8 +144,12 @@ async def transcribe_audio(
         if _truthy(refine) and full_text:
             from services.refinement import maybe_refine
             refined = await asyncio.to_thread(maybe_refine, full_text)
-            if refined and refined != full_text:
-                refined_text = refined
+            if refined:
+                # Polish the refined text too, so both surfaced strings read as
+                # typed text (mirrors the raw-vs-refined contract of the WS).
+                refined = polish_text(refined)
+                if refined != full_text:
+                    refined_text = refined
 
         logger.info(
             "Capture transcription done: engine=%s, elapsed=%.2fs, duration=%.1fs, mode=%s, refined=%s",

backend/api/routers/capture_ws.py

@@ -19,7 +19,15 @@ Protocol:
          "segments": [...], "language": "en",
          "duration_s": 4.2, "transcription_time_s": 0.8,
          "engine": "mlx-whisper"}
-        {"type": "error",   "detail": "..."}              — error
+        {"type": "status",  "stage": "downloading"|"loading"|"ready"}
+                                                          — model cold-start
+        {"type": "error",   "message": "...", "kind": "...",
+         "detail": "..."}                                  — error ("detail"
+                                                          kept for legacy)
+
+    Every ``final`` text is normalised by services.text_polish (leading
+    capital for Latin scripts, terminal punctuation, single-spaced) so the
+    pasted result reads like typed text. Partials are raw.
 """
 from __future__ import annotations
 
@@ -32,6 +40,7 @@ import time
 from fastapi import APIRouter, WebSocket, WebSocketDisconnect
 
 from api.dependencies import _LOOPBACK_HOSTS, ws_remote_authorized
+from services.text_polish import polish_text
 
 router = APIRouter()
 logger = logging.getLogger("omnivoice.capture_ws")
@@ -101,6 +110,30 @@ def _pcm16_to_wav(pcm: bytes, sample_rate: int) -> str | None:
         return None
 
 
+def _select_sherpa_spec(websocket: WebSocket):
+    """Resolve the sherpa dictation model for this WS session, or None.
+
+    A ``?model=<id>`` query param wins (the frontend can pin a model per
+    session); otherwise the persisted ``dictation.model_id`` pref is used (only
+    when dictation is enabled). Returns the :class:`SherpaModelSpec` or None
+    (None → the legacy Whisper/WebM path runs unchanged).
+    """
+    try:
+        from services import sherpa_dictation as sd
+    except Exception:
+        return None
+    requested = websocket.query_params.get("model")
+    if requested:
+        return sd.get_spec(requested)  # explicit selection (may be None if bad)
+    # Fall back to the persisted dictation pref.
+    try:
+        from services.asr_backend import dictation_model_id
+        mid = dictation_model_id()
+    except Exception:
+        mid = None
+    return sd.get_spec(mid) if mid else None
+
+
 @router.websocket("/ws/transcribe")
 async def ws_transcribe(websocket: WebSocket):
     """Stream audio in, get partial + final transcription out."""
@@ -119,6 +152,24 @@ async def ws_transcribe(websocket: WebSocket):
 
     await websocket.accept()
 
+    # Live-dictation engine selection. When a sherpa-onnx model is selected
+    # (via ?model= or the dictation.model_id pref) AND sherpa is installed,
+    # run the dedicated low-latency handler. Otherwise fall through to the
+    # legacy Whisper/WebM path, byte-for-byte unchanged.
+    spec = _select_sherpa_spec(websocket)
+    if spec is not None:
+        from services.asr_backend import SherpaDictationBackend
+        ok, _reason = SherpaDictationBackend.is_available()
+        if ok:
+            if spec.streaming:
+                await _run_sherpa_streaming(websocket, spec)
+            else:
+                await _run_sherpa_offline(websocket, spec)
+            return
+        # sherpa not installed → fall through to the legacy path so the user
+        # still gets dictation (just not live partials).
+        logger.info("sherpa dictation selected but unavailable — legacy path")
+
     # Opt-in dictate-over-playback AEC (parity Action 8b). Default OFF →
     # identical legacy behaviour. When on, frames are 1-byte-tagged raw PCM
     # and the cleaned mic stream is muxed via stdlib wave (not ffmpeg).
@@ -260,20 +311,29 @@ async def ws_transcribe(websocket: WebSocket):
     if total_bytes > MIN_FINAL_BUFFER_BYTES:
         try:
             result = await _transcribe_buffer_full(audio_chunks, pcm_sr=pcm_sr)
+            # Dictation v2: deterministic polish so the pasted final reads
+            # like typed text (leading capital, terminal punctuation).
+            result["text"] = polish_text(result.get("text", ""))
             # Wave 2.1: optional local-LLM refinement of the final text.
-            # Off-thread (network call, not GPU); pass-through on any
-            # failure or when no LLM backend is configured. The raw text
-            # always ships too — clients paste refined_text ?? text.
+            # HARD-BOUNDED (maybe_refine_async, ~4s OMNIVOICE_REFINE_TIMEOUT_S):
+            # a slow/dead LLM can never delay this `final` beyond the budget —
+            # it falls back to the unrefined (but polished) text. Best-effort:
+            # never let refinement turn a good final into an error. The raw
+            # text always ships too — clients paste refined_text ?? text.
             if result.get("text"):
-                from services.refinement import maybe_refine
-                refined = await asyncio.to_thread(maybe_refine, result["text"])
-                if refined and refined != result["text"]:
-                    result["refined_text"] = refined
+                try:
+                    from services.refinement import maybe_refine_async
+                    refined = await maybe_refine_async(result["text"])
+                    if refined and refined != result["text"]:
+                        result["refined_text"] = refined
+                except Exception as e:  # noqa: BLE001
+                    logger.debug("Dictation refinement skipped: %s", e)
             if not await _safe_send({"type": "final", **result}):
                 logger.debug("Skipped final send — client already disconnected")
         except Exception as e:
             logger.error("Final transcription failed: %s", e)
-            await _safe_send({"type": "error", "detail": str(e)})
+            await _safe_send({"type": "error", "message": str(e),
+                              "kind": "transcribe", "detail": str(e)})
     else:
         await _safe_send({
             "type": "final",
@@ -292,6 +352,413 @@ async def ws_transcribe(websocket: WebSocket):
             pass
 
 
+# ── sherpa-onnx live dictation handlers ─────────────────────────────────────
+#
+# Both handlers read raw int16 mono PCM frames (reusing the AEC framing: an
+# opt-in 1-byte type prefix when ?aec=1, else bare PCM) at ?sr= (default 16000).
+# This is the low-latency transport — no WebM/ffmpeg in the hot path.
+
+# How often the offline-kind handler re-decodes the live window for a partial
+# (streaming-kind decodes every frame, no cadence needed).
+SHERPA_OFFLINE_PARTIAL_S = float(os.environ.get("OMNIVOICE_SHERPA_OFFLINE_PARTIAL", "0.8"))
+
+# Utterance gate for the offline-kind handler: once the trailing this-many
+# seconds of the live buffer fall below the RMS floor, the utterance is
+# COMMITTED — decoded, flushed as a `final`, and dropped from the buffer. Each
+# decode is thereby bounded by one utterance instead of the whole session
+# (the old full-buffer re-decode was O(n²)), and a sentence commits ~0.6s
+# after the user stops speaking instead of only at EOF.
+SHERPA_OFFLINE_SILENCE_S = float(os.environ.get("OMNIVOICE_SHERPA_OFFLINE_SILENCE", "0.6"))
+SHERPA_OFFLINE_RMS_FLOOR = float(os.environ.get("OMNIVOICE_SHERPA_OFFLINE_RMS", "0.01"))
+
+
+def _pcm16_to_f32(pcm: bytes):
+    """int16 little-endian mono PCM bytes → float32 numpy in [-1, 1]."""
+    import numpy as np
+    if not pcm:
+        return np.zeros(0, dtype=np.float32)
+    # Guard against an odd trailing byte from a split frame.
+    if len(pcm) % 2:
+        pcm = pcm[:-1]
+    return np.frombuffer(pcm, dtype=np.int16).astype(np.float32) / 32768.0
+
+
+async def _sherpa_session(websocket: WebSocket):
+    """Shared WS receive setup for the sherpa handlers.
+
+    Returns ``(get_frame, state)`` where ``get_frame`` is an async callable
+    that yields the next near-end (mic) PCM bytes, ``b""`` for a keepalive/ref
+    frame, or ``None`` on EOF/disconnect. ``state`` carries sample rate, AEC,
+    and the disconnect flag for the caller's finaliser.
+    """
+    pcm_sr = 16000
+    try:
+        pcm_sr = int(websocket.query_params.get("sr", "16000"))
+    except (TypeError, ValueError):
+        pcm_sr = 16000
+    aec = None
+    if websocket.query_params.get("aec") in ("1", "true", "on"):
+        try:
+            from services.aec import NlmsEchoCanceller
+            aec = NlmsEchoCanceller(sample_rate=pcm_sr)
+        except Exception as e:
+            logger.warning("AEC requested but disabled (sherpa): %s", e)
+            aec = None
+    return pcm_sr, aec
+
+
+async def _recv_pcm_frame(websocket: WebSocket, aec):
+    """Receive one frame; return (kind, pcm_bytes).
+
+    kind ∈ {"near","eof","skip"}. Demuxes AEC-tagged frames when ``aec`` is on
+    and feeds the playback reference into the canceller. A text "EOF" or an
+    empty/closed socket yields kind "eof".
+    """
+    msg = await websocket.receive()
+    mtype = msg.get("type")
+    if mtype == "websocket.disconnect":
+        return "eof", b""
+    if mtype != "websocket.receive":
+        return "skip", b""
+    data = msg.get("bytes")
+    if data is not None:
+        if len(data) == 0:
+            return "eof", b""
+        if aec is not None:
+            kind, payload = _demux_aec_frame(data)
+            if kind == "far":
+                aec.push_far_end(payload)
+                return "skip", b""
+            if not payload:
+                return "skip", b""
+            return "near", aec.process_near_end(payload)
+        return "near", data
+    if msg.get("text") == "EOF":
+        return "eof", b""
+    return "skip", b""
+
+
+async def _sherpa_load_with_status(websocket: WebSocket, backend, spec) -> bool:
+    """Build the recognizer off the event loop, narrating cold-start progress.
+
+    Sends ``{"type":"status","stage":"downloading"|"loading"}`` before the
+    load ("downloading" when the pinned assets aren't in the HF cache yet;
+    stage-only — HF's per-file progress isn't worth a callback plumb-through)
+    and ``{"type":"status","stage":"ready"}`` after, so the widget can show
+    *why* the first dictation takes a moment. Returns False when the load
+    failed (the error frame is sent and the socket closed here).
+    """
+    try:
+        from services import sherpa_dictation as _sd
+        stage = "loading" if _sd.is_installed(spec) else "downloading"
+    except Exception:
+        stage = "loading"
+    try:
+        await websocket.send_json({"type": "status", "stage": stage})
+    except Exception:
+        pass
+    try:
+        await asyncio.to_thread(backend.ensure_loaded)
+    except Exception as e:
+        logger.error("sherpa dictation load failed (%s): %s", spec.id, e)
+        try:
+            await websocket.send_json({"type": "error", "message": str(e),
+                                       "kind": "load", "detail": str(e)})
+            await websocket.close()
+        except Exception:
+            pass
+        return False
+    try:
+        await websocket.send_json({"type": "status", "stage": "ready"})
+    except Exception:
+        pass
+    return True
+
+
+async def _run_sherpa_streaming(websocket: WebSocket, spec):
+    """True streaming: feed the OnlineRecognizer frame-by-frame, emit `partial`
+    every time the decoded text grows, and `final` on sherpa's endpoint (silence)
+    detection and on EOF. <300ms perceived latency on CPU for the tiny models.
+    """
+    import numpy as np
+    from services.asr_backend import get_sherpa_dictation_backend
+
+    pcm_sr, aec = await _sherpa_session(websocket)
+    logger.info("sherpa streaming dictation: model=%s sr=%d aec=%s",
+                spec.id, pcm_sr, bool(aec))
+
+    # Reuse the shared, per-model warm backend (#888): the recognizer is built
+    # once and shared across sessions instead of rebuilt (1.3–2.5s) per connect,
+    # so the first dictation is instant when the preload warmed it. Each session
+    # still gets its own decode stream below.
+    backend = get_sherpa_dictation_backend(spec.id)
+    # Build the recognizer off the event loop if it isn't warm yet
+    # (download-on-first-use + ONNX session init can take a moment); status
+    # frames keep the widget honest.
+    if not await _sherpa_load_with_status(websocket, backend, spec):
+        return
+    rec = backend._rec
+    stream = rec.create_stream()
+
+    last_partial = ""
+    committed: list[str] = []     # finalized utterances this session
+    client_disconnected = False
+
+    async def _send(payload) -> bool:
+        nonlocal client_disconnected
+        if client_disconnected:
+            return False
+        try:
+            await websocket.send_json(payload)
+            return True
+        except Exception:
+            client_disconnected = True
+            return False
+
+    def _decode_after_feed(pcm: bytes):
+        """Blocking: feed one PCM frame, decode, return (text, is_endpoint).
+        Runs in a thread so the ONNX work never blocks the event loop."""
+        samples = _pcm16_to_f32(pcm)
+        if len(samples):
+            stream.accept_waveform(pcm_sr, samples)
+        while rec.is_ready(stream):
+            rec.decode_stream(stream)
+        endpoint = rec.is_endpoint(stream)
+        text = (rec.get_result(stream) or "").strip()
+        return text, endpoint
+
+    def _flush_final():
+        """Blocking: pad + drain the stream for the trailing utterance."""
+        tail = np.zeros(int(0.5 * pcm_sr), dtype=np.float32)
+        stream.accept_waveform(pcm_sr, tail)
+        stream.input_finished()
+        while rec.is_ready(stream):
+            rec.decode_stream(stream)
+        return (rec.get_result(stream) or "").strip()
+
+    try:
+        while True:
+            kind, pcm = await _recv_pcm_frame(websocket, aec)
+            if kind == "eof":
+                break
+            if kind == "skip":
+                continue
+            text, endpoint = await asyncio.to_thread(_decode_after_feed, pcm)
+            if endpoint:
+                # Commit this utterance (polished — it gets pasted); reset
+                # for the next one.
+                text = polish_text(text)
+                if text:
+                    committed.append(text)
+                    await _send({"type": "final", "text": text,
+                                 "segments": [{"start": 0.0, "end": None, "text": text}],
+                                 "language": "auto", "engine": backend.id})
+                rec.reset(stream)
+                last_partial = ""
+            elif text and text != last_partial:
+                last_partial = text
+                await _send({"type": "partial", "text": text})
+    except WebSocketDisconnect:
+        client_disconnected = True
+    except Exception as e:
+        logger.warning("sherpa streaming loop ended: %s", e)
+        client_disconnected = True
+
+    # Drain the trailing (un-endpointed) utterance on EOF.
+    try:
+        tail_text = await asyncio.to_thread(_flush_final)
+    except Exception as e:
+        logger.debug("sherpa streaming flush failed: %s", e)
+        tail_text = ""
+    tail_text = polish_text(tail_text)
+    if tail_text and tail_text != (committed[-1] if committed else None):
+        committed.append(tail_text)
+
+    # Pieces are already polished; the join is too (polish is idempotent).
+    full = " ".join(t for t in committed if t).strip()
+    segments = [{"start": 0.0, "end": None, "text": t} for t in committed if t]
+    if not client_disconnected:
+        if full:
+            # Hard-bounded refinement (~4s): never delays this summary `final`
+            # beyond OMNIVOICE_REFINE_TIMEOUT_S even with a dead LLM endpoint.
+            try:
+                from services.refinement import maybe_refine_async
+                refined = await maybe_refine_async(full)
+            except Exception:
+                refined = None
+            payload = {"type": "final", "text": full, "segments": segments,
+                       "language": "auto", "engine": backend.id}
+            if refined and refined != full:
+                payload["refined_text"] = refined
+            await _send(payload)
+        else:
+            await _send({"type": "final", "text": "", "segments": [],
+                         "language": "auto", "engine": backend.id})
+        try:
+            await websocket.close()
+        except Exception:
+            pass
+
+
+async def _run_sherpa_offline(websocket: WebSocket, spec):
+    """Offline-kind sherpa model with live partials, utterance-windowed.
+
+    Raw PCM accumulates in a *live* buffer holding only the current
+    (uncommitted) utterance. Every ~800ms the live window is re-decoded for a
+    ``partial``; when the trailing ~0.6s of it fall below the RMS floor the
+    utterance is committed — decoded once more, flushed as a ``final``, and
+    its samples dropped — so per-partial cost is bounded by one utterance
+    (not the whole session) and sentences commit as the user pauses instead
+    of only at EOF."""
+    from services.asr_backend import get_sherpa_dictation_backend
+
+    pcm_sr, aec = await _sherpa_session(websocket)
+    logger.info("sherpa offline dictation: model=%s sr=%d aec=%s",
+                spec.id, pcm_sr, bool(aec))
+
+    # Shared, per-model warm backend (#888) — built once, reused per session.
+    backend = get_sherpa_dictation_backend(spec.id)
+    if not await _sherpa_load_with_status(websocket, backend, spec):
+        return
+
+    buf = bytearray()             # live (uncommitted) PCM only
+    committed: list[str] = []     # polished utterances already flushed
+    last_partial = ""
+    running = True
+    client_disconnected = False
+    last_audio = time.monotonic()
+    # Trailing-silence gate window, in bytes of int16 mono PCM.
+    sil_bytes = max(2, int(SHERPA_OFFLINE_SILENCE_S * pcm_sr) * 2)
+
+    async def _send(payload) -> bool:
+        nonlocal client_disconnected
+        if client_disconnected:
+            return False
+        try:
+            await websocket.send_json(payload)
+            return True
+        except Exception:
+            client_disconnected = True
+            return False
+
+    def _rms(pcm: bytes) -> float:
+        samples = _pcm16_to_f32(pcm)
+        if not len(samples):
+            return 0.0
+        return float((samples * samples).mean() ** 0.5)
+
+    def _decode_window(pcm: bytes) -> str:
+        samples = _pcm16_to_f32(pcm)
+        if not len(samples):
+            return ""
+        return backend._decode_offline(samples, pcm_sr)
+
+    async def receive():
+        nonlocal running, client_disconnected, last_audio
+        try:
+            while running:
+                kind, pcm = await _recv_pcm_frame(websocket, aec)
+                if kind == "eof":
+                    running = False
+                    break
+                if kind == "skip":
+                    continue
+                buf.extend(pcm)
+                last_audio = time.monotonic()
+        except WebSocketDisconnect:
+            client_disconnected = True
+            running = False
+        except Exception as e:
+            logger.debug("sherpa offline receive ended: %s", e)
+            running = False
+
+    async def _commit(snapshot: bytes):
+        """Finalize one utterance: decode it off-thread, flush a polished
+        `final`, drop its samples from the live buffer. `receive()` may
+        append while we decode — only the snapshot's prefix is dropped."""
+        nonlocal last_partial
+        try:
+            text = await asyncio.to_thread(_decode_window, snapshot)
+        except Exception as e:
+            logger.debug("sherpa offline commit decode failed: %s", e)
+            return
+        del buf[:len(snapshot)]
+        last_partial = ""
+        text = polish_text(text)
+        if text:
+            committed.append(text)
+            await _send({"type": "final", "text": text,
+                         "segments": [{"start": 0.0, "end": None, "text": text}],
+                         "language": "auto", "engine": backend.id})
+
+    async def partials():
+        nonlocal last_partial, running
+        while running:
+            await asyncio.sleep(SHERPA_OFFLINE_PARTIAL_S)
+            if not running or len(buf) < 2000:
+                continue
+            snapshot = bytes(buf)
+            if len(snapshot) > sil_bytes and \
+                    _rms(snapshot[-sil_bytes:]) < SHERPA_OFFLINE_RMS_FLOOR:
+                if _rms(snapshot[:-sil_bytes]) >= SHERPA_OFFLINE_RMS_FLOOR:
+                    await _commit(snapshot)
+                else:
+                    # Pure silence — drop it (keep the gate window for
+                    # continuity) so a long pause can't grow the buffer.
+                    del buf[:len(snapshot) - sil_bytes]
+                continue
+            try:
+                text = await asyncio.to_thread(_decode_window, snapshot)
+            except Exception as e:
+                logger.debug("sherpa offline partial failed: %s", e)
+                continue
+            if text and text != last_partial:
+                last_partial = text
+                await _send({"type": "partial", "text": text})
+
+    recv_task = asyncio.create_task(receive())
+    part_task = asyncio.create_task(partials())
+    await asyncio.wait([recv_task, part_task], return_when=asyncio.FIRST_COMPLETED)
+    running = False
+    for t in (recv_task, part_task):
+        if not t.done():
+            t.cancel()
+            try:
+                await t
+            except (asyncio.CancelledError, Exception):
+                pass
+
+    # Drain the trailing (un-committed) utterance on EOF.
+    try:
+        tail = await asyncio.to_thread(_decode_window, bytes(buf))
+    except Exception as e:
+        logger.error("sherpa offline final failed: %s", e)
+        tail = ""
+    tail = polish_text(tail)
+    if tail:
+        committed.append(tail)
+    # Pieces are already polished; the join is too (polish is idempotent).
+    full = " ".join(committed).strip()
+    segments = [{"start": 0.0, "end": None, "text": t} for t in committed]
+    if not client_disconnected:
+        payload = {"type": "final", "text": full, "segments": segments,
+                   "language": "auto", "engine": backend.id}
+        if full:
+            # Hard-bounded refinement (~4s) — never delays the `final`.
+            try:
+                from services.refinement import maybe_refine_async
+                refined = await maybe_refine_async(full)
+                if refined and refined != full:
+                    payload["refined_text"] = refined
+            except Exception:
+                pass
+        await _send(payload)
+        try:
+            await websocket.close()
+        except Exception:
+            pass
+
+
 async def _transcribe_buffer(chunks: list[bytes], *, pcm_sr: int | None = None) -> str:
     """Quick partial transcription of the current audio buffer."""
 
@@ -301,15 +768,17 @@ async def _transcribe_buffer(chunks: list[bytes], *, pcm_sr: int | None = None)
 
     try:
         from services.model_manager import _gpu_pool
-        from services.asr_backend import get_capture_asr_backend
+        from services.asr_backend import get_capture_asr_backend, run_transcribe_guarded
 
         def _run():
             backend = get_capture_asr_backend()
             result = backend.transcribe(tmp, word_timestamps=False)
             return result.get("text", "")
 
-        loop = asyncio.get_running_loop()
-        text = await loop.run_in_executor(_gpu_pool, _run)
+        # Bound dictation transcribes (#730): a wedged whisperx/CTranslate2 call
+        # must not hold its GPU-pool worker forever and starve TTS / other ASR
+        # into a "can't reach backend"; on timeout the pool is reset to recover.
+        text = await run_transcribe_guarded(_gpu_pool, _run, what="Dictation")
         return text.strip()
     finally:
         try:
@@ -327,7 +796,7 @@ async def _transcribe_buffer_full(chunks: list[bytes], *, pcm_sr: int | None = N
 
     try:
         from services.model_manager import _gpu_pool
-        from services.asr_backend import get_capture_asr_backend
+        from services.asr_backend import get_capture_asr_backend, run_transcribe_guarded
 
         def _run():
             backend = get_capture_asr_backend()
@@ -362,8 +831,9 @@ async def _transcribe_buffer_full(chunks: list[bytes], *, pcm_sr: int | None = N
                 "engine": backend.id,
             }
 
-        loop = asyncio.get_running_loop()
-        return await loop.run_in_executor(_gpu_pool, _run)
+        # Bounded + pool-resetting on timeout (#730), same rationale as the
+        # partial path above.
+        return await run_transcribe_guarded(_gpu_pool, _run, what="Dictation")
     finally:
         try:
             os.unlink(tmp)

backend/api/routers/dictation.py

@@ -0,0 +1,127 @@
+"""
+Dictation router — sherpa-onnx live-dictation engine.
+
+Exposes the seven sherpa-onnx dictation models and the dictation prefs the
+frontend dictation UI binds to.
+
+    GET  /dictation/models   → the 7 models + install state (frontend model list)
+    GET  /dictation/prefs    → { enabled, mode, model_id }
+    POST /dictation/prefs    → persist any subset of those prefs
+
+Install state reuses the same HF-cache check the model store uses, so a model
+shown "installed" here is the same snapshot the backend will load.
+
+Prefs are stored in the shared ``prefs.json`` store under the ``dictation.*``
+namespace (``dictation.enabled``, ``dictation.mode``, ``dictation.model_id``),
+mirroring how the ASR/TTS engine picks persist.
+"""
+from __future__ import annotations
+
+import logging
+
+from fastapi import APIRouter, Depends, HTTPException
+from pydantic import BaseModel
+from typing import Optional
+
+from api.dependencies import require_loopback
+from core import prefs
+from services import sherpa_dictation as sd
+
+router = APIRouter()
+logger = logging.getLogger("omnivoice.dictation")
+
+# Pref keys (the binding contract — the frontend writes exactly these).
+PREF_ENABLED = "dictation.enabled"
+PREF_MODE = "dictation.mode"
+PREF_MODEL_ID = "dictation.model_id"
+
+_DEFAULT_ENABLED = True
+_DEFAULT_MODE = "toggle"
+_VALID_MODES = ("toggle", "hold")
+
+
+def _read_prefs() -> dict:
+    mid = prefs.get(PREF_MODEL_ID, sd.DEFAULT_MODEL_ID)
+    if not sd.is_sherpa_model(mid):
+        mid = sd.DEFAULT_MODEL_ID
+    mode = prefs.get(PREF_MODE, _DEFAULT_MODE)
+    if mode not in _VALID_MODES:
+        mode = _DEFAULT_MODE
+    return {
+        "enabled": bool(prefs.get(PREF_ENABLED, _DEFAULT_ENABLED)),
+        "mode": mode,
+        "model_id": mid,
+    }
+
+
+@router.get("/dictation/models", dependencies=[Depends(require_loopback)])
+def list_dictation_models():
+    """The seven sherpa-onnx dictation models + install state.
+
+    Each entry: id, repo_id, label, tag ("offline"|"streaming"), recommended,
+    size_gb, languages, kind, and install state (installed/installing). The
+    ``installed`` flag is computed from the same HF cache the model store reads,
+    so it matches the model-store row state.
+    """
+    available, reason = sd.sherpa_available()
+    out = []
+    for spec in sd.list_specs():
+        out.append({
+            "id": spec.id,
+            "repo_id": spec.repo_id,
+            "label": spec.label,
+            "tag": spec.tag,
+            "recommended": spec.recommended,
+            "size_gb": spec.size_gb,
+            "languages": spec.languages,
+            "kind": spec.kind,
+            "installed": sd.is_installed(spec),
+        })
+    return {
+        "models": out,
+        "engine_available": available,
+        "engine_reason": None if available else reason,
+        "default_model_id": sd.DEFAULT_MODEL_ID,
+    }
+
+
+@router.get("/dictation/prefs", dependencies=[Depends(require_loopback)])
+def get_dictation_prefs():
+    return _read_prefs()
+
+
+class DictationPrefsUpdate(BaseModel):
+    enabled: Optional[bool] = None
+    mode: Optional[str] = None
+    model_id: Optional[str] = None
+
+
+@router.post("/dictation/prefs", dependencies=[Depends(require_loopback)])
+def set_dictation_prefs(req: DictationPrefsUpdate):
+    """Persist any subset of the dictation prefs. Validates ``mode`` and
+    ``model_id`` so a bad value can't wedge the capture engine."""
+    if req.mode is not None:
+        if req.mode not in _VALID_MODES:
+            raise HTTPException(
+                status_code=400,
+                detail=f"mode must be one of {_VALID_MODES}",
+            )
+        prefs.set_(PREF_MODE, req.mode)
+    if req.model_id is not None:
+        if not sd.is_sherpa_model(req.model_id):
+            raise HTTPException(
+                status_code=400,
+                detail=f"unknown dictation model_id {req.model_id!r}",
+            )
+        # Normalise to the canonical dictation id (accept repo_id too).
+        prefs.set_(PREF_MODEL_ID, sd.get_spec(req.model_id).id)
+    if req.enabled is not None:
+        prefs.set_(PREF_ENABLED, bool(req.enabled))
+    # Rebuild the cached capture singleton so the change takes effect at once.
+    try:
+        from services import asr_backend
+        asr_backend._capture_backend = None
+        asr_backend._capture_backend_key = None
+    except Exception:
+        pass
+    return _read_prefs()

backend/api/routers/dub_core.py

@@ -16,6 +16,7 @@ from core.tasks import task_manager
 from core import event_bus
 from schemas.requests import DubIngestUrlRequest
 from services.model_manager import get_model, _gpu_pool, _cpu_pool, get_diarization_pipeline, offload_tts_for_asr, restore_tts_after_asr
+from services.asr_backend import ASRTimeoutError, reset_pool_after_wedge, run_transcribe_guarded
 from services.audio_io import _safe_soundfile_write
 from services.ffmpeg_utils import find_ffmpeg
 from services.segmentation import (
@@ -23,6 +24,9 @@ from services.segmentation import (
     assign_speakers_from_diarization,
     assign_speakers_from_turns,
     assign_speakers_heuristic,
+    resplit_segments_by_diarization,
+    resplit_segments_by_turns,
+    _words_from_whisper,
     clean_up_segments,
 )
 from services.onset_align import snap_segment_starts
@@ -31,6 +35,7 @@ from services import dub_pipeline
 router = APIRouter()
 logger = logging.getLogger("omnivoice.api")
 
+
 # ── Legacy-name aliases to services/dub_pipeline.py ────────────────────────
 # Phase 2.4 moved the business logic into a service. Other routers
 # (dub_generate, dub_translate, dub_export) + internal call sites below still
@@ -360,6 +365,11 @@ async def dub_ingest_url(req: DubIngestUrlRequest):
 
 TRANSCRIBE_CHUNK_S = float(os.environ.get("OMNIVOICE_TRANSCRIBE_CHUNK_S", "30.0"))
 TRANSCRIBE_CHUNK_TIMEOUT_S = float(os.environ.get("OMNIVOICE_TRANSCRIBE_CHUNK_TIMEOUT_S", "120.0"))
+#: How many times to attempt each transcribe chunk before giving up on it. A
+#: transient wedge (esp. the first chunk, where whisperx cold-loads its model)
+#: shouldn't silently drop that whole window — retry once on a fresh pool so the
+#: transcript doesn't come back "missing the beginning".
+_CHUNK_TRANSCRIBE_ATTEMPTS = max(1, int(os.environ.get("OMNIVOICE_TRANSCRIBE_CHUNK_ATTEMPTS", "2")))
 
 
 _sse_event = dub_pipeline.sse_event
@@ -425,10 +435,22 @@ async def dub_transcribe_stream(
                 try:
                     # The PyTorch-Whisper backend lazily builds its own pipeline
                     # when no preloaded `_asr_pipe` is present (issue #255), so it
-                    # no longer needs OMNIVOICE_PRELOAD_TTS_ASR=1 — don't reject it
-                    # here; any load failure surfaces per-chunk with a real cause.
+                    # no longer needs OMNIVOICE_PRELOAD_TTS_ASR=1.
                     _asr_backend = get_active_asr_backend(asr_pipe=getattr(_model, "_asr_pipe", None))
+                    # Eagerly load the model HERE so a real load failure (e.g.
+                    # WhisperX: missing weights, CTranslate2/cuDNN mismatch, the
+                    # torch-2.6 weights-only VAD regression) surfaces once, with
+                    # its actual cause, as a clean preflight `error` event —
+                    # instead of being buried in N cryptic per-chunk failures
+                    # and retried on every chunk (#578). Run in a thread so the
+                    # (blocking) load doesn't stall the event loop.
+                    _ensure_loaded = getattr(_asr_backend, "ensure_loaded", None)
+                    if callable(_ensure_loaded):
+                        await asyncio.get_running_loop().run_in_executor(
+                            _gpu_pool, _ensure_loaded
+                        )
                 except Exception as e:
+                    logger.exception("transcribe preflight: ASR load failed (job=%s)", job_id)
                     from core.failure import build_failure
                     f = build_failure(e, stage="transcribe-preflight", include_diagnostic=False)
                     preflight_error = "ASR backend initialization failed: " + f["reason"] + (
@@ -436,9 +458,16 @@ async def dub_transcribe_stream(
                     )
                 scene_cuts = job.get("scene_cuts") or []
 
-    async def gen():
+    async def _gen_body():
         if preflight_error:
-            yield _sse_event("error", {"detail": preflight_error})
+            # Always follow a terminal `error` with `done` so the stream closes
+            # via a named event, not a raw connection drop. A bare error+close
+            # races the browser's native EventSource error (which carries no
+            # `data`); if that native error wins, the client falls back to the
+            # misleading generic "stream dropped … ASR backend failed" message
+            # and the real cause (in `detail`) is lost (#578).
+            yield _sse_event("error", {"detail": preflight_error, "retryable": True})
+            yield _sse_event("done", {})
             return
         import math
         import tempfile
@@ -453,7 +482,9 @@ async def dub_transcribe_stream(
         try:
             audio_np, sr = await loop.run_in_executor(_cpu_pool, _load)
         except Exception as e:
-            yield _sse_event("error", {"detail": f"audio load failed: {e}"})
+            # Terminal error → always emit `done` (see preflight note, #578).
+            yield _sse_event("error", {"detail": f"audio load failed: {e}", "retryable": True})
+            yield _sse_event("done", {})
             return
 
         total = float(len(audio_np)) / float(sr) if sr else 0.0
@@ -470,6 +501,9 @@ async def dub_transcribe_stream(
             logger.warning("offload_tts_for_asr failed (continuing): %s", e)
 
         all_segments: list[dict] = []
+        # Words (global-timeline) retained so diarization can re-split a segment
+        # that spans two speakers' turns at the word boundary (#486).
+        all_words: list = []
         detected_lang = None
         next_seg_id = 0
         chunk_errors: list[str] = []
@@ -521,31 +555,59 @@ async def dub_transcribe_stream(
                     logger.exception("chunk transcribe failed (backend=%s)", _asr_backend.id)
                     return {"chunks": [], "language": None, "error": str(e)}
 
-            try:
-                # wait_for in a loop to yield pings so the EventSource connection doesn't drop
-                fut = loop.run_in_executor(_gpu_pool, _transcribe_chunk)
-                waited = 0.0
-                part = None
+            # Retry a failed/timed-out chunk once on a fresh pool before giving
+            # up. Otherwise a transient wedge on the FIRST chunk (whisperx often
+            # cold-loads its model there, the #730 hang) drops that whole window
+            # and the transcript is "missing the beginning, only middle+end".
+            # The retry reuses the same audio window, so a recovered chunk fills
+            # the hole instead of leaving silent gaps.
+            part = None
+            for _attempt in range(1, _CHUNK_TRANSCRIBE_ATTEMPTS + 1):
+                # A wedged chunk gets the SAME guarded-timeout + pool-reset
+                # semantics as the whole-file paths (#730/#851):
+                # run_transcribe_guarded bounds the call, abandons the poisoned
+                # pool so the retry (and any concurrent TTS work) gets a fresh
+                # worker, and raises the actionable ASRTimeoutError. Run it as
+                # a task and poll so we can keep yielding pings — the
+                # EventSource connection drops without them.
+                pool_reset_by_guard = False
+                task = asyncio.ensure_future(run_transcribe_guarded(
+                    _gpu_pool, _transcribe_chunk,
+                    what=f"Dub chunk {i + 1}/{chunks_n}",
+                    timeout=TRANSCRIBE_CHUNK_TIMEOUT_S,
+                    timeout_env="OMNIVOICE_TRANSCRIBE_CHUNK_TIMEOUT_S",
+                ))
                 while True:
-                    done, pending = await asyncio.wait([fut], timeout=5.0)
+                    done, _pending = await asyncio.wait({task}, timeout=5.0)
                     if done:
-                        part = done.pop().result()
                         break
                     yield _sse_event("ping", {})
-                    waited += 5.0
-                    if waited >= TRANSCRIBE_CHUNK_TIMEOUT_S:
-                        # Re-raise TimeoutError if we exceed the overall limit
-                        raise asyncio.TimeoutError()
-            except asyncio.TimeoutError:
-                logger.error(
-                    "Transcribe chunk %d/%d timed out after %.0fs (job=%s)",
-                    i + 1, chunks_n, TRANSCRIBE_CHUNK_TIMEOUT_S, job_id,
-                )
-                part = {
-                    "chunks": [], "language": None,
-                    "error": f"Chunk {i+1} timed out after {TRANSCRIBE_CHUNK_TIMEOUT_S:.0f}s — "
-                             f"ASR backend may be stuck. Try restarting the server.",
-                }
+                try:
+                    part = task.result()
+                except ASRTimeoutError as e:
+                    # The guard already reset the pool; keep the actionable
+                    # message (it names the durable fixes, and — after repeated
+                    # timeouts — the crash-isolated engine escape hatch).
+                    pool_reset_by_guard = True
+                    logger.error(
+                        "Transcribe chunk %d/%d timed out after %.0fs (attempt %d/%d, job=%s)",
+                        i + 1, chunks_n, TRANSCRIBE_CHUNK_TIMEOUT_S, _attempt,
+                        _CHUNK_TRANSCRIBE_ATTEMPTS, job_id,
+                    )
+                    part = {"chunks": [], "language": None, "error": str(e)}
+                # Success → keep it. Failure/timeout → retry once on a fresh
+                # worker (the internal _transcribe_chunk except returns an
+                # error-part; the timeout path already reset the pool).
+                if part is not None and not part.get("error"):
+                    break
+                if _attempt < _CHUNK_TRANSCRIBE_ATTEMPTS:
+                    logger.warning(
+                        "Retrying transcribe chunk %d/%d after failure/timeout (next attempt %d/%d, job=%s)",
+                        i + 1, chunks_n, _attempt + 1, _CHUNK_TRANSCRIBE_ATTEMPTS, job_id,
+                    )
+                    if not pool_reset_by_guard:
+                        reset_pool_after_wedge(
+                            _gpu_pool, what=f"Dub chunk {i + 1}/{chunks_n}")
             if part.get("error"):
                 chunk_errors.append(part["error"])
                 logger.warning("Chunk %d/%d error: %s", i + 1, chunks_n, part["error"])
@@ -553,6 +615,12 @@ async def dub_transcribe_stream(
                 detected_lang = part["language"]
             asr_speaker_turns.extend(part.get("speaker_turns") or [])
             chunk_segs = segment_transcript(part, duration=t1, scene_cuts=scene_cuts)
+            # Same word source segment_transcript used (already global-timeline),
+            # kept for the post-diarization speaker re-split (#486).
+            try:
+                all_words.extend(_words_from_whisper(part))
+            except Exception:
+                pass
             # #280: Whisper often stretches a segment's start back over
             # leading music/silence (classic case: speech begins at 0:03,
             # transcript says 0.0 → the dub plays 3 s early). Snap starts
@@ -631,7 +699,10 @@ async def dub_transcribe_stream(
             # use its speaker turns directly and skip pyannote entirely (#182).
             if asr_speaker_turns:
                 logger.info("Using inline ASR diarization (%d turns); skipping pyannote.", len(asr_speaker_turns))
-                return assign_speakers_from_turns(all_segments, asr_speaker_turns), None
+                assigned = assign_speakers_from_turns(all_segments, asr_speaker_turns)
+                # #486: split any segment that spans two speakers' turns at the
+                # word boundary (single-speaker segments pass through unchanged).
+                return resplit_segments_by_turns(assigned, all_words, asr_speaker_turns), None
 
             from services.model_manager import (
                 DIARIZATION_ERR_LICENSE,
@@ -708,7 +779,10 @@ async def dub_transcribe_stream(
                     diar = diar_pipe(asr_audio_target, num_speakers=num_speakers)
                 else:
                     diar = diar_pipe(asr_audio_target)
-                return assign_speakers_from_diarization(all_segments, diar), None
+                assigned = assign_speakers_from_diarization(all_segments, diar)
+                # #486: split any segment that spans two speakers' turns at the
+                # word boundary (single-speaker segments pass through unchanged).
+                return resplit_segments_by_diarization(assigned, all_words, diar), None
             except Exception as e:
                 logger.error(f"Diarization failed: {e}")
                 # Mid-run failure — classify against the same sentinels so a
@@ -856,6 +930,25 @@ async def dub_transcribe_stream(
         })
         yield _sse_event("done", {})
 
+    async def gen():
+        # Terminal-event guard (#516): the SSE stream must NEVER close without a
+        # terminal event. Any unanticipated exception in the body (e.g. an ASR
+        # load that escapes the per-chunk handler) previously dropped the
+        # connection, which the frontend can only report as "stream dropped,
+        # likely ASR failed" — hiding the real cause. Emit a structured `error`
+        # (with the actionable hint from build_failure) then `done`, so the user
+        # sees the real failure + a Retry instead of a silent disconnect.
+        try:
+            async for ev in _gen_body():
+                yield ev
+        except Exception as e:  # noqa: BLE001 — last-resort stream finalizer
+            logger.exception("transcribe stream crashed (job=%s)", job_id)
+            from core.failure import build_failure
+            f = build_failure(e, stage="transcribe", include_diagnostic=False)
+            detail = f["reason"] + (f" — {f['hint']}" if f.get("hint") else "")
+            yield _sse_event("error", {"detail": detail, "retryable": True})
+            yield _sse_event("done", {})
+
     return StreamingResponse(
         gen(),
         media_type="text/event-stream",
@@ -959,7 +1052,11 @@ async def dub_transcribe(job_id: str):
     try:
         loop = asyncio.get_running_loop()
         try:
-            segments_result = await loop.run_in_executor(_gpu_pool, _transcribe)
+            # Bound the whole-file transcribe (#730): a wedged whisperx/CTranslate2
+            # call would otherwise hold its GPU-pool worker forever and starve
+            # every other request into a "can't reach backend". run_transcribe_guarded
+            # also resets the pool on timeout so capacity is restored.
+            segments_result = await run_transcribe_guarded(_gpu_pool, _transcribe, what="Dub")
         except asyncio.CancelledError:
             job["aborted"] = True
             raise

backend/api/routers/dub_export.py

@@ -1187,8 +1187,14 @@ async def dub_qc_pass(job_id: str, lang: str = Query(None), drift_threshold: flo
 
     try:
         from services.model_manager import _get_gpu_pool
-        loop = asyncio.get_running_loop()
-        recognized, engine_id = await loop.run_in_executor(_get_gpu_pool(), _recognize)
+        from services.asr_backend import ASRTimeoutError, run_transcribe_guarded
+        recognized, engine_id = await run_transcribe_guarded(
+            _get_gpu_pool(), _recognize, what="QC",
+        )
+    except ASRTimeoutError as e:
+        # Backend is alive; ASR just couldn't finish in time. 504, not 500/connection.
+        logger.warning("dub QC ASR pass timed out for %s: %s", job_id, e)
+        raise HTTPException(status_code=504, detail=str(e))
     except Exception as e:
         logger.exception("dub QC ASR pass failed for %s", job_id)
         raise HTTPException(status_code=500, detail=f"QC transcription failed: {e}")

backend/api/routers/dub_generate.py

@@ -11,7 +11,7 @@ from core.db import db_conn
 from core.config import DUB_DIR, VOICES_DIR, dub_seg_path
 from core.tasks import task_manager
 from schemas.requests import DubRequest
-from services.model_manager import get_model, _gpu_pool
+from services.model_manager import get_model, _gpu_pool, run_on_gpu_pool_guarded
 from services.audio_dsp import apply_mastering, normalize_audio, apply_effects_chain, get_effect_chain
 from services.audio_io import atomic_save_wav, _safe_torchaudio_save
 from services.ffmpeg_utils import (
@@ -28,6 +28,7 @@ from services.incremental import segment_fingerprint, fit_fingerprint
 from services.fit_planner import FitParams, plan_fit
 from services.watermark import embed_watermark
 from api.routers.dub_core import _get_job, _save_job
+from omnivoice.utils.voice_design import heal_design_instruct
 
 logger = logging.getLogger("omnivoice.dub")
 
@@ -106,6 +107,123 @@ async def dub_generate(job_id: str, req: DubRequest):
         all_segment_wavs = []
         sync_scores = []
 
+        # Throttle the device cache flush. empty_cache() is a synchronous
+        # device stall, so calling it every segment (as the old code did)
+        # serialised the GPU loop; the batched-I/O design it replaced kept
+        # it off the hot path on purpose. Flush every ~16 releases instead —
+        # frequent enough to bound VRAM, rare enough to stay invisible.
+        _RELEASE_FLUSH_EVERY = 16
+        _release_count = {"n": 0}
+
+        def _release_audio_tensors(*objs) -> None:
+            """Best-effort VRAM cleanup after a segment is safely on disk.
+
+            Tensors are freed by the callers' own ``del`` once they fall out
+            of scope; this only throttles the device cache flush. ``*objs`` is
+            kept for call-site compatibility but intentionally unused — a local
+            ``del`` here would only unbind the parameter, never the caller's
+            reference.
+            """
+            _release_count["n"] += 1
+            if _release_count["n"] % _RELEASE_FLUSH_EVERY != 0:
+                return
+            try:
+                if torch.cuda.is_available():
+                    torch.cuda.empty_cache()
+                elif hasattr(torch.backends, "mps") and torch.backends.mps.is_available():
+                    torch.mps.empty_cache()
+            except Exception:
+                pass
+
+        # mix_<id> scratch WAVs written for silence/cached-fail/error slots are
+        # pure assembly inputs (no preview/regen contract), so they're deleted
+        # once the final track is written.
+        _mix_temp_paths: list[str] = []
+
+        def _store_mix_wav(start: float, end: float, wav: torch.Tensor, sr: int, seg_key: str):
+            """Write one segment to disk and keep only its path in the mix manifest.
+
+            A zero/negative-length buffer is never written (``atomic_save_wav``
+            raises on empty audio); instead a harmless zero-length in-memory
+            entry is returned, which the assembly tolerates via its ``e > s``
+            guard.
+            """
+            if wav.shape[-1] <= 0:
+                return (start, end, torch.zeros(1, 0), sr)
+            path = dub_seg_path(job_id, seg_key)
+            os.makedirs(os.path.dirname(path), exist_ok=True)
+            atomic_save_wav(path, wav.detach().cpu(), sr)
+            if seg_key.startswith("mix_"):
+                _mix_temp_paths.append(path)
+            _release_audio_tensors(wav)
+            return (start, end, path, sr)
+
+        def _entry_num_samples(entry) -> int:
+            # Zero/negative-duration slots are kept as in-memory tensors (never
+            # written to disk); report their length directly.
+            if isinstance(entry[2], torch.Tensor):
+                return int(entry[2].shape[-1])
+            try:
+                info = torchaudio.info(entry[2])
+                return int(info.num_frames)
+            except Exception:
+                wav, _sr = torchaudio.load(entry[2])
+                n = int(wav.shape[-1])
+                _release_audio_tensors(wav)
+                return n
+
+        def _load_entry_wav(entry, target_sr: int) -> torch.Tensor:
+            if isinstance(entry[2], torch.Tensor):
+                return entry[2]
+            wav, loaded_sr = torchaudio.load(entry[2])
+            if loaded_sr != target_sr:
+                import torchaudio.functional as AF
+                wav = AF.resample(wav, loaded_sr, target_sr)
+            return wav
+
+        def _write_memmap_wav_atomic(target_path: str, samples, sample_rate: int) -> None:
+            """Write a mono float32 memmap to int16 WAV without loading it all.
+
+            Intentionally does NOT watermark: the final track is assembled from
+            per-segment WAVs that were already watermarked once at synthesis
+            time (see the seg-write path below), exactly as ``main`` does.
+            Re-marking here would double-mark every segment in the final mix.
+            """
+            import tempfile
+            import wave
+            import numpy as np
+
+            target_dir = os.path.dirname(target_path) or "."
+            target_base = os.path.basename(target_path)
+            fd, tmp_path = tempfile.mkstemp(
+                prefix=f".{target_base}.",
+                suffix=".wav",
+                dir=target_dir,
+            )
+            os.close(fd)
+            chunk_samples = max(sample_rate * 30, 1)
+            try:
+                with wave.open(tmp_path, "wb") as wf:
+                    wf.setnchannels(1)
+                    wf.setsampwidth(2)
+                    wf.setframerate(sample_rate)
+                    total_len = int(samples.shape[0])
+                    for off in range(0, total_len, chunk_samples):
+                        chunk = np.array(samples[off: off + chunk_samples], dtype=np.float32, copy=True)
+                        if chunk.size == 0:
+                            continue
+                        np.nan_to_num(chunk, copy=False, nan=0.0, posinf=1.0, neginf=-1.0)
+                        chunk = np.clip(chunk, -1.0, 1.0)
+                        pcm = (chunk * 32767.0).astype("<i2", copy=False)
+                        wf.writeframes(pcm.tobytes())
+                os.replace(tmp_path, target_path)
+            except BaseException:
+                try:
+                    os.unlink(tmp_path)
+                except OSError:
+                    pass
+                raise
+
         # Phase 4.1 — partial regen. If `regen_only` is set, we only run TTS
         # on segments whose id is in that set; the others reuse their existing
         # `seg_i.wav` on disk and slot into the final mix unchanged.
@@ -125,9 +243,9 @@ async def dub_generate(job_id: str, req: DubRequest):
         # reorder; index-keyed readers (preview/export) resolve via this manifest.
         job["seg_order"] = [seg_ids[k] if k < len(seg_ids) else f"seg_{k}" for k in range(len(req.segments))]
 
-        # Deferred disk writes: collect (index, tensor, sr, seg_id, fingerprint,
-        # num_step) tuples during the hot loop and batch-flush after all TTS
-        # completes. Eliminates ~200ms/seg of synchronous I/O from the GPU path.
+        # Per-segment metadata to persist after the hot loop. Audio itself is
+        # written immediately and only file paths are kept, so long videos don't
+        # retain every generated tensor in RAM until final assembly.
         _pending_seg_writes: list[tuple] = []
 
         # Phase 4.1 bench instrumentation: measure where incremental time goes.
@@ -149,8 +267,16 @@ async def dub_generate(job_id: str, req: DubRequest):
             seg_duration = seg.end - seg.start
             if seg_duration <= 0.05 or not seg.text.strip():
                 sr = _model.sampling_rate
-                silence = torch.zeros(1, int(seg_duration * sr))
-                all_segment_wavs.append((seg.start, seg.end, silence, sr))
+                # max(0, …): a zero/negative-duration slot must not feed a
+                # negative length to torch.zeros (raises) — _store_mix_wav
+                # turns the empty buffer into a harmless in-memory entry.
+                silence = torch.zeros(1, max(0, int(seg_duration * sr)))
+                all_segment_wavs.append(_store_mix_wav(seg.start, seg.end, silence, sr, f"mix_{seg_id}"))
+                try:
+                    del silence
+                except Exception:
+                    pass
+                _release_audio_tensors()
                 sync_scores.append(1.0)
                 continue
 
@@ -181,7 +307,12 @@ async def dub_generate(job_id: str, req: DubRequest):
                                 cached_wav = torch.nn.functional.pad(cached_wav, (0, target_samples - current_samples))
                             elif current_samples > target_samples:
                                 cached_wav = cached_wav[..., :target_samples]
-                        all_segment_wavs.append((seg.start, seg.end, cached_wav, _model.sampling_rate))
+                        all_segment_wavs.append(_store_mix_wav(seg.start, seg.end, cached_wav, _model.sampling_rate, f"mix_{seg_id}"))
+                        try:
+                            del cached_wav
+                        except Exception:
+                            pass
+                        _release_audio_tensors()
                         sync_scores.append(getattr(seg, 'sync_ratio', None) or 1.0)
                         _t_cache += time.perf_counter() - _t_cache_0
                         continue
@@ -190,8 +321,13 @@ async def dub_generate(job_id: str, req: DubRequest):
                         # is broken — cleaner than aborting the whole mix.
                         yield f"data: {json.dumps({'type': 'warning', 'segment': i, 'message': f'cached seg lost, padding silence: {str(e)[:120]}'})}\n\n"
                 sr = _model.sampling_rate
-                silence = torch.zeros(1, int(seg_duration * sr))
-                all_segment_wavs.append((seg.start, seg.end, silence, sr))
+                silence = torch.zeros(1, max(0, int(seg_duration * sr)))
+                all_segment_wavs.append(_store_mix_wav(seg.start, seg.end, silence, sr, f"mix_{seg_id}"))
+                try:
+                    del silence
+                except Exception:
+                    pass
+                _release_audio_tensors()
                 sync_scores.append(1.0)
                 continue
 
@@ -258,7 +394,11 @@ async def dub_generate(job_id: str, req: DubRequest):
                             used_seed = row["seed"]
                             
                         if not instruct_str:
-                            instruct_str = row["instruct"]
+                            try:
+                                _vd = row["vd_states"]
+                            except (KeyError, IndexError):
+                                _vd = None
+                            instruct_str = heal_design_instruct(row["instruct"], _vd)
 
                 if used_seed is not None:
                     torch.manual_seed(used_seed)
@@ -401,10 +541,14 @@ async def dub_generate(job_id: str, req: DubRequest):
                 # where dur_s is the slot hint.
                 _dur_for_tts = seg_duration if strategy == "strict_slot" else None
 
-                audio_tensor = await loop.run_in_executor(
-                    _gpu_pool, _gen,
-                    seg.text, seg_lang, seg_instruct, _dur_for_tts,
-                    _num_step, req.guidance_scale, seg_speed, seg_profile, seg_effect_preset,
+                # Bounded + pool-reset on hang so a wedged dub segment can't
+                # starve the GPU pool and brick the backend (#730 class).
+                audio_tensor = await run_on_gpu_pool_guarded(
+                    lambda: _gen(
+                        seg.text, seg_lang, seg_instruct, _dur_for_tts,
+                        _num_step, req.guidance_scale, seg_speed, seg_profile, seg_effect_preset,
+                    ),
+                    what="Dub generate",
                 )
                 _t_tts += time.perf_counter() - _t_tts_0
 
@@ -452,7 +596,7 @@ async def dub_generate(job_id: str, req: DubRequest):
                 except Exception as e:
                     logger.debug("seg fingerprint skipped for %s: %s", seg_id, e)
 
-                _pending_seg_writes.append((i, audio_tensor, _model.sampling_rate, seg_id, _seg_fp, _num_step))
+                _pending_seg_writes.append((i, _model.sampling_rate, seg_id, _seg_fp, _num_step))
 
                 # RVC needs the WAV on disk, so write it immediately only
                 # when RVC is active (uncommon path).
@@ -474,32 +618,54 @@ async def dub_generate(job_id: str, req: DubRequest):
                     except Exception as e:
                         yield f"data: {json.dumps({'type': 'warning', 'segment': i, 'message': f'RVC skipped: {str(e)[:120]}'})}\n\n"
 
-                all_segment_wavs.append((seg.start, seg.end, audio_tensor, _model.sampling_rate))
+                # Watermark this FRESH TTS output exactly once, right before it
+                # is persisted. The same seg_<id>.wav is BOTH the downloadable
+                # per-segment file AND the assembly input for the final track,
+                # so marking it here (and nowhere else) gives the downloadable
+                # WAV its mark back and the final mix inherits it — no double-
+                # mark. Cached-reuse audio is already marked; silence/zero slots
+                # carry no speech to mark, so neither is re-watermarked.
+                audio_tensor = embed_watermark(audio_tensor, _model.sampling_rate)
+
+                seg_wav_path = dub_seg_path(job_id, seg_id)
+                try:
+                    # Keep the existing per-segment WAV contract for previews
+                    # and partial regeneration, but do not keep the tensor in RAM.
+                    atomic_save_wav(seg_wav_path, audio_tensor, _model.sampling_rate)
+                except Exception as e:
+                    logger.warning("seg write failed for %s: %s", seg_id, e)
+                    # If the durable segment write fails, still preserve a mix
+                    # copy so this generation can finish.
+                    all_segment_wavs.append(_store_mix_wav(seg.start, seg.end, audio_tensor, _model.sampling_rate, f"mix_{seg_id}"))
+                    try:
+                        del audio_tensor
+                    except Exception:
+                        pass
+                    _release_audio_tensors()
+                else:
+                    all_segment_wavs.append((seg.start, seg.end, seg_wav_path, _model.sampling_rate))
+                    try:
+                        del audio_tensor
+                    except Exception:
+                        pass
+                    _release_audio_tensors()
             except Exception as e:
                 yield f"data: {json.dumps({'type': 'error', 'segment': i, 'error': str(e)})}\n\n"
                 sr = _model.sampling_rate
-                all_segment_wavs.append((seg.start, seg.end, torch.zeros(1, int(seg_duration * sr)), sr))
+                all_segment_wavs.append(_store_mix_wav(seg.start, seg.end, torch.zeros(1, max(0, int(seg_duration * sr))), sr, f"mix_{seg_id}"))
                 sync_scores.append(1.0)
 
         _t_loop_end = time.perf_counter()
 
         yield f"data: {json.dumps({'type': 'assembling'})}\n\n"
 
-        # ── Batch disk-write phase ────────────────────────────────────
-        # Flush all per-segment WAVs and fingerprints in one burst now
-        # that the GPU-hot loop is done. This keeps I/O off the critical
-        # path and cuts ~200ms × N_segments of latency.
+        # ── Batch metadata phase ──────────────────────────────────────
+        # Per-segment WAVs were written during the loop to keep RAM bounded.
+        # Flush only lightweight fingerprints/quality metadata here.
         _t_diskw_0 = time.perf_counter()
         hashes = job.setdefault("seg_hashes", {})
         quality_map = job.setdefault("seg_num_step", {})
-        for (_si, _wav, _sr, _sid, _fp, _nstep) in _pending_seg_writes:
-            seg_wav_path = dub_seg_path(job_id, _sid)
-            try:
-                # Apply invisible watermark before writing to disk
-                _wav = embed_watermark(_wav, _sr)
-                atomic_save_wav(seg_wav_path, _wav, _sr)
-            except Exception as e:
-                logger.warning("deferred seg write failed for %s: %s", _sid, e)
+        for (_si, _sr, _sid, _fp, _nstep) in _pending_seg_writes:
             if _fp is not None:
                 hashes[_sid] = _fp
             quality_map[_sid] = _nstep
@@ -527,8 +693,8 @@ async def dub_generate(job_id: str, req: DubRequest):
 
         if strategy == "stretch_video":
             cursor = 0.0
-            for i, (orig_start, orig_end, wav, _) in enumerate(all_segment_wavs):
-                wl_i = wav.shape[-1]
+            for i, (orig_start, orig_end, wav_path, _) in enumerate(all_segment_wavs):
+                wl_i = _entry_num_samples((orig_start, orig_end, wav_path, sr))
                 natural_dur = (wl_i / sr) if wl_i > 0 else max(0.0, orig_end - orig_start)
                 if i == 0:
                     # Preserve the pre-roll (silence before the first seg).
@@ -578,9 +744,9 @@ async def dub_generate(job_id: str, req: DubRequest):
                         "start": s,
                         "end": e,
                     }
-                    for i, (s, e, _w, _) in enumerate(all_segment_wavs)
+                    for i, (s, e, _path, _) in enumerate(all_segment_wavs)
                 ],
-                [w.shape[-1] / sr for (_s, _e, w, _) in all_segment_wavs],
+                [_entry_num_samples(entry) / sr for entry in all_segment_wavs],
                 orig_total_dur,
                 fit_params,
             )
@@ -593,183 +759,245 @@ async def dub_generate(job_id: str, req: DubRequest):
         # not from the plan — so subtitles land exactly on the audio.
         fitted_cues: list[dict] = []
 
-        full_audio = torch.zeros(1, total_samples)
+        lang_code = req.language_code or "und"
+        track_path = os.path.join(DUB_DIR, job_id, f"dubbed_{lang_code}.wav")
+        os.makedirs(os.path.dirname(track_path), exist_ok=True)
 
-        for i, (start, end, wav, _) in enumerate(all_segment_wavs):
-            seg_ref = req.segments[i] if i < len(req.segments) else None
-            seg_gain = getattr(seg_ref, "gain", None) if seg_ref is not None else None
-            seg_gain = seg_gain if seg_gain is not None else 1.0
-            seg_gain = max(0.0, min(2.0, seg_gain))
-            adjusted = wav * seg_gain
-            wl = adjusted.shape[-1]
-            natural_dur = wl / sr if wl > 0 else 0.0
-            orig_dur = max(0.0, end - start)
+        import gc
+        import tempfile
+        import numpy as np
 
-            if strategy == "stretch_video":
-                # Mode B: audio at natural rate, placed on the stretched
-                # timeline. No trim, no atempo. dub_export handles the video.
-                new_start, _new_end = new_layout[i]
-                place_at = new_start
-                fit_status.append({
-                    "status": "video_stretched",
-                    "stretch_ratio": round(natural_dur / max(orig_dur, 1e-3), 3),
-                })
+        mix_samples = max(total_samples, 1)
+        fd, mix_path = tempfile.mkstemp(
+            prefix=f".{os.path.basename(track_path)}.mix.",
+            suffix=".f32",
+            dir=os.path.dirname(track_path),
+        )
+        os.close(fd)
+        try:
+            with open(mix_path, "r+b") as mix_file:
+                mix_file.truncate(mix_samples * 4)
+            mix_audio = np.memmap(mix_path, dtype=np.float32, mode="r+", shape=(mix_samples,))
 
-            elif strategy == "smart_fit":
-                # Smart Fit: apply the planner's audio_rate via the same
-                # pitch-preserving atempo pipe strict_slot uses, place the
-                # result at the planned new_start, and hard-trim whatever
-                # the caps couldn't absorb. The video side (video_ratio per
-                # chunk) is persisted below for the export pipeline.
-                sf = fit_plan.segments[i]
-                place_at = sf.new_start
-                if sf.audio_rate > 1.0 + 1e-6 and wl > 0:
-                    target = max(1, int(round(wl / sf.audio_rate)))
-                    try:
-                        adjusted = await _pitch_preserving_stretch(
-                            adjusted, target, sr,
-                        )
-                    except Exception as e:
-                        logger.warning(
-                            "atempo stretch failed for seg %d (%.2f×), "
-                            "falling back to linear interp: %s",
-                            i, sf.audio_rate, e,
-                        )
-                        adjusted = torch.nn.functional.interpolate(
-                            adjusted.unsqueeze(0),
-                            size=target,
-                            mode='linear',
-                            align_corners=False,
-                        ).squeeze(0)
-                    wl = adjusted.shape[-1]
-                # Residual overflow → hard-trim to the segment's new video
-                # slot (fade below keeps the cut pop-free).
-                new_slot_samples = int(max(0.0, sf.new_end - sf.new_start) * sr)
-                if new_slot_samples > 0 and wl > new_slot_samples:
-                    adjusted = adjusted[..., :new_slot_samples]
-                    wl = adjusted.shape[-1]
-                # Truthful per-segment verdict for the UI badge.
-                entry = {"status": sf.status}
-                if sf.audio_rate > 1.0 + 1e-6:
-                    entry["audio_rate"] = round(sf.audio_rate, 3)
-                if sf.video_ratio > 1.0 + 1e-6:
-                    entry["video_ratio"] = round(sf.video_ratio, 3)
-                if sf.overflow_s > 0:
-                    entry["overflow_s"] = round(sf.overflow_s, 3)
-                fit_status.append(entry)
-                # Cue times from the ACTUAL stretched sample positions.
-                fitted_cues.append({
-                    "id": sf.seg_id,
-                    "start": round(place_at, 4),
-                    "end": round(place_at + wl / sr, 4),
-                })
+            for i, (start, end, wav_path, _) in enumerate(all_segment_wavs):
+                seg_ref = req.segments[i] if i < len(req.segments) else None
+                seg_gain = getattr(seg_ref, "gain", None) if seg_ref is not None else None
+                seg_gain = seg_gain if seg_gain is not None else 1.0
+                seg_gain = max(0.0, min(2.0, seg_gain))
+                wav = _load_entry_wav((start, end, wav_path, sr), sr)
+                adjusted = wav * seg_gain
+                if adjusted.ndim == 2 and adjusted.shape[0] > 1:
+                    adjusted = adjusted.mean(dim=0, keepdim=True)
+                wl = adjusted.shape[-1]
+                natural_dur = wl / sr if wl > 0 else 0.0
+                orig_dur = max(0.0, end - start)
 
-            elif strategy == "concise":
-                # Mode A: never compress. Allow the audio to extend into the
-                # silent gap before the next seg (existing heuristic) plus
-                # any extra `overflow_budget_s`. Beyond that, hard-trim with
-                # a short fade so we never overlap the next speaker.
-                place_at = start
-                effective_end = end
-                if i + 1 < len(all_segment_wavs):
-                    next_start = all_segment_wavs[i + 1][0]
-                    gap = next_start - end
-                    if gap > GAP_OVERFLOW_BUFFER_S:
-                        effective_end = end + min(
-                            gap - GAP_OVERFLOW_BUFFER_S, GAP_OVERFLOW_MAX_S,
-                        )
-                effective_end += overflow_budget_s
-                slot_samples_eff = int(max(0.0, (effective_end - start)) * sr)
-                if slot_samples_eff > 0 and wl > slot_samples_eff:
-                    overflow_s = (wl - slot_samples_eff) / sr
-                    adjusted = adjusted[..., :slot_samples_eff]
-                    wl = adjusted.shape[-1]
+                if strategy == "stretch_video":
+                    # Mode B: audio at natural rate, placed on the stretched
+                    # timeline. No trim, no atempo. dub_export handles the video.
+                    new_start, _new_end = new_layout[i]
+                    place_at = new_start
                     fit_status.append({
-                        "status": "overflows",
-                        "overflow_s": round(overflow_s, 3),
+                        "status": "video_stretched",
+                        "stretch_ratio": round(natural_dur / max(orig_dur, 1e-3), 3),
                     })
-                else:
-                    fit_status.append({"status": "fits"})
 
-            else:
-                # strict_slot (legacy): preserve the previous atempo / trim /
-                # off semantics so existing callers and back-compat tests
-                # keep passing.
-                place_at = start
-                effective_end = end
-                if i + 1 < len(all_segment_wavs):
-                    next_start = all_segment_wavs[i + 1][0]
-                    gap = next_start - end
-                    if gap > GAP_OVERFLOW_BUFFER_S:
-                        effective_end = end + min(
-                            gap - GAP_OVERFLOW_BUFFER_S, GAP_OVERFLOW_MAX_S,
-                        )
-                slot_samples = int(max(0.0, (effective_end - start)) * sr)
-                if slot_fit != "off" and slot_samples > 0 and wl > slot_samples:
-                    if slot_fit == "time_stretch":
-                        ratio = wl / slot_samples
-                        capped_ratio = min(ratio, MAX_STRETCH_RATIO)
-                        capped_target = int(wl / capped_ratio)
+                elif strategy == "smart_fit":
+                    # Smart Fit: apply the planner's audio_rate via the same
+                    # pitch-preserving atempo pipe strict_slot uses, place the
+                    # result at the planned new_start, and hard-trim whatever
+                    # the caps couldn't absorb. The video side (video_ratio per
+                    # chunk) is persisted below for the export pipeline.
+                    sf = fit_plan.segments[i]
+                    place_at = sf.new_start
+                    if sf.audio_rate > 1.0 + 1e-6 and wl > 0:
+                        target = max(1, int(round(wl / sf.audio_rate)))
                         try:
                             adjusted = await _pitch_preserving_stretch(
-                                adjusted, capped_target, sr,
+                                adjusted, target, sr,
                             )
-                            if adjusted.shape[-1] > slot_samples:
-                                adjusted = adjusted[..., :slot_samples]
-                            if ratio > MAX_STRETCH_RATIO:
-                                logger.info(
-                                    "seg %d compression %.2f× exceeded cap; "
-                                    "stretched to %.2f×, tail trimmed",
-                                    i, ratio, capped_ratio,
-                                )
                         except Exception as e:
                             logger.warning(
                                 "atempo stretch failed for seg %d (%.2f×), "
                                 "falling back to linear interp: %s",
-                                i, ratio, e,
+                                i, sf.audio_rate, e,
                             )
                             adjusted = torch.nn.functional.interpolate(
                                 adjusted.unsqueeze(0),
-                                size=slot_samples,
+                                size=target,
                                 mode='linear',
                                 align_corners=False,
                             ).squeeze(0)
-                    else:  # "trim"
-                        adjusted = adjusted[..., :slot_samples]
+                        wl = adjusted.shape[-1]
+                    # Residual overflow → hard-trim to the segment's new video
+                    # slot (fade below keeps the cut pop-free).
+                    new_slot_samples = int(max(0.0, sf.new_end - sf.new_start) * sr)
+                    if new_slot_samples > 0 and wl > new_slot_samples:
+                        adjusted = adjusted[..., :new_slot_samples]
+                        wl = adjusted.shape[-1]
+                    # Truthful per-segment verdict for the UI badge.
+                    entry = {"status": sf.status}
+                    if sf.audio_rate > 1.0 + 1e-6:
+                        entry["audio_rate"] = round(sf.audio_rate, 3)
+                    if sf.video_ratio > 1.0 + 1e-6:
+                        entry["video_ratio"] = round(sf.video_ratio, 3)
+                    if sf.overflow_s > 0:
+                        entry["overflow_s"] = round(sf.overflow_s, 3)
+                    fit_status.append(entry)
+                    # Cue times from the ACTUAL stretched sample positions.
+                    fitted_cues.append({
+                        "id": sf.seg_id,
+                        "start": round(place_at, 4),
+                        "end": round(place_at + wl / sr, 4),
+                    })
+
+                elif strategy == "concise":
+                    # Mode A: never compress. Allow the audio to extend into the
+                    # silent gap before the next seg (existing heuristic) plus
+                    # any extra `overflow_budget_s`. Beyond that, hard-trim with
+                    # a short fade so we never overlap the next speaker.
+                    place_at = start
+                    effective_end = end
+                    if i + 1 < len(all_segment_wavs):
+                        next_start = all_segment_wavs[i + 1][0]
+                        gap = next_start - end
+                        if gap > GAP_OVERFLOW_BUFFER_S:
+                            effective_end = end + min(
+                                gap - GAP_OVERFLOW_BUFFER_S, GAP_OVERFLOW_MAX_S,
+                            )
+                    effective_end += overflow_budget_s
+                    slot_samples_eff = int(max(0.0, (effective_end - start)) * sr)
+                    if slot_samples_eff > 0 and wl > slot_samples_eff:
+                        overflow_s = (wl - slot_samples_eff) / sr
+                        adjusted = adjusted[..., :slot_samples_eff]
+                        wl = adjusted.shape[-1]
+                        fit_status.append({
+                            "status": "overflows",
+                            "overflow_s": round(overflow_s, 3),
+                        })
+                    else:
+                        fit_status.append({"status": "fits"})
+
+                else:
+                    # strict_slot (legacy): preserve the previous atempo / trim /
+                    # off semantics so existing callers and back-compat tests
+                    # keep passing.
+                    place_at = start
+                    effective_end = end
+                    if i + 1 < len(all_segment_wavs):
+                        next_start = all_segment_wavs[i + 1][0]
+                        gap = next_start - end
+                        if gap > GAP_OVERFLOW_BUFFER_S:
+                            effective_end = end + min(
+                                gap - GAP_OVERFLOW_BUFFER_S, GAP_OVERFLOW_MAX_S,
+                            )
+                    slot_samples = int(max(0.0, (effective_end - start)) * sr)
+                    if slot_fit != "off" and slot_samples > 0 and wl > slot_samples:
+                        if slot_fit == "time_stretch":
+                            ratio = wl / slot_samples
+                            capped_ratio = min(ratio, MAX_STRETCH_RATIO)
+                            capped_target = int(wl / capped_ratio)
+                            try:
+                                adjusted = await _pitch_preserving_stretch(
+                                    adjusted, capped_target, sr,
+                                )
+                                if adjusted.shape[-1] > slot_samples:
+                                    adjusted = adjusted[..., :slot_samples]
+                                if ratio > MAX_STRETCH_RATIO:
+                                    logger.info(
+                                        "seg %d compression %.2f× exceeded cap; "
+                                        "stretched to %.2f×, tail trimmed",
+                                        i, ratio, capped_ratio,
+                                    )
+                            except Exception as e:
+                                logger.warning(
+                                    "atempo stretch failed for seg %d (%.2f×), "
+                                    "falling back to linear interp: %s",
+                                    i, ratio, e,
+                                )
+                                adjusted = torch.nn.functional.interpolate(
+                                    adjusted.unsqueeze(0),
+                                    size=slot_samples,
+                                    mode='linear',
+                                    align_corners=False,
+                                ).squeeze(0)
+                        else:  # "trim"
+                            adjusted = adjusted[..., :slot_samples]
+                        wl = adjusted.shape[-1]
+                    fit_status.append({
+                        "status": "fits",
+                        "compression_applied": (slot_fit == "time_stretch"
+                                                and wl != int(natural_dur * sr)),
+                    })
+
+                # Common: short fades to avoid pops, then mix into disk-backed audio.
+                fade_ms = 15
+                fade_samples = int((fade_ms / 1000.0) * sr)
+                if wl > fade_samples * 2:
+                    ramp_up = torch.linspace(0, 1, fade_samples, device=adjusted.device)
+                    ramp_down = torch.linspace(1, 0, fade_samples, device=adjusted.device)
+                    adjusted[0, :fade_samples] *= ramp_up
+                    adjusted[0, -fade_samples:] *= ramp_down
+
+                s = int(place_at * sr)
+                if s < 0:
+                    adjusted = adjusted[..., -s:]
                     wl = adjusted.shape[-1]
-                fit_status.append({
-                    "status": "fits",
-                    "compression_applied": (slot_fit == "time_stretch"
-                                            and wl != int(natural_dur * sr)),
-                })
+                    s = 0
+                e = min(s + wl, total_samples)
+                if s < total_samples and e > s:
+                    mix_len = e - s
+                    seg_np = (
+                        adjusted[:, :mix_len]
+                        .detach()
+                        .cpu()
+                        .to(torch.float32)
+                        .clamp(-1.0, 1.0)
+                        .squeeze(0)
+                        .numpy()
+                    )
+                    mix_audio[s:e] += seg_np
+                try:
+                    del wav, adjusted
+                except Exception:
+                    pass
+                _release_audio_tensors()
 
-            # Common: short fades to avoid pops, then mix into full_audio.
-            fade_ms = 15
-            fade_samples = int((fade_ms / 1000.0) * sr)
-            if wl > fade_samples * 2:
-                ramp_up = torch.linspace(0, 1, fade_samples, device=adjusted.device)
-                ramp_down = torch.linspace(1, 0, fade_samples, device=adjusted.device)
-                adjusted[0, :fade_samples] *= ramp_up
-                adjusted[0, -fade_samples:] *= ramp_down
-
-            s = int(place_at * sr)
-            e = min(s + wl, total_samples)
-            if s < total_samples:
-                full_audio[:, s:e] += adjusted[:, :e - s]
-
-        lang_code = req.language_code or "und"
-        track_path = os.path.join(DUB_DIR, job_id, f"dubbed_{lang_code}.wav")
-        _t_save_0 = time.perf_counter()
-        # Apply invisible watermark to the final assembled track
-        full_audio = embed_watermark(full_audio, sr)
-        atomic_save_wav(track_path, full_audio, sr)
-        _t_save = time.perf_counter() - _t_save_0
-        _t_mix = _t_save_0 - _t_loop_end
+            _t_save_0 = time.perf_counter()
+            mix_audio.flush()
+            _write_memmap_wav_atomic(track_path, mix_audio[:mix_samples], sr)
+            _t_save = time.perf_counter() - _t_save_0
+            _t_mix = _t_save_0 - _t_loop_end
+        finally:
+            try:
+                mix_audio.flush()
+                mix_mmap = getattr(mix_audio, "_mmap", None)
+                if mix_mmap is not None:
+                    mix_mmap.close()
+            except Exception:
+                pass
+            try:
+                del mix_audio
+            except Exception:
+                pass
+            gc.collect()
+            try:
+                os.unlink(mix_path)
+            except OSError:
+                pass
+            # The final track is written; the mix_<id> scratch WAVs (silence /
+            # cached-fail / error slots) have served their only purpose as
+            # assembly inputs and would otherwise leak into the job dir.
+            for _mp in _mix_temp_paths:
+                try:
+                    os.unlink(_mp)
+                except OSError:
+                    pass
         # Per-track metadata. For stretch_video, the dub wav is at the new
         # (longer) timeline, so we record its actual duration here too — the
         # mux step needs this to know whether to use the original video as-is
         # or stretch it per the plan.
-        track_dur = full_audio.shape[-1] / sr if full_audio.shape[-1] > 0 else 0.0
+        track_dur = total_samples / sr if total_samples > 0 else 0.0
         job["dubbed_tracks"][lang_code] = {
             "path": track_path,
             "language": req.language,
@@ -928,8 +1156,9 @@ async def preview_segment(job_id: str, req: SegmentPreviewRequest):
         )
         return normalize_audio(mastered, target_dBFS=-2.0)
 
-    loop = asyncio.get_running_loop()
-    audio_tensor = await loop.run_in_executor(_gpu_pool, _gen)
+    # Bounded + pool-reset on hang so a wedged preview generate can't starve the
+    # GPU pool and brick the backend (#730 class).
+    audio_tensor = await run_on_gpu_pool_guarded(_gen, what="Dub preview generate")
 
     sr = getattr(_model, "sampling_rate", 24000)
     buf = io.BytesIO()

backend/api/routers/dub_translate.py

@@ -8,7 +8,7 @@ from fastapi.responses import JSONResponse
 
 from schemas.requests import TranslateRequest
 from services.model_manager import _cpu_pool, _gpu_pool
-from services.translator import cinematic_available, cinematic_refine_many
+from services.translator import cinematic_available, cinematic_refine_many, _cinematic_budget
 from api.routers.dub_core import _get_job
 
 router = APIRouter()
@@ -302,15 +302,20 @@ async def dub_translate(req: TranslateRequest):
             translated = await loop.run_in_executor(_gpu_pool, _translate_nllb)
             if os.environ.get("OMNIVOICE_UNLOAD_NLLB", "1") == "1":
                 _unload_nllb()
-            return {"translated": translated, "target_lang": req.target_lang, "source_lang": src_lang,
-                    **_dialect_flags(req, applied=False)}
+            # Cinematic/Autofit refine + rate-ratio badges must run for NLLB too
+            # (previously this returned before _maybe_cinematic, so a Cinematic
+            # pick on NLLB silently produced plain Fast output). Unloading NLLB
+            # first is fine — the refine LLM is a separate network provider.
+            return await _maybe_cinematic(translated, req, src_lang, loop)
 
         # OpenAI / Ollama Local LLM Translation
         if provider == "openai":
             base_url = os.environ.get("TRANSLATE_BASE_URL")
             model_name = os.environ.get("TRANSLATE_MODEL", "gpt-3.5-turbo")
             from openai import OpenAI
-            client = OpenAI(base_url=base_url, api_key=api_key or "local")
+            # max_retries=0: a 429 + long Retry-After must not let one segment's
+            # SDK call sleep+retry and blow the overall translate wall time.
+            client = OpenAI(base_url=base_url, api_key=api_key or "local", max_retries=0)
 
             def _build_prompt(src_code: str, tgt_code: str) -> str:
                 """Build a system prompt that resists hallucinations on small
@@ -399,25 +404,38 @@ async def dub_translate(req: TranslateRequest):
                             seg.id, attempt + 1, e,
                         )
                 # Both attempts failed — keep source text + flag error so the
-                # frontend can surface "fallback to literal" warning.
-                return {"id": seg.id, "text": seg.text, "error": last_err or "llm-failed"}
+                # frontend can surface "fallback to literal" warning. Scrub the
+                # provider error: some OpenAI-compatible providers echo the key
+                # or a user_id in the body, which must not reach the UI verbatim.
+                from core.scrub import scrub_provider_error
+                return {"id": seg.id, "text": seg.text,
+                        "error": scrub_provider_error(last_err, api_key) or "llm-failed"}
 
             tasks = [loop.run_in_executor(_cpu_pool, _translate_llm, seg) for seg in req.segments]
             translated = await asyncio.gather(*tasks)
             translated.sort(key=lambda x: str(x["id"]))
-            return {"translated": translated, "target_lang": req.target_lang, "source_lang": src_lang,
-                    **_dialect_flags(req, applied=True)}
+            # provider="openai" is already an LLM translation — _maybe_cinematic
+            # skips the reflect/adapt re-refine (already_llm) but still stamps
+            # rate-ratio badges and runs the bounded Autofit fit pass. Before
+            # this it returned here, so Cinematic/Autofit on the LLM engine did
+            # nothing.
+            return await _maybe_cinematic(translated, req, src_lang, loop, already_llm=True)
 
         # Offline Argos Translate
         if provider == "argos" or provider == "libretranslate":
             try:
                 import argostranslate  # noqa: F401
             except ImportError:
+                # Single-source the install command from the engine registry so
+                # this 400 and the proactive Install button in the Engine
+                # selector can never drift (see translation_engines.install_command).
+                from services.translation_engines import install_command
+                cmd = install_command("argos") or "uv pip install argostranslate"
                 friendly = (
                     f"The '{provider}' translation engine needs the optional "
                     f"`argostranslate` Python package, which isn't installed in "
-                    f"this backend. Install it with `uv pip install argostranslate` "
-                    f"(or `pip install argostranslate`) and restart the server, or "
+                    f"this backend. Install it with `{cmd}` "
+                    f"and restart the server, or "
                     f"switch the Engine dropdown to another provider."
                 )
                 return JSONResponse(status_code=400, content={"error": friendly})
@@ -460,8 +478,11 @@ async def dub_translate(req: TranslateRequest):
                 return results
 
             translated = await loop.run_in_executor(_cpu_pool, _translate_argos)
-            return {"translated": translated, "target_lang": req.target_lang, "source_lang": src_lang,
-                    **_dialect_flags(req, applied=False)}
+            # Argos is the DEFAULT engine — routing it through _maybe_cinematic is
+            # the headline fix: a user who picks Cinematic/Autofit on Argos now
+            # gets the LLM refine + fit pass (and rate-ratio badges in Fast mode)
+            # instead of silent plain-Fast output.
+            return await _maybe_cinematic(translated, req, src_lang, loop)
 
         # Legacy / API Deep_Translator logic.
         # Preflight the optional `deep_translator` dep once so we fail with a
@@ -470,11 +491,16 @@ async def dub_translate(req: TranslateRequest):
         try:
             import deep_translator  # noqa: F401
         except ImportError:
+            # Same single-source install command as the Engine selector's Install
+            # button (translation_engines.install_command) — google/deepl/
+            # microsoft/mymemory all share the deep_translator package.
+            from services.translation_engines import install_command
+            cmd = install_command(provider) or "uv pip install deep_translator"
             friendly = (
                 f"The '{provider}' translation engine needs the optional "
                 f"`deep_translator` Python package, which isn't installed in "
-                f"this backend. Install it with `uv pip install deep_translator` "
-                f"(or `pip install deep_translator`) and restart the server, or "
+                f"this backend. Install it with `{cmd}` "
+                f"and restart the server, or "
                 f"switch the Engine dropdown to Argos (local, bundled), NLLB "
                 f"(local, heavier), or OpenAI (LLM)."
             )
@@ -530,7 +556,11 @@ async def dub_translate(req: TranslateRequest):
                     )
                     time.sleep(0.25 * (attempt + 1))
             logger.error("translate %s -> %s gave up (provider=%s): %s", src_arg, seg_lc, provider, last_err)
-            return {"id": seg.id, "text": seg.text, "error": last_err or "unknown"}
+            # Scrub before it reaches the UI — DeepL/Microsoft errors can echo
+            # the API key (same class as the OpenAI user_id leak).
+            from core.scrub import scrub_provider_error
+            return {"id": seg.id, "text": seg.text,
+                    "error": scrub_provider_error(last_err, _deepl_key or _msft_key or api_key) or "unknown"}
 
         tasks = [loop.run_in_executor(_cpu_pool, _translate_single, seg) for seg in req.segments]
         translated = await asyncio.gather(*tasks)
@@ -544,24 +574,19 @@ async def dub_translate(req: TranslateRequest):
         return JSONResponse(status_code=500, content={"error": str(e)})
 
 
-async def _maybe_cinematic(translated, req, src_lang, loop):
-    """If quality=cinematic and a usable LLM is configured, run REFLECT+ADAPT.
-    Otherwise return Fast-mode shape unchanged.
+def _stamp_predicted_rate_ratio(translated, req) -> None:
+    """Stamp a predicted ``rate_ratio`` on every row that has a known slot.
+
+    No LLM needed — just the per-language CPS table from ``services/speech_rate``.
+    The UI's ``seg-rate-badge`` reads it (Fast mode included) to show which
+    segments will compress hard at generation time, so users can edit text or
+    pick a heavier quality. Mutates ``translated`` in place; never raises.
     """
-    quality = (getattr(req, "quality", None) or "fast").lower()
-    # Stamp the predicted rate_ratio on every translated row that has a
-    # known slot. Works for Fast mode too — no LLM needed; just the CPS
-    # table from services/speech_rate. The UI's `seg-rate-badge` reads
-    # this value and shows users which segments will compress hard at
-    # generation time, so they can edit text or pick Cinematic quality.
     try:
         from services.speech_rate import rate_ratio as _predict_rate_ratio
+        slots = {str(s.id): getattr(s, "slot_seconds", None) for s in req.segments}
         for row in translated:
-            seg_ref = next(
-                (s for s in req.segments if str(s.id) == str(row["id"])),
-                None,
-            )
-            slot = getattr(seg_ref, "slot_seconds", None) if seg_ref else None
+            slot = slots.get(str(row["id"]))
             text = (row.get("text") or "").strip()
             if slot and text and not row.get("error"):
                 row["rate_ratio"] = round(
@@ -570,19 +595,119 @@ async def _maybe_cinematic(translated, req, src_lang, loop):
     except Exception as e:
         logger.debug("non-LLM rate_ratio prediction skipped: %s", e)
 
-    base = {"translated": translated, "target_lang": req.target_lang, "source_lang": src_lang,
-            "quality_used": "fast", **_dialect_flags(req, applied=False)}
 
-    if quality != "cinematic":
+async def _apply_fit_pass(rows, req, slots_by_id, source_by_id, quality, loop, deadline) -> None:
+    """Run the Autofit slot-fit pass over ``rows`` concurrently, in place.
+
+    Bounded by ``deadline`` (shared with the cinematic refine) so a slow /
+    rate-limited LLM can't spin the fit pass per-segment unbounded — the old
+    behavior, which ran one blocking ``adjust_for_slot`` per segment in the
+    merge loop, outside any budget. Segments still running at the deadline keep
+    their current text and get ``rate_error='fit-budget'``. Only rows with a
+    slot + text + no prior error participate.
+    """
+    strict = (quality == "autofit")
+    items = []
+    for row in rows:
+        seg_id = str(row["id"])
+        slot = slots_by_id.get(seg_id)
+        text = row.get("text") or ""
+        if slot and text and not row.get("error"):
+            items.append((seg_id, text, float(slot), req.target_lang,
+                          source_by_id.get(seg_id), strict))
+    if not items:
+        return
+    try:
+        from services.speech_rate import adjust_for_slot_many
+        fits = await adjust_for_slot_many(
+            items, executor=_cpu_pool, deadline=deadline, loop=loop,
+        )
+    except Exception as e:
+        logger.warning("rate-fit pass skipped: %s", e)
+        return
+    for row in rows:
+        f = fits.get(str(row["id"]))
+        if not f:
+            continue
+        if f.get("text"):
+            row["text"] = f["text"]
+        if f.get("rate_ratio") is not None:
+            row["rate_ratio"] = f["rate_ratio"]
+        if f.get("error"):
+            row["rate_error"] = f["error"]
+
+
+async def _maybe_cinematic(translated, req, src_lang, loop, *, already_llm=False):
+    """Post-process a literal translation into Cinematic/Autofit output.
+
+    Runs for EVERY provider now (Argos/NLLB/Google/…/OpenAI). The three
+    LLM-independent branches (nllb/argos) and the openai branch used to return
+    *before* reaching this, so a Cinematic/Autofit pick on them — including the
+    DEFAULT Argos engine — silently produced plain Fast output with a success
+    toast. Fast mode still returns the plain translation (plus rate-ratio badges).
+
+    ``already_llm`` (provider="openai"): the translation was itself produced by
+    an LLM, so the REFLECT+ADAPT *re*-refine is skipped, but the bounded Autofit
+    fit pass + rate-ratio stamping still run, and the dialect the translate
+    prompt already baked in is reported as applied.
+    """
+    quality = (getattr(req, "quality", None) or "fast").lower()
+
+    _stamp_predicted_rate_ratio(translated, req)
+
+    # #280 item 2 — regional dialect hint, guarded against a stale dialect from
+    # another language. For already_llm the initial translate prompt already
+    # applied it, so it's reported applied in the Fast-shape base too.
+    dialect_hint = ""
+    _dialect = getattr(req, "dialect", None)
+    if _dialect and str(_dialect).lower().startswith(str(req.target_lang).lower()[:2]):
+        dialect_hint = dialect_clause(_dialect)
+
+    base = {"translated": translated, "target_lang": req.target_lang, "source_lang": src_lang,
+            "quality_used": "fast",
+            **_dialect_flags(req, applied=(already_llm and bool(dialect_hint)))}
+
+    # Fast (and anything unrecognised) returns the plain translation unchanged.
+    if quality not in ("cinematic", "autofit"):
         return base
 
+    source_by_id: dict[str, str] = {str(s.id): s.text for s in req.segments}
+    slots_by_id = {
+        str(s.id): getattr(s, "slot_seconds", None)
+        for s in req.segments
+        if getattr(s, "slot_seconds", None)
+    }
+
+    # One wall-clock deadline shared by the whole LLM phase (refine + fit), so a
+    # slow/rate-limited provider can't run either pass unbounded. <=0 disables.
+    budget = _cinematic_budget()
+    deadline = (loop.time() + budget) if budget and budget > 0 else None
+
+    # provider="openai": already an LLM translation → skip REFLECT+ADAPT, keep
+    # the rate-ratio badges, still run the bounded fit pass.
+    if already_llm:
+        merged = []
+        for row in translated:
+            out = {"id": row["id"],
+                   "text": row.get("text", "") or "",
+                   "literal": row.get("text", "") or ""}
+            if row.get("error"):
+                out["error"] = row["error"]
+            if "rate_ratio" in row:
+                out["rate_ratio"] = row["rate_ratio"]
+            merged.append(out)
+        await _apply_fit_pass(merged, req, slots_by_id, source_by_id, quality, loop, deadline)
+        return {"translated": merged, "target_lang": req.target_lang,
+                "source_lang": src_lang, "quality_used": quality,
+                **_dialect_flags(req, applied=bool(dialect_hint))}
+
+    # Non-LLM provider → the reflect/adapt refine needs a separately-configured
+    # LLM (Settings → LLM Providers). Without one, degrade to Fast with a flag.
     if not cinematic_available():
-        logger.warning("cinematic requested but no LLM configured — returning Fast result.")
+        logger.warning("%s requested but no LLM configured — returning Fast result.", quality)
         base["cinematic_skipped"] = "no-llm-configured"
         return base
 
-    # Build a map from id → original segment (to fetch source text + direction).
-    source_by_id: dict[str, str] = {str(s.id): s.text for s in req.segments}
     directions: dict[str, str] = {
         str(s.id): s.direction
         for s in req.segments
@@ -590,7 +715,7 @@ async def _maybe_cinematic(translated, req, src_lang, loop):
     }
     pairs = []
     passthrough_index = {}
-    for i, row in enumerate(translated):
+    for row in translated:
         seg_id = str(row["id"])
         literal = row.get("text", "") or ""
         if row.get("error") or not literal.strip():
@@ -601,12 +726,6 @@ async def _maybe_cinematic(translated, req, src_lang, loop):
     if not pairs:
         return base
 
-    # #280 item 2: thread the regional-dialect hint into the reflect/adapt
-    # prompts. Guard against a stale dialect from another language.
-    dialect_hint = ""
-    if req.dialect and str(req.dialect).lower().startswith(str(req.target_lang).lower()[:2]):
-        dialect_hint = dialect_clause(req.dialect)
-
     refined = await cinematic_refine_many(
         pairs,
         source_lang=src_lang,
@@ -618,16 +737,6 @@ async def _maybe_cinematic(translated, req, src_lang, loop):
     )
     refined_by_id = {r["id"]: r for r in refined}
 
-    # Phase 4.4 — speech-rate fit pass. Segment boundaries aren't in the
-    # translate request (by design — translator is boundary-agnostic), so we
-    # only run it when the caller supplied `slot_seconds` on each segment.
-    # The frontend populates this for Cinematic calls from the edit view.
-    slots_by_id = {
-        str(s.id): getattr(s, "slot_seconds", None)
-        for s in req.segments
-        if getattr(s, "slot_seconds", None)
-    }
-
     merged = []
     for row in translated:
         seg_id = str(row["id"])
@@ -646,35 +755,15 @@ async def _maybe_cinematic(translated, req, src_lang, loop):
         }
         if r.get("error"):
             out["error"] = r["error"]
-
-        # Optional slot-fit pass — only when the caller asked for cinematic
-        # *and* provided a slot. Runs best-effort; no-LLM or mid-loop failure
-        # just leaves the cinematic text untouched.
-        slot = slots_by_id.get(seg_id)
-        if slot and out["text"]:
-            try:
-                from services.speech_rate import adjust_for_slot
-                fit = await asyncio.to_thread(
-                    adjust_for_slot,
-                    out["text"],
-                    slot_seconds=float(slot),
-                    target_lang=req.target_lang,
-                    source_text=source_by_id.get(seg_id),
-                )
-                if fit.get("text"):
-                    out["text"] = fit["text"]
-                out["rate_ratio"] = fit.get("rate_ratio")
-                if fit.get("error"):
-                    out["rate_error"] = fit["error"]
-            except Exception as e:
-                logger.warning("rate-fit skipped for %s: %s", seg_id, e)
-
         merged.append(out)
 
+    # Phase 4.4 speech-rate fit pass — now concurrent + bounded (see helper).
+    await _apply_fit_pass(merged, req, slots_by_id, source_by_id, quality, loop, deadline)
+
     return {
         "translated": merged,
         "target_lang": req.target_lang,
         "source_lang": src_lang,
-        "quality_used": "cinematic",
+        "quality_used": quality,
         **_dialect_flags(req, applied=bool(dialect_hint)),
     }

backend/api/routers/engines.py

@@ -15,6 +15,8 @@ Environment variables (`OMNIVOICE_TTS_BACKEND`, `OMNIVOICE_ASR_BACKEND`,
 `OMNIVOICE_LLM_BACKEND`) still win over the UI choice so power-users can pin
 a backend without Settings silently undoing it.
 """
+import os
+import threading
 from time import perf_counter
 
 from fastapi import APIRouter, Depends, HTTPException
@@ -261,6 +263,169 @@ def engine_health(engine_id: str):
     }
 
 
+# ── Real-synthesis self-test (in-process TTS engines) ──────────────────────
+#
+# ``/health`` above is a liveness/import probe — for an in-process backend it
+# only calls ``is_available()`` and the UI labels the result "deps OK". This
+# route goes one step further: for an AVAILABLE, IN-PROCESS TTS engine it runs
+# a *tiny real synthesis* from a fixed short phrase and reports duration +
+# sample-rate + sample count, proving the engine actually emits audio rather
+# than merely importing. The Compat Matrix's "Self-test" button calls it.
+#
+# Guardrails (kept identical across macOS/Windows/Linux per the default-feature
+# rule — the phrase, timeout and gating don't branch on OS):
+#   * TTS family + available + in-process only. Subprocess engines keep their
+#     spawn-and-ping ``health_check`` (a real synth there is a sidecar
+#     cold-start — out of scope for a click-to-test affordance).
+#   * Bounded wall-clock timeout (``OMNIVOICE_SELFTEST_TIMEOUT_S``, default 90s):
+#     a runaway synth returns ``ok=False`` / ``timed_out=True`` instead of
+#     hanging the Settings panel. The orphaned worker is best-effort daemon.
+#   * A process-wide lock serialises self-tests so a click-storm can't stack
+#     concurrent model loads.
+#   * Only ever on user click (POST) — never on Settings load. Loopback-gated.
+
+# Deliberately short + ASCII so the synth stays CPU-cheap and the phrase never
+# trips the no-hardcoded-CJK guard.
+_SELFTEST_PHRASE = "OmniVoice engine self test."
+_SELFTEST_LOCK = threading.Lock()
+
+
+def _selftest_timeout_s() -> float:
+    try:
+        return max(1.0, float(os.environ.get("OMNIVOICE_SELFTEST_TIMEOUT_S", "90")))
+    except (TypeError, ValueError):
+        return 90.0
+
+
+def _sample_count(audio) -> int:
+    """Total sample count of an engine's ``generate()`` return, tolerant of
+    torch.Tensor / numpy.ndarray / list shapes. 0 when it can't be measured."""
+    try:
+        shape = getattr(audio, "shape", None)
+        if shape is not None and len(shape) > 0:
+            return int(shape[-1])
+        return int(len(audio))
+    except Exception:
+        return 0
+
+
+def _run_synth_bounded(backend, timeout_s: float) -> dict | None:
+    """Run one tiny synthesis in a daemon thread, bounded by ``timeout_s``.
+
+    Returns ``{"audio": .., "duration_ms": ..}`` on success, ``{"error": exc}``
+    on a synth exception, or ``None`` when the timeout elapsed (worker left
+    running best-effort — Python threads can't be force-killed)."""
+    box: dict = {}
+
+    def _worker():
+        t0 = perf_counter()
+        try:
+            audio = backend.generate(_SELFTEST_PHRASE, language="en", num_step=8)
+            box["audio"] = audio
+        except Exception as exc:  # noqa: BLE001 — surfaced to the caller as ok=False
+            box["error"] = exc
+        finally:
+            box["duration_ms"] = (perf_counter() - t0) * 1000.0
+
+    th = threading.Thread(target=_worker, name="engine-selftest", daemon=True)
+    th.start()
+    th.join(timeout_s)
+    if th.is_alive():
+        return None
+    return box
+
+
+class SelfTestResponse(BaseModel):
+    id: str
+    ok: bool
+    message: str
+    duration_ms: float
+    sample_rate: int | None = None
+    num_samples: int | None = None
+    audio_seconds: float | None = None
+    timed_out: bool = False
+
+
+@router.post(
+    "/engines/{engine_id}/selftest",
+    response_model=SelfTestResponse,
+    dependencies=[Depends(require_loopback)],
+)
+def engine_selftest(engine_id: str):
+    """Run a bounded, real synthesis on an available in-process TTS engine.
+
+    404 for an unknown TTS id; 400 when the engine is subprocess-isolated or
+    not currently available (a real synth on either is meaningless). Never
+    raises through to a 500 on a synth failure — the exception is captured into
+    ``ok=False`` / ``message`` so the panel renders a per-row failure."""
+    if engine_id not in tts_backend._REGISTRY:
+        raise HTTPException(
+            status_code=404,
+            detail=f"unknown TTS engine id: {engine_id!r}",
+        )
+    cls = tts_backend._REGISTRY[engine_id]
+    if getattr(cls, "_is_subprocess_isolated", False):
+        raise HTTPException(
+            status_code=400,
+            detail=(
+                f"{engine_id} is subprocess-isolated — self-test runs real "
+                "synthesis for in-process engines only. Use Test engine "
+                "(spawn-and-ping) for subprocess engines."
+            ),
+        )
+    try:
+        ok, msg = cls.is_available()
+    except Exception as exc:  # noqa: BLE001
+        ok, msg = False, f"{type(exc).__name__}: {exc}"
+    if not ok:
+        raise HTTPException(
+            status_code=400,
+            detail=(
+                f"{engine_id} is not available: {tts_backend._mask_hf_tokens(msg)}. "
+                "Install/enable the engine, then self-test."
+            ),
+        )
+
+    timeout_s = _selftest_timeout_s()
+    # Serialise so a click-storm can't stack concurrent model loads.
+    with _SELFTEST_LOCK:
+        backend = _get_engine_instance(cls)
+        res = _run_synth_bounded(backend, timeout_s)
+
+    if res is None:
+        return SelfTestResponse(
+            id=engine_id,
+            ok=False,
+            message=f"timed out after {timeout_s:.0f}s (model still loading?)",
+            duration_ms=timeout_s * 1000.0,
+            timed_out=True,
+        )
+    if "error" in res:
+        exc = res["error"]
+        return SelfTestResponse(
+            id=engine_id,
+            ok=False,
+            message=tts_backend._mask_hf_tokens(f"{type(exc).__name__}: {exc}"),
+            duration_ms=res.get("duration_ms", 0.0),
+        )
+
+    n = _sample_count(res.get("audio"))
+    try:
+        sr = int(getattr(backend, "sample_rate", 0) or 0) or None
+    except Exception:
+        sr = None
+    secs = round(n / sr, 3) if (sr and n) else None
+    return SelfTestResponse(
+        id=engine_id,
+        ok=n > 0,
+        message="synthesized" if n > 0 else "engine returned no audio",
+        duration_ms=res["duration_ms"],
+        sample_rate=sr,
+        num_samples=n or None,
+        audio_seconds=secs,
+    )
+
+
 class SelectEngineRequest(BaseModel):
     family: str   # "tts" | "asr" | "llm"
     backend_id: str

backend/api/routers/generation.py

@@ -1,7 +1,9 @@
 import os
 import io
+import re
 import uuid
 import time
+import random
 import asyncio
 import tempfile
 import contextlib
@@ -11,16 +13,36 @@ from typing import Optional
 from fastapi import APIRouter, File, Form, UploadFile, HTTPException
 from fastapi.responses import StreamingResponse
 
-from core.db import db_conn
+import sqlite3
+from core.db import db_conn, ensure_schema
 from core.config import OUTPUTS_DIR, VOICES_DIR
-from services.model_manager import get_model, _gpu_pool
+import functools
+from services.model_manager import (
+    get_model, _gpu_pool, run_on_gpu_pool_guarded, GpuJobTimeoutError,
+)
 from services.audio_io import _safe_torchaudio_save
 from core import event_bus
+from omnivoice.utils.voice_design import heal_design_instruct
 
 router = APIRouter()
 logger = logging.getLogger("omnivoice.generate")
 
 
+def _profile_instruct(row):
+    """Validator-safe instruct for a stored profile row.
+
+    Sanitizes the persisted instruct (dropping the ``"[object Object]"``
+    sentinel / freeform prose that older builds saved) and, for a design row,
+    rebuilds the tags from ``vd_states`` when the stored value is unusable — so
+    a poisoned/legacy profile never 400-s generation (#550 #571 #594 #596).
+    """
+    try:
+        vd = row["vd_states"]
+    except (KeyError, IndexError):
+        vd = None
+    return heal_design_instruct(row["instruct"], vd)
+
+
 def _render_with_pauses(gen_span, segments, sample_rate):
     """Synthesize ``[(text, pause_ms), ...]`` spans and stitch silence between
     them (issue #276).
@@ -60,6 +82,23 @@ def _render_with_pauses(gen_span, segments, sample_rate):
     return torch.cat(parts, dim=-1)
 
 
+def _sanitize_audio(audio_out):
+    """Replace non-finite samples (NaN / ±inf) with silence so a model glitch
+    can't produce an unreadable WAV (#629). Returns the input unchanged when it's
+    already finite or isn't a tensor. Never raises."""
+    try:
+        import torch
+        if torch.is_tensor(audio_out) and not bool(torch.isfinite(audio_out).all()):
+            logger.warning(
+                "Generated audio contained non-finite samples (NaN/inf) — "
+                "sanitizing to silence to keep the WAV decodable (#629)."
+            )
+            return torch.nan_to_num(audio_out, nan=0.0, posinf=0.0, neginf=0.0)
+    except Exception:
+        pass
+    return audio_out
+
+
 def _apply_effect_chain(audio_out, sample_rate, effect_preset, *, skip_mastering=False):
     """Shared post-DSP for /generate: preset validation → mastering →
     effect chain → loudness normalization.
@@ -75,6 +114,14 @@ def _apply_effect_chain(audio_out, sample_rate, effect_preset, *, skip_mastering
         apply_effects_chain, get_effect_chain,
     )
 
+    # #629: a numerical glitch in the model (observed on MPS) can leave NaN/±inf
+    # samples, which write an unreadable WAV that then fails decoding with an
+    # opaque "ffmpeg returned error code: 183 / Invalid data" — surfaced to the
+    # user as a misleading "ran out of memory". Replace non-finite samples with
+    # silence here, before any DSP/encode touches the audio, so the output is
+    # always a valid WAV. Covers the raw path too (it returns just below).
+    audio_out = _sanitize_audio(audio_out)
+
     preset = effect_preset or "broadcast"
     if preset not in EFFECT_PRESETS:
         raise ValueError(
@@ -96,6 +143,136 @@ def _apply_effect_chain(audio_out, sample_rate, effect_preset, *, skip_mastering
     return normalize_audio(audio_out, target_dBFS=-2.0)
 
 
+def _exception_chain(e):
+    """Yield ``e`` plus every ``__cause__``/``__context__`` beneath it
+    (cycle-safe). Engines and hub libraries routinely wrap the original
+    transport/allocator error, so classification must look at the whole
+    chain, not just the outermost message."""
+    seen = set()
+    stack = [e]
+    while stack:
+        exc = stack.pop()
+        if exc is None or id(exc) in seen:
+            continue
+        seen.add(id(exc))
+        yield exc
+        stack.append(exc.__cause__)
+        stack.append(exc.__context__)
+
+
+# #880: transport-level exception type names from httpx (huggingface_hub ≥1.x
+# downloads over it) and requests/urllib3 (older engine deps). Any of these
+# anywhere in the exception chain means the network — not memory — killed the
+# generation.
+_NETWORK_EXC_NAMES = frozenset({
+    # httpx
+    "ConnectError", "ConnectTimeout", "ReadTimeout", "ReadError",
+    "WriteError", "WriteTimeout", "PoolTimeout", "NetworkError",
+    "TransportError", "RemoteProtocolError", "ProxyError", "CloseError",
+    # requests / urllib3
+    "ConnectionError", "ChunkedEncodingError", "MaxRetryError",
+    "NewConnectionError", "ProtocolError",
+    # stdlib socket-level drops mid-download
+    "ConnectionResetError", "ConnectionAbortedError", "ConnectionRefusedError",
+    # huggingface_hub: failed first-use download with nothing in the disk cache
+    "LocalEntryNotFoundError",
+})
+
+# Same class, but the transport error was stringified into a wrapper message
+# (so the type name is gone). All lowercase; matched against .lower().
+_NETWORK_MSG_SIGNATURES = (
+    "client has been closed",    # httpx closed-client lifecycle error (#880)
+    "cannot send a request",     # httpx: same error, message head
+    "connection error",          # requests / huggingface_hub wording
+    "connection reset",          # ECONNRESET mid-download
+    "read timed out",            # requests/urllib3 timeout wording
+    "max retries exceeded",      # urllib3 retry exhaustion
+    "temporary failure in name resolution",  # DNS down (glibc)
+    "name or service not known",             # DNS down (glibc)
+    "getaddrinfo failed",                    # DNS down (Windows)
+)
+
+
+def _is_network_failure(e) -> bool:
+    """True iff the failure (anywhere in its chain) is an HTTP-client
+    lifecycle / network-transport error — e.g. a first-use model download
+    from the HF Hub dying mid-generation (#880)."""
+    for exc in _exception_chain(e):
+        if type(exc).__name__ in _NETWORK_EXC_NAMES:
+            return True
+        low = str(exc).lower()
+        if any(sig in low for sig in _NETWORK_MSG_SIGNATURES):
+            return True
+    return False
+
+
+# Signatures of an *actual* out-of-memory condition. All lowercase.
+_OOM_MSG_SIGNATURES = (
+    "out of memory",               # CUDA / MPS / generic torch wording
+    "not enough memory",           # torch CPU DefaultCPUAllocator
+    "cannot allocate memory",      # OS-level ENOMEM
+    "std::bad_alloc",              # C++ allocator failure
+    "cublas_status_alloc_failed",  # cuBLAS workspace allocation
+    "cuda_error_out_of_memory",    # raw CUDA driver error name
+    "paging file is too small",    # Windows [WinError 1455] mapping DLLs
+)
+
+
+def _is_oom_failure(e) -> bool:
+    """True iff the failure (anywhere in its chain) actually looks like an
+    out-of-memory condition — the only case where the Flush hint is honest."""
+    for exc in _exception_chain(e):
+        if isinstance(exc, MemoryError):
+            return True
+        # torch.cuda.OutOfMemoryError subclasses RuntimeError; match by name
+        # so this needs no torch import (and covers other frameworks' twins).
+        if type(exc).__name__ == "OutOfMemoryError":
+            return True
+        low = str(exc).lower()
+        if any(sig in low for sig in _OOM_MSG_SIGNATURES):
+            return True
+    return False
+
+
+# #919: an engine that requires a model path / env var which isn't set (or is
+# set to a directory missing its model files) fails with a *configuration*
+# error, not a runtime one. The reporting user selected sherpa-onnx and hit
+# "OMNIVOICE_SHERPA_MODEL not set. Point it to a sherpa-onnx TTS model
+# directory …" — a pure setup problem — yet the OOM catch-all told them (on a
+# 63 GB-RAM box) to press Flush for memory they never ran out of. Classify the
+# whole CLASS of "engine not configured / required env var not set" errors so
+# any current or future opt-in engine (sherpa/Confucius4/dots/MOSS …) surfaces
+# actionable setup guidance instead of the memory hint. All lowercase; matched
+# over the whole exception chain (engines wrap the original error).
+_CONFIG_MSG_SIGNATURES = (
+    "not set. point it to",      # sherpa: OMNIVOICE_SHERPA_MODEL not set
+    "no model.onnx found in",    # sherpa: dir set but the model file is missing
+    "not configured",            # generic "engine not configured" wording
+    "venv not found. set",       # confucius4/dots/MOSS dedicated-venv opt-ins
+    "unavailable: omnivoice_",   # is_available() reason wrapped by _ensure_loaded
+)
+
+# An OMNIVOICE_* engine env var named alongside "not set" / "point it to" /
+# "set omnivoice_…" is the strongest config-missing signal and generalizes to
+# any engine gated on such a var (issue #919 class).
+_CONFIG_ENV_RE = re.compile(r"omnivoice_[a-z0-9_]+")
+
+
+def _is_config_failure(e) -> bool:
+    """True iff the failure is a *configuration* problem — a required engine
+    model path / env var that isn't set (or points nowhere) — rather than a
+    runtime fault. The remedy is to set the value, never to Flush VRAM."""
+    for exc in _exception_chain(e):
+        low = str(exc).lower()
+        if any(sig in low for sig in _CONFIG_MSG_SIGNATURES):
+            return True
+        if _CONFIG_ENV_RE.search(low) and (
+            "not set" in low or "point it to" in low or "set omnivoice_" in low
+        ):
+            return True
+    return False
+
+
 def _oom_friendly_reraise(e):
     """Best-effort cache flush + the user-facing OOM hint shared by both
     inference paths."""
@@ -127,10 +304,116 @@ def _oom_friendly_reraise(e):
             f"or run `chmod +x` on the engine binary named in the error. "
             f"Underlying error: {e}"
         ) from e
+    # #629: a decode/ffmpeg failure on the rendered audio is NOT out of memory —
+    # it's unreadable audio (usually a transient numerical glitch). Say so rather
+    # than sending the user down the OOM path.
+    if "ffmpeg returned error" in es or "Decoding failed" in es or "Invalid data found" in es:
+        raise RuntimeError(
+            f"The engine produced unreadable audio (a decode step failed) — this is "
+            f"usually a transient glitch. Use the Flush button to reload the model, "
+            f"then regenerate. Underlying error: {e}"
+        ) from e
+    # #664: a bad voice-design instruct (free-form prose, mixed EN/ZH, or
+    # conflicting tags) raises "Unsupported instruct items …" / "Cannot mix …
+    # in a single instruct" / "Conflicting instruct items …" from omnivoice's
+    # _resolve_instruct. That's a USER-INPUT validation error, not an OOM. Match
+    # on the message signature (NOT the type — a lower layer can wrap the original
+    # ValueError, which is why the route's `except ValueError` guard misses it)
+    # and re-raise as a clean ValueError so the route returns a 400 with the
+    # instruct guidance, instead of a 500 telling the user to Flush for memory
+    # they never ran out of. (Complements the client-side guard in #658/#612.)
+    _low = es.lower()
+    if ("unsupported instruct items" in _low
+            or "conflicting instruct items" in _low
+            or "in a single instruct" in _low):
+        raise ValueError(es) from e
+    # #705: a corrupt or wrong-architecture native component (a .dll / .pyd / .exe
+    # — torch, ffmpeg, or a bundled engine binary) fails to load/spawn on Windows
+    # with "[WinError 193] %1 is not a valid Win32 application". That is NOT OOM,
+    # and Flush won't help — reinstalling/repairing the component is the real fix.
+    if "[winerror 193]" in _low or "is not a valid win32 application" in _low:
+        raise RuntimeError(
+            f"A native component (a DLL / .pyd / .exe — e.g. torch, ffmpeg, or an "
+            f"engine binary) is corrupt or built for the wrong architecture "
+            f"([WinError 193]). Reinstall or repair that component — the Flush "
+            f"button won't help here. Underlying error: {e}"
+        ) from e
+    # #715: a "[Errno 32] Broken pipe" (BrokenPipeError) surfacing from
+    # generation is NOT out of memory — it means the backend's stdout/stderr
+    # pipe to the desktop shell that launched it closed mid-render (an orphaned
+    # backend whose parent shell exited or relaunched). main.py wraps
+    # sys.stdout/stderr to swallow EPIPE, but a C-level write inside the native
+    # engine/torch can still raise one past that guard. Flush won't help —
+    # relaunching the app re-parents the backend to a live shell.
+    # #756: the GPU's compute capability isn't in this PyTorch build's arch list,
+    # so CUDA can't launch kernels ("no kernel image is available for execution").
+    # NOT OOM. get_best_device() now falls back to CPU up front, but classify the
+    # raw error too in case CUDA was forced (OMNIVOICE_FORCE_CUDA) or a sub-path
+    # still ran on the GPU — point at the real fix, not the Flush button.
+    if "no kernel image is available" in _low:
+        raise RuntimeError(
+            f"Your GPU isn't supported by the installed PyTorch build (CUDA can't "
+            f"launch kernels for its compute capability). Switch the compute device "
+            f"to CPU in Settings, or install a matching PyTorch (e.g. a cu128 build "
+            f"for newer GPUs). The Flush button won't help. Underlying error: {e}"
+        ) from e
+    if isinstance(e, BrokenPipeError) or "broken pipe" in _low or "errno 32" in _low:
+        raise RuntimeError(
+            f"The backend lost its output pipe mid-generation — the desktop app "
+            f"that launched it closed or relaunched ([Errno 32] Broken pipe). "
+            f"Restart the app and try again; the Flush button won't help here. "
+            f"Underlying error: {e}"
+        ) from e
+    # #880: an httpx/requests transport failure surfacing from generation —
+    # most commonly a first-use model download from the HF Hub dying with
+    # httpx's "Cannot send a request, as the client has been closed" (the
+    # shared client got closed mid-lifecycle), a connect/read timeout, or a
+    # dropped connection — is NOT out of memory. The model never finished
+    # loading, so Flush is the wrong remedy; retrying is. Matched over the
+    # whole exception chain (type names + stringified signatures) because
+    # engines wrap the original transport error.
+    if _is_network_failure(e):
+        raise RuntimeError(
+            f"A model download or network call failed mid-generation (usually "
+            f"the engine fetching its model files on first use). This is a "
+            f"network problem, not a memory problem — flushing VRAM won't "
+            f"help. Retry the generation; if it keeps failing, check your "
+            f"internet connection and any HF_ENDPOINT/mirror setting. "
+            f"Underlying error: {e}"
+        ) from e
+    # #919: a required engine model path / env var that isn't set is a pure
+    # CONFIGURATION problem, not a runtime one. sherpa-onnx's
+    # "OMNIVOICE_SHERPA_MODEL not set. Point it to …" used to fall through to
+    # the OOM catch-all, telling a user with 63 GB of RAM to press Flush. Point
+    # at the real fix — set the variable — and never mention memory or Flush.
+    # The underlying error already names the exact variable + what to point it
+    # at (and Settings → Engines shows a copy-paste setup line), so keep it
+    # front-and-center. Checked before the OOM branch so a config error can
+    # never be mislabeled as memory.
+    if _is_config_failure(e):
+        raise RuntimeError(
+            f"This TTS engine isn't set up yet — it needs a model path or "
+            f"environment variable that isn't configured, so nothing was "
+            f"generated. Set it as the underlying error describes (it names the "
+            f"exact variable and what to point it at), then restart OmniVoice — "
+            f"or pick a ready engine in Settings → Engines. This is a setup "
+            f"problem, not a memory one. Underlying error: {e}"
+        ) from e
+    # #880 (the class bug): the OOM hint used to be the catch-all fallback,
+    # so ANY unrecognized error told the user to press Flush for memory they
+    # never ran out of. Only claim OOM when something in the chain actually
+    # looks like one; everything else surfaces as what it is — unrecognized —
+    # with the real error front and center.
+    if _is_oom_failure(e):
+        raise RuntimeError(
+            f"TTS engine stopped mid-generation. This usually means it ran out of memory. "
+            f"Try the Flush button to reload the model, then regenerate. Underlying error: {e}"
+        ) from e
     raise RuntimeError(
-        f"TTS engine stopped mid-generation. This usually means it ran out of memory. "
-        f"Try the Flush button to reload the model, then regenerate. Underlying error: {e}"
-    )
+        f"TTS engine stopped mid-generation with an error OmniVoice doesn't "
+        f"recognize. Retry once; if it keeps failing, please report it with "
+        f"the full trace. Underlying error: {e}"
+    ) from e
 
 
 def _run_inference(
@@ -318,7 +601,21 @@ async def generate_speech(
     # boundaries and crossfaded. 0 disables chunking (whole text to engine).
     max_chunk_chars: int = Form(800, ge=0),
     crossfade_ms: int = Form(50, ge=0, le=1000),
+    # Expressive-TTS Spec 01: apply the user pronunciation dictionary + inline
+    # [[…]] overrides to the text before synthesis. Default ON; the global
+    # OMNIVOICE_PRONUNCIATION pref can disable it for power users. Omitting it
+    # with an empty dictionary is byte-identical to legacy behavior.
+    pronounce: bool = Form(True),
 ):
+    # #502: NFC-normalize the input text so decomposed (NFD) diacritics — common
+    # in pasted Vietnamese and other Latin-with-marks text — are composed to the
+    # single codepoints the tokenizer/model expect, instead of base-letter +
+    # combining-mark sequences that render as distorted/garbled speech. NFC is a
+    # no-op for already-composed text; mirrors the duration estimator
+    # (utils/duration.py) so the estimate and the synthesis see the same text.
+    import unicodedata
+    text = unicodedata.normalize("NFC", text)
+
     # ── Engine resolution (issue #312) ──────────────────────────────────────
     # The request runs on the engine selected in Settings (POST /engines/select,
     # env var OMNIVOICE_TTS_BACKEND wins), or an explicit per-request `engine`
@@ -400,7 +697,7 @@ async def generate_speech(
                 if not ref_text:
                     ref_text = row["ref_text"]
                 if not instruct:
-                    instruct = row["instruct"]
+                    instruct = _profile_instruct(row)
                 if used_seed is None and row["seed"] is not None:
                     used_seed = row["seed"]
             elif profile_kind == "design":
@@ -410,14 +707,14 @@ async def generate_speech(
                 if ref_audio_path and not ref_text and row["ref_text"]:
                     ref_text = row["ref_text"]
                 if not instruct:
-                    instruct = row["instruct"]
+                    instruct = _profile_instruct(row)
                 if used_seed is None and row["seed"] is not None:
                     used_seed = row["seed"]
             elif row["instruct"] and not row["is_locked"] and not row["ref_audio_path"]:
                 # Legacy design-shaped row (pre-0004 archetype materialization
                 # failure path): instruct-only conditioning.
                 if not instruct:
-                    instruct = row["instruct"]
+                    instruct = _profile_instruct(row)
                 if used_seed is None and row["seed"] is not None:
                     used_seed = row["seed"]
             else:
@@ -430,6 +727,20 @@ async def generate_speech(
                     used_seed = row["seed"]
             if language == "Auto":
                 language = None
+            # #533: a profile's stored language must drive generation when the
+            # request didn't pin one. Without this the German (etc.) archetype
+            # generates with language=None and the model drifts to English —
+            # even though the archetype PREVIEW renders correctly (archetypes.py
+            # passes the language). An EXPLICIT non-Auto request language still
+            # wins; we only fill the gap. `row` is a sqlite3.Row, so guard the
+            # column lookup for pre-language DBs mid-upgrade.
+            if language is None:
+                try:
+                    prof_lang = row["language"]
+                except (KeyError, IndexError):
+                    prof_lang = None
+                if prof_lang and prof_lang != "Auto":
+                    language = prof_lang
     elif ref_audio is not None:
         try:
             with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as f:
@@ -446,32 +757,88 @@ async def generate_speech(
     # fallback behaves exactly as before.
     if ref_audio_path and not ref_text:
         from services.asr_backend import transcribe_reference
-        ref_text = await asyncio.get_running_loop().run_in_executor(
-            _gpu_pool, transcribe_reference, ref_audio_path
-        )
+        # Same #730 hang risk as any whisperx transcribe — bound + reset the pool
+        # so a wedged reference transcribe can't brick the backend. This path is
+        # best-effort (transcribe_reference returns None on failure → the model's
+        # built-in ASR fallback), so a timeout degrades to None rather than
+        # failing the whole generate.
+        try:
+            ref_text = await run_on_gpu_pool_guarded(
+                functools.partial(transcribe_reference, ref_audio_path),
+                what="Reference transcribe",
+            )
+        except GpuJobTimeoutError as e:
+            logger.warning("reference transcribe hung (%s); using model ASR fallback", e)
+            ref_text = None
+
+    # #526: materialize a concrete seed when none was supplied (and no profile
+    # pinned one) so the take is reproducible and we can hand it back via the
+    # X-Seed header for the "keep this seed" control. An explicit request seed
+    # or a profile's stored seed still wins — used_seed is only filled when it
+    # is still None here, never overwritten.
+    if used_seed is None:
+        used_seed = random.randint(0, 2**31 - 1)
+
+    # Expressive-TTS Spec 01: apply the user pronunciation dictionary + inline
+    # [[…]] one-off overrides to the text, here — AFTER `language` is fully
+    # resolved (a profile may fill it above) so per-language entries match the
+    # real render language, and BEFORE the text reaches either inference path
+    # (native OmniVoice or a pluggable backend) and the chunk splitter. This is
+    # the single point user text → normalized text → model, so the transform
+    # covers generate for every engine. Pure text substitution → identical on
+    # mac/Win/Linux. A disabled pref or empty dictionary is a pass-through, so
+    # plain text stays byte-identical (#G5 backward-compat).
+    from core import prefs as _prefs
+    _pron_env = os.environ.get("OMNIVOICE_PRONUNCIATION")
+    if _pron_env is not None:
+        # Env wins (power-user override); "0"/"false"/"no"/"off" disable it.
+        _pron_enabled = _pron_env.strip().lower() not in ("0", "false", "no", "off", "")
+    else:
+        _pron_enabled = bool(_prefs.get("pronunciation_enabled", True))
+    if pronounce and _pron_enabled:
+        from services.pronunciation import apply_pronunciation, load_entries_from_db
+        try:
+            _pron_rows = load_entries_from_db()
+        except Exception:  # noqa: BLE001 — table missing / DB locked → no-op
+            _pron_rows = []
+        text = apply_pronunciation(text, _pron_rows, language)
+    else:
+        # Even with the dictionary off, inline [[…]] overrides are an explicit,
+        # in-text authoring choice → always honored (and never left as literal
+        # double-bracket text the model would mispronounce).
+        from services.pronunciation import apply_inline_overrides
+        text = apply_inline_overrides(text)
 
     start_time = time.time()
     try:
         loop = asyncio.get_running_loop()
         if _backend is not None:
-            audio_tensor = await loop.run_in_executor(
-                _gpu_pool, _run_backend_inference,
-                _backend, text, language, ref_audio_path, ref_text, instruct,
-                duration, num_step, guidance_scale, speed, denoise,
-                postprocess_output, used_seed, effect_preset,
-                max_chunk_chars, crossfade_ms,
+            # Bounded + pool-reset on hang so a wedged generate can't starve the
+            # GPU pool and brick the backend ("can't reach backend", #730 class).
+            audio_tensor = await run_on_gpu_pool_guarded(
+                functools.partial(
+                    _run_backend_inference,
+                    _backend, text, language, ref_audio_path, ref_text, instruct,
+                    duration, num_step, guidance_scale, speed, denoise,
+                    postprocess_output, used_seed, effect_preset,
+                    max_chunk_chars, crossfade_ms,
+                ),
+                what="TTS generate",
             )
             # Read after generation: engines with lazy model loading report
             # their real rate only once weights are up.
             sample_rate = _backend.sample_rate
         else:
-            audio_tensor = await loop.run_in_executor(
-                _gpu_pool, _run_inference,
-                _model, text, language, ref_audio_path, ref_text, instruct, duration,
-                num_step, guidance_scale, speed, t_shift, denoise,
-                postprocess_output, layer_penalty_factor, position_temperature,
-                class_temperature, used_seed, effect_preset,
-                max_chunk_chars, crossfade_ms,
+            audio_tensor = await run_on_gpu_pool_guarded(
+                functools.partial(
+                    _run_inference,
+                    _model, text, language, ref_audio_path, ref_text, instruct, duration,
+                    num_step, guidance_scale, speed, t_shift, denoise,
+                    postprocess_output, layer_penalty_factor, position_temperature,
+                    class_temperature, used_seed, effect_preset,
+                    max_chunk_chars, crossfade_ms,
+                ),
+                what="TTS generate",
             )
             sample_rate = _model.sampling_rate
         # Invisible AudioSeal provenance watermark on the final audio. Embedding
@@ -493,13 +860,29 @@ async def generate_speech(
 
         audio_dur = round(audio_tensor.shape[-1] / sample_rate, 2)
 
-        with db_conn() as conn:
-            conn.execute(
-                "INSERT INTO generation_history (id, text, mode, language, instruct, profile_id, audio_path, duration_seconds, generation_time, seed, created_at) VALUES (?,?,?,?,?,?,?,?,?,?,?)",
-                (audio_id, text[:200], history_mode or ("clone" if ref_audio_path else "design"),
-                 language or "Auto", instruct or "", resolved_profile_id,
-                 audio_filename, audio_dur, gen_time, used_seed, time.time())
-            )
+        # #710: the clip is already generated and saved above. A history-write
+        # failure — e.g. "no such table: generation_history" on a DB that missed
+        # schema init — must NOT 500 the user's generation. Self-heal the schema
+        # once and retry; if it still fails, log and return the audio anyway.
+        def _write_history():
+            with db_conn() as conn:
+                conn.execute(
+                    "INSERT INTO generation_history (id, text, mode, language, instruct, profile_id, audio_path, duration_seconds, generation_time, seed, created_at) VALUES (?,?,?,?,?,?,?,?,?,?,?)",
+                    (audio_id, text[:200], history_mode or ("clone" if ref_audio_path else "design"),
+                     language or "Auto", instruct or "", resolved_profile_id,
+                     audio_filename, audio_dur, gen_time, used_seed, time.time())
+                )
+        try:
+            _write_history()
+        except sqlite3.OperationalError as e:
+            logger.warning("generation history write failed (%s); healing schema + retrying", e)
+            try:
+                ensure_schema()
+                _write_history()
+            except Exception as e2:
+                logger.warning("history write still failed after schema heal; returning audio anyway: %s", e2)
+        except Exception as e:
+            logger.warning("generation history write failed; returning audio anyway: %s", e)
         event_bus.emit("generation_history", {"action": "created", "id": audio_id})
 
         buffer = io.BytesIO()
@@ -535,6 +918,12 @@ async def generate_speech(
         )
     except HTTPException:
         raise
+    except GpuJobTimeoutError as e:
+        # A wedged GPU generate — the pool was already reset to restore capacity
+        # (#730 class). Report the actionable timeout instead of the misleading
+        # "can't reach backend" the frontend shows when the pool starves.
+        logger.error("Generate timed out: %s", e)
+        raise HTTPException(status_code=503, detail=str(e)) from e
     except ValueError as e:
         logger.error("Validation failed: %s", e)
         raise HTTPException(status_code=400, detail=str(e)) from e

backend/api/routers/glossary.py

@@ -189,15 +189,21 @@ def auto_extract(project_id: str, req: AutoExtractRequest):
     Writes them as `auto=1` rows. Existing terms with the same (source,target)
     are NOT duplicated. Returns the full current glossary after the pass.
     """
-    from services.translator import _llm_client, _llm_model, _llm_timeout  # reuse same client
+    # Resolved through the LLM Skills registry so auto-extract can be toggled
+    # or routed to its own provider (Settings → LLM Skills) independently of
+    # the translation pipeline. None == disabled or no provider configured.
+    from services import llm_skills
 
-    client = _llm_client()
-    if client is None:
+    handle = llm_skills.resolve_skill_client("glossary_extract")
+    if handle is None:
         raise HTTPException(
             status_code=503,
             detail=(
-                "Auto-extract needs an LLM. Set TRANSLATE_BASE_URL + TRANSLATE_API_KEY "
-                "(Ollama works locally: base_url=http://localhost:11434/v1) and try again."
+                "Auto-extract needs an LLM. Set one up in Settings → LLM Providers "
+                "(pick a provider, add its key, choose a model, Test) — or use local "
+                "Ollama / LM Studio for a fully offline setup — and make sure the "
+                "Glossary auto-extract skill is enabled in Settings → LLM Skills, "
+                "then try again."
             ),
         )
 
@@ -220,9 +226,9 @@ def auto_extract(project_id: str, req: AutoExtractRequest):
     )
 
     try:
-        res = client.chat.completions.create(
-            model=_llm_model(),
-            timeout=_llm_timeout(),
+        res = handle.client.chat.completions.create(
+            model=handle.model,
+            timeout=handle.timeout,
             messages=[
                 {"role": "system", "content": system},
                 {"role": "user", "content": user},
@@ -231,9 +237,18 @@ def auto_extract(project_id: str, req: AutoExtractRequest):
         body = (res.choices[0].message.content or "").strip()
     except Exception as e:
         logger.warning("auto-extract LLM call failed: %s", e)
+        # Scrub the provider error — some OpenAI-compatible providers echo the
+        # API key or a user_id in the body, which must not reach the UI verbatim.
+        from core.scrub import scrub_provider_error
+        from services import llm_providers
+        _p = llm_providers.active_provider()
+        _key = llm_providers.resolve_api_key(_p) if _p else None
         raise HTTPException(
             status_code=502,
-            detail=f"LLM didn't respond. Check Settings → Logs → Backend for the trace. Error: {e}",
+            detail=(
+                "LLM didn't respond. Check Settings → Logs → Backend for the trace. "
+                f"Error: {scrub_provider_error(e, _key)}"
+            ),
         )
 
     # Parse: SOURCE || TARGET || note (lines are allowed to be sloppy — we're forgiving).

backend/api/routers/openai_compat.py

@@ -22,7 +22,6 @@ from __future__ import annotations
 import io
 import logging
 import os
-import asyncio
 import tempfile
 from typing import Literal, Optional
 
@@ -30,7 +29,7 @@ from fastapi import APIRouter, File, Form, HTTPException, UploadFile
 from fastapi.responses import StreamingResponse
 from pydantic import BaseModel, Field
 
-from services.model_manager import _gpu_pool
+from services.model_manager import _gpu_pool, run_on_gpu_pool_guarded
 
 logger = logging.getLogger("omnivoice.openai_compat")
 
@@ -313,8 +312,10 @@ async def create_speech(req: SpeechRequest):
             kw["voice"] = voice
 
     try:
-        loop = asyncio.get_running_loop()
-        wav, sr = await loop.run_in_executor(_gpu_pool, _run_tts, backend, req.input, kw)
+        # Bounded + pool-reset on hang so a wedged TTS request can't starve the
+        # GPU pool and brick the backend (#730 class).
+        wav, sr = await run_on_gpu_pool_guarded(
+            lambda: _run_tts(backend, req.input, kw), what="OpenAI TTS generate")
     except Exception as e:
         logger.exception("OpenAI TTS failed: %s", e)
         raise HTTPException(status_code=500, detail=str(e))
@@ -384,12 +385,15 @@ async def create_transcription(
     try:
         backend = get_active_asr_backend()
 
-        # Run transcription in the thread pool to avoid blocking the event loop
-        loop = asyncio.get_running_loop()
+        # Run transcription in the thread pool to avoid blocking the event loop,
+        # bounded so a stuck/starved ASR returns a 504 with guidance instead of
+        # hanging the request forever (see run_transcribe_guarded).
+        from services.asr_backend import run_transcribe_guarded
         word_ts = response_format == "verbose_json"
-        result = await loop.run_in_executor(
+        result = await run_transcribe_guarded(
             _gpu_pool,
             lambda: backend.transcribe(tmp_path, word_timestamps=word_ts),
+            what="OpenAI",
         )
 
         # Extract the full text from segments
@@ -456,6 +460,12 @@ async def create_transcription(
         # Default: json
         return TranscriptionResponse(text=full_text)
 
+    except HTTPException:
+        raise
+    except TimeoutError as e:
+        # ASRTimeoutError (subclass): backend alive, ASR too heavy for compute.
+        logger.warning("OpenAI transcription timed out: %s", e)
+        raise HTTPException(status_code=504, detail=str(e))
     except Exception as e:
         logger.exception("OpenAI transcription failed: %s", e)
         raise HTTPException(status_code=500, detail=str(e))

backend/api/routers/personas.py

@@ -60,6 +60,11 @@ async def export_persona(
     profile = dict(row)
 
     tag_list = [t.strip() for t in tags.split(",") if t.strip()]
+    # #693: if OMNIVOICE_MODEL is set, record the *resolved* checkpoint in the
+    # exported bundle so a leaked engine id (e.g. "omnivoice") can't be baked in;
+    # keep "" when unset (the bundle's "engine unspecified" marker).
+    from services.model_manager import resolve_omnivoice_checkpoint
+    engine_id = resolve_omnivoice_checkpoint() if os.environ.get("OMNIVOICE_MODEL", "").strip() else ""
     try:
         loop = asyncio.get_running_loop()
         content = await loop.run_in_executor(
@@ -70,7 +75,7 @@ async def export_persona(
                 license_spdx=license_spdx,
                 tags=tag_list,
                 include_reference=include_reference,
-                engine_id=os.environ.get("OMNIVOICE_MODEL", ""),
+                engine_id=engine_id,
                 omnivoice_version=APP_VERSION,
             ),
         )

backend/api/routers/profiles.py

@@ -12,6 +12,7 @@ from core.db import db_conn
 from core.config import VOICES_DIR, OUTPUTS_DIR
 from core import event_bus
 from core.personalities import get_personalities
+from omnivoice.utils.voice_design import heal_design_instruct, sanitize_instruct
 
 router = APIRouter()
 
@@ -76,6 +77,13 @@ async def create_profile(
         # instruct — that's still a valid, saveable voice: synthesis falls back
         # to neutral instruct-only conditioning (see generation.py design path).
         # Don't gate save on a non-empty instruct.
+        #
+        # Defence-in-depth against the "[object Object]" / freeform-prose poison
+        # (#550 #571 #594 #596): never persist an instruct the engine validator
+        # would reject. Sanitize the submitted instruct and, if it's unusable,
+        # rebuild the tags from vd_states — so the row is always generation-safe
+        # regardless of which frontend build saved it.
+        instruct = heal_design_instruct(instruct, parsed)
 
     profile_id = str(uuid.uuid4())[:8]
 
@@ -167,6 +175,10 @@ def update_profile(profile_id: str, patch: ProfileUpdate):
             continue
         if col == "name" and not val.strip():
             raise HTTPException(status_code=400, detail="A voice profile needs a name.")
+        if col == "instruct":
+            # Never let an edit persist a validator-rejecting instruct (prose /
+            # "[object Object]"); keep only whitelist tags (#550 #571 #594 #596).
+            val = sanitize_instruct(val)
         fields.append(f"{col} = ?")
         params.append(val.strip() if col in ("name", "language") else val)
     if not fields:

backend/api/routers/pronunciation.py

@@ -0,0 +1,306 @@
+"""
+Pronunciation dictionary router — Expressive-TTS Spec 01 Phase 1.
+
+CRUD for the DB-backed, per-language pronunciation dictionary the
+``PronunciationPanel`` (Settings → Pronunciation) edits, plus a model-free
+``/pronunciation/test`` dry-run. Entries are applied as pure text substitution
+before synthesis (see ``services/pronunciation.apply_pronunciation`` and the
+generate path), so a saved entry actually changes the audio on every engine.
+
+Endpoints (loopback-only, like the dictation router):
+    GET    /pronunciation              → list every entry
+    POST   /pronunciation              → create one entry
+    PUT    /pronunciation/{entry_id}   → update an entry (partial)
+    DELETE /pronunciation/{entry_id}   → remove an entry
+    POST   /pronunciation/test         → dry-run substitution (no model)
+    GET    /pronunciation/export       → all entries as JSON (round-trips import)
+    POST   /pronunciation/import       → bulk add entries from JSON
+
+Scope: ``language='*'`` is global (applies to every request); a 2-letter code
+(``'en'``, ``'de'``) applies only when the request language matches.
+"""
+from __future__ import annotations
+
+import logging
+import re
+import time
+import uuid
+from typing import List, Optional
+
+from fastapi import APIRouter, Depends, HTTPException
+from pydantic import BaseModel
+
+from api.dependencies import require_loopback
+from core.db import db_conn
+from services.pronunciation import apply_pronunciation, entries_for_language
+
+logger = logging.getLogger("omnivoice.pronunciation")
+router = APIRouter()
+
+_VALID_TYPES = ("respelling", "ipa", "cmu")
+_ALL_LANG = "*"
+
+# IPA: the input is validated as a non-empty string of Unicode letters / IPA
+# extension codepoints + the usual suprasegmental marks; we reject ASCII control
+# and the bracket/pipe chars that would collide with the inline grammar. This is
+# a charset gate (catches obvious garbage early), not a full IPA grammar.
+_IPA_BAD = re.compile(r"[\[\]\|\x00-\x1f]")
+# CMU / ARPABET: space-separated phoneme tokens (letters + an optional 0-2 stress
+# digit), e.g. "N AH0 V AE1 D AH0". Reject anything else.
+_CMU_TOKEN = re.compile(r"^[A-Za-z]{1,3}[0-2]?$")
+
+
+def _validate_type_replacement(etype: str, replacement: str) -> None:
+    """Raise 400 on a phoneme replacement that's obviously malformed.
+
+    Respelling rows accept any text. IPA rows must be a non-empty string free of
+    bracket/pipe/control chars. CMU rows must be space-separated ARPABET tokens.
+    Validating on save (not at synth) means a model never sees garbage phonemes
+    (Spec 01 §R3 — never pass unvalidated phoneme strings to a model).
+    """
+    if etype == "respelling":
+        return
+    rep = (replacement or "").strip()
+    if not rep:
+        raise HTTPException(
+            status_code=400,
+            detail=f"A {etype.upper()} entry needs a phoneme string in 'replacement'.",
+        )
+    if etype == "ipa":
+        if _IPA_BAD.search(rep):
+            raise HTTPException(
+                status_code=400,
+                detail="That IPA string contains brackets, a pipe, or control characters. "
+                       "Use plain IPA symbols, e.g. ˈnɛvʌdə.",
+            )
+    elif etype == "cmu":
+        tokens = rep.split()
+        if not tokens or any(not _CMU_TOKEN.match(tok) for tok in tokens):
+            raise HTTPException(
+                status_code=400,
+                detail="That doesn't look like CMU/ARPABET. Use space-separated tokens with "
+                       "optional stress digits, e.g. N AH0 V AE1 D AH0.",
+            )
+
+
+def _norm_language(language: Optional[str]) -> str:
+    """Normalize a scope to '*' (global) or a lowercase 2-letter code."""
+    if not language:
+        return _ALL_LANG
+    s = str(language).strip()
+    if not s or s == _ALL_LANG or s.lower() == "auto":
+        return _ALL_LANG
+    return s.lower()[:2]
+
+
+def _row_to_dict(r) -> dict:
+    d = dict(r)
+    d["enabled"] = bool(d.get("enabled"))
+    # ``scope`` is the UI-facing alias for ``language`` ('*' shows as Global).
+    d["scope"] = d.get("language") or _ALL_LANG
+    return d
+
+
+# ── Schemas ──────────────────────────────────────────────────────────────────
+
+
+class PronEntry(BaseModel):
+    term: str
+    replacement: str = ""
+    type: str = "respelling"
+    language: str = _ALL_LANG
+    enabled: bool = True
+
+
+class PronEntryUpdate(BaseModel):
+    term: Optional[str] = None
+    replacement: Optional[str] = None
+    type: Optional[str] = None
+    language: Optional[str] = None
+    enabled: Optional[bool] = None
+
+
+class PronTestRequest(BaseModel):
+    text: str
+    language: Optional[str] = None
+
+
+class PronImportRequest(BaseModel):
+    entries: List[PronEntry]
+    replace: bool = False  # True → clear existing rows first
+
+
+# ── CRUD ─────────────────────────────────────────────────────────────────────
+
+
+@router.get("/pronunciation", dependencies=[Depends(require_loopback)])
+def list_entries():
+    with db_conn() as conn:
+        rows = conn.execute(
+            "SELECT id, term, replacement, type, language, enabled, created_at "
+            "FROM pronunciation_entries ORDER BY created_at ASC, id ASC"
+        ).fetchall()
+    return [_row_to_dict(r) for r in rows]
+
+
+@router.post("/pronunciation", dependencies=[Depends(require_loopback)])
+def create_entry(entry: PronEntry):
+    term = entry.term.strip()
+    if not term:
+        raise HTTPException(status_code=400, detail="A pronunciation entry needs a term.")
+    etype = (entry.type or "respelling").strip().lower()
+    if etype not in _VALID_TYPES:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Unknown entry type {entry.type!r}. Use one of: {', '.join(_VALID_TYPES)}.",
+        )
+    _validate_type_replacement(etype, entry.replacement)
+    eid = str(uuid.uuid4())[:12]
+    now = time.time()
+    lang = _norm_language(entry.language)
+    with db_conn() as conn:
+        conn.execute(
+            "INSERT INTO pronunciation_entries (id, term, replacement, type, language, enabled, created_at) "
+            "VALUES (?, ?, ?, ?, ?, ?, ?)",
+            (eid, term, entry.replacement, etype, lang, 1 if entry.enabled else 0, now),
+        )
+        row = conn.execute(
+            "SELECT id, term, replacement, type, language, enabled, created_at "
+            "FROM pronunciation_entries WHERE id = ?", (eid,)
+        ).fetchone()
+    return _row_to_dict(row)
+
+
+@router.put("/pronunciation/{entry_id}", dependencies=[Depends(require_loopback)])
+def update_entry(entry_id: str, patch: PronEntryUpdate):
+    with db_conn() as conn:
+        existing = conn.execute(
+            "SELECT id, term, replacement, type, language, enabled, created_at "
+            "FROM pronunciation_entries WHERE id = ?", (entry_id,)
+        ).fetchone()
+        if existing is None:
+            raise HTTPException(status_code=404, detail="No such pronunciation entry.")
+
+        # Resolve the post-update type + replacement so phoneme validation runs
+        # against the final state (e.g. switching type without changing text).
+        new_type = (patch.type.strip().lower() if patch.type is not None else existing["type"]) or "respelling"
+        if new_type not in _VALID_TYPES:
+            raise HTTPException(
+                status_code=400,
+                detail=f"Unknown entry type {patch.type!r}. Use one of: {', '.join(_VALID_TYPES)}.",
+            )
+        new_replacement = patch.replacement if patch.replacement is not None else existing["replacement"]
+        _validate_type_replacement(new_type, new_replacement)
+
+        fields, params = [], []
+        if patch.term is not None:
+            term = patch.term.strip()
+            if not term:
+                raise HTTPException(status_code=400, detail="A pronunciation entry needs a term.")
+            fields.append("term = ?"); params.append(term)
+        if patch.replacement is not None:
+            fields.append("replacement = ?"); params.append(patch.replacement)
+        if patch.type is not None:
+            fields.append("type = ?"); params.append(new_type)
+        if patch.language is not None:
+            fields.append("language = ?"); params.append(_norm_language(patch.language))
+        if patch.enabled is not None:
+            fields.append("enabled = ?"); params.append(1 if patch.enabled else 0)
+        if not fields:
+            raise HTTPException(
+                status_code=400,
+                detail="PUT body was empty. Include at least one field to change, or DELETE the entry.",
+            )
+        params.append(entry_id)
+        # nosec B608 - `fields` are fixed literal assignments ("term = ?", …) from
+        # the allowlist above; every user value is a bound `?` parameter, never
+        # interpolated. The f-string only joins constant column fragments.
+        conn.execute(
+            f"UPDATE pronunciation_entries SET {', '.join(fields)} WHERE id = ?",  # nosec B608
+            params,
+        )
+        row = conn.execute(
+            "SELECT id, term, replacement, type, language, enabled, created_at "
+            "FROM pronunciation_entries WHERE id = ?", (entry_id,)
+        ).fetchone()
+    return _row_to_dict(row)
+
+
+@router.delete("/pronunciation/{entry_id}", dependencies=[Depends(require_loopback)])
+def delete_entry(entry_id: str):
+    with db_conn() as conn:
+        cur = conn.execute("DELETE FROM pronunciation_entries WHERE id = ?", (entry_id,))
+    return {"deleted": cur.rowcount > 0}
+
+
+# ── Dry-run + import/export ───────────────────────────────────────────────────
+
+
+@router.post("/pronunciation/test", dependencies=[Depends(require_loopback)])
+def test_substitution(req: PronTestRequest):
+    """Show the post-substitution text for ``req.text`` — no model call.
+
+    Applies the same dictionary + inline ``[[…]]`` resolution the synth path
+    runs, so the user sees exactly what the engine will be handed.
+    """
+    with db_conn() as conn:
+        rows = conn.execute(
+            "SELECT id, term, replacement, type, language, enabled, created_at "
+            "FROM pronunciation_entries"
+        ).fetchall()
+    substituted = apply_pronunciation(req.text, rows, req.language)
+    applied = entries_for_language(rows, req.language)
+    return {
+        "input": req.text,
+        "substituted": substituted,
+        "changed": substituted != req.text,
+        "applied_terms": sorted(applied.keys(), key=len, reverse=True),
+    }
+
+
+@router.get("/pronunciation/export", dependencies=[Depends(require_loopback)])
+def export_entries():
+    """Every entry as a JSON-serializable list (round-trips ``/import``)."""
+    with db_conn() as conn:
+        rows = conn.execute(
+            "SELECT term, replacement, type, language, enabled "
+            "FROM pronunciation_entries ORDER BY created_at ASC, id ASC"
+        ).fetchall()
+    return {"entries": [
+        {"term": r["term"], "replacement": r["replacement"], "type": r["type"],
+         "language": r["language"], "enabled": bool(r["enabled"])}
+        for r in rows
+    ]}
+
+
+@router.post("/pronunciation/import", dependencies=[Depends(require_loopback)])
+def import_entries(req: PronImportRequest):
+    """Bulk-add entries. ``replace=true`` clears the table first.
+
+    Each entry is validated like ``POST /pronunciation``; one bad row fails the
+    whole import (400) so the table is never left half-applied.
+    """
+    now = time.time()
+    cleaned = []
+    for e in req.entries:
+        term = e.term.strip()
+        if not term:
+            continue  # silently skip blank terms — they're a no-op anyway
+        etype = (e.type or "respelling").strip().lower()
+        if etype not in _VALID_TYPES:
+            raise HTTPException(
+                status_code=400,
+                detail=f"Entry {term!r}: unknown type {e.type!r}.",
+            )
+        _validate_type_replacement(etype, e.replacement)
+        cleaned.append((str(uuid.uuid4())[:12], term, e.replacement, etype,
+                        _norm_language(e.language), 1 if e.enabled else 0, now))
+    with db_conn() as conn:
+        if req.replace:
+            conn.execute("DELETE FROM pronunciation_entries")
+        conn.executemany(
+            "INSERT INTO pronunciation_entries (id, term, replacement, type, language, enabled, created_at) "
+            "VALUES (?, ?, ?, ?, ?, ?, ?)",
+            cleaned,
+        )
+    return {"imported": len(cleaned), "replaced": req.replace}

backend/api/routers/settings.py

@@ -12,6 +12,7 @@ The state endpoint duplicates `/system/hf-token/state` (which lives on
 """
 from __future__ import annotations
 
+import asyncio
 import logging
 import os
 from dataclasses import asdict
@@ -134,12 +135,22 @@ class _RefinementBody(BaseModel):
 
 
 def _refinement_state():
-    from services.refinement import get_refinement_config
-    from services.llm_backend import get_active_llm_backend
+    from services.refinement import (
+        _skill_llm,
+        get_last_refine_status,
+        get_refinement_config,
+    )
 
     cfg = get_refinement_config()
-    # The UI shows whether refinement can actually run (needs an LLM).
-    cfg["llm_ready"] = get_active_llm_backend().id != "off"
+    # `llm_ready` only means "an endpoint is CONFIGURED" — a placeholder/dead
+    # endpoint still reads ready. It's resolved through the LLM Skills registry
+    # so a disabled dictation_refinement skill / per-skill provider override
+    # reads the same here as on the actual refine path. The honesty layer is
+    # `last_refine_status`: {ok, reason, at} from the most recent final, so the
+    # panel can flag a configured-but-failing LLM (the real safety is the hard
+    # refine timeout, which keeps a dead endpoint from ever stalling the final).
+    cfg["llm_ready"] = _skill_llm().id != "off"
+    cfg["last_refine_status"] = get_last_refine_status()
     return cfg
 
 
@@ -234,6 +245,237 @@ def set_llm_endpoint(body: _LLMEndpointBody):
     return _llm_endpoint_state()
 
 
+# ── Multi-provider LLM registry (Settings → LLM Providers) ────────────────
+# Keys persist ENCRYPTED via settings_store.set_secret (never .env, never
+# returned). base_url/model/account overrides are non-secret. Loopback-gated
+# by the router dep, so LAN peers can't read masks or write keys.
+
+class _LLMProviderBody(BaseModel):
+    api_key: str | None = Field(None, description="API key; '' clears it, None leaves unchanged")
+    base_url: str | None = None
+    model: str | None = None
+    account_id: str | None = Field(None, description="Cloudflare account id")
+    make_active: bool = False
+
+
+class _LLMActiveBody(BaseModel):
+    provider: str = Field(..., description="provider id to activate")
+
+
+@router.get("/llm-providers")
+def list_llm_providers():
+    """All providers with resolved base_url/model + whether a key is configured.
+
+    Never returns key material — only `has_key`/`key_from_env` booleans.
+    """
+    from services import llm_providers
+    return {
+        "active": llm_providers.active_provider_id(),
+        "providers": [llm_providers.describe(p) for p in llm_providers.all_providers()],
+    }
+
+
+@router.put("/llm-providers/{provider_id}")
+def save_llm_provider(provider_id: str, body: _LLMProviderBody):
+    """Save a provider's key (encrypted) + optional base_url/model/account.
+
+    A None field is left unchanged; an empty api_key clears the stored key.
+    """
+    from services import llm_providers
+    if llm_providers.get_provider(provider_id) is None:
+        raise HTTPException(status_code=404, detail=f"unknown provider {provider_id!r}")
+    if body.api_key is not None:
+        llm_providers.save_key(provider_id, body.api_key.strip())
+    llm_providers.save_overrides(
+        provider_id, base_url=body.base_url, model=body.model,
+        account_id=body.account_id,
+    )
+    if body.make_active:
+        llm_providers.set_active_provider(provider_id)
+    return list_llm_providers()
+
+
+@router.post("/llm-providers/active")
+def set_active_llm_provider(body: _LLMActiveBody):
+    from services import llm_providers
+    if llm_providers.get_provider(body.provider) is None:
+        raise HTTPException(status_code=404, detail=f"unknown provider {body.provider!r}")
+    llm_providers.set_active_provider(body.provider)
+    return list_llm_providers()
+
+
+def _scrub_llm_detail(e: Exception, api_key: str | None) -> str:
+    """Scrubbed, UI-safe failure text. scrub_text() covers env secrets and
+    home paths — but a STORE-persisted key isn't in the env, and some
+    providers echo the key in error bodies, so redact the exact resolved key
+    explicitly before the generic pass."""
+    from core.scrub import scrub_text
+    detail = f"{type(e).__name__}: {e}"
+    if api_key and api_key != "local" and len(api_key) >= 8:
+        detail = detail.replace(api_key, "•••")
+    return scrub_text(detail)
+
+
+def _classify_llm_error(e: Exception) -> str:
+    """Map a provider-call failure to an actionable kind the UI can localize.
+
+    Kinds: auth (bad/missing key), not_found (model or endpoint path),
+    rate_limit, network (DNS/conn/timeout), error (everything else).
+    Status codes win when the OpenAI SDK provides one; exception-family
+    names catch the non-HTTP failures (DNS, refused, TLS, timeout).
+    """
+    status = getattr(e, "status_code", None)
+    if status in (401, 403):
+        return "auth"
+    if status == 404:
+        return "not_found"
+    if status == 429:
+        return "rate_limit"
+    name = type(e).__name__
+    if name in ("APIConnectionError", "APITimeoutError", "ConnectError",
+                "ConnectTimeout", "TimeoutError"):
+        return "network"
+    if name == "AuthenticationError":
+        return "auth"
+    if name == "NotFoundError":
+        return "not_found"
+    if name == "RateLimitError":
+        return "rate_limit"
+    return "error"
+
+
+@router.post("/llm-providers/{provider_id}/test")
+def test_llm_provider(provider_id: str):
+    """One cheap round-trip against a provider to prove the key/URL work.
+
+    Temporarily activates the provider for the probe by resolving its config
+    directly (does not change the persisted active selection). Returns
+    latency_ms plus, on failure, a classified ``kind`` (config / auth /
+    not_found / rate_limit / network / error) so the UI shows an actionable,
+    localizable message instead of a raw exception string.
+    """
+    import time as _time
+
+    from services import llm_providers
+    p = llm_providers.get_provider(provider_id)
+    if p is None:
+        raise HTTPException(status_code=404, detail=f"unknown provider {provider_id!r}")
+    base_url = llm_providers.resolve_base_url(p)
+    api_key = llm_providers.resolve_api_key(p)
+    if not base_url:
+        return {"ok": False, "kind": "config", "detail": "No Base URL set for this provider."}
+    if not api_key:
+        return {"ok": False, "kind": "config", "detail": "No API key configured for this provider."}
+    t0 = _time.monotonic()
+    try:
+        from openai import OpenAI
+        # max_retries=0: this is an interactive probe with a live spinner — the
+        # SDK's default 2 automatic retries turn a 429/timeout into a ~34s hang.
+        # Surface the first failure immediately instead.
+        client = OpenAI(api_key=api_key, base_url=base_url, max_retries=0)
+        res = client.chat.completions.create(
+            model=llm_providers.resolve_model(p),
+            messages=[{"role": "user", "content": "Reply with the single word: ok"}],
+            timeout=20,
+        )
+        reply = (res.choices[0].message.content or "").strip()
+        return {
+            "ok": True,
+            "model": llm_providers.resolve_model(p),
+            "reply": reply[:80],
+            "latency_ms": int((_time.monotonic() - t0) * 1000),
+        }
+    except Exception as e:  # noqa: BLE001 — surface a clean, scrubbed error to the UI
+        return {
+            "ok": False,
+            "kind": _classify_llm_error(e),
+            "detail": _scrub_llm_detail(e, api_key),
+            "latency_ms": int((_time.monotonic() - t0) * 1000),
+        }
+
+
+@router.get("/llm-providers/{provider_id}/models")
+def list_llm_provider_models(provider_id: str):
+    """List model ids the provider's key can access (OpenAI-compat /models).
+
+    Powers the model-picker datalist in Settings → LLM Providers so users
+    don't have to guess model names. Read-only; failures return the same
+    classified shape as /test; capped so a huge catalog can't bloat the UI.
+    """
+    from services import llm_providers
+    p = llm_providers.get_provider(provider_id)
+    if p is None:
+        raise HTTPException(status_code=404, detail=f"unknown provider {provider_id!r}")
+    base_url = llm_providers.resolve_base_url(p)
+    api_key = llm_providers.resolve_api_key(p)
+    if not base_url or not api_key:
+        return {"ok": False, "kind": "config", "models": []}
+    try:
+        from openai import OpenAI
+        # max_retries=0: interactive probe — fail fast, don't burn ~34s on the
+        # SDK's default retry ladder when the key/URL is wrong (matches /test).
+        client = OpenAI(api_key=api_key, base_url=base_url, max_retries=0)
+        ids = sorted(m.id for m in client.models.list(timeout=10))
+        # Cap so a huge catalog can't bloat the datalist; flag the cap so the UI
+        # can say "first 200 shown" rather than implying it's the full list.
+        return {"ok": True, "models": ids[:200], "truncated": len(ids) > 200}
+    except Exception as e:  # noqa: BLE001
+        return {
+            "ok": False,
+            "kind": _classify_llm_error(e),
+            "detail": _scrub_llm_detail(e, api_key),
+            "models": [],
+        }
+
+
+# ── LLM Skills (Settings → LLM Skills) ─────────────────────────────────────
+# Per-feature enable/route control for every LLM consumption point. Each
+# skill can be toggled off (degrades exactly like "no LLM configured") or
+# routed to a specific provider (local Ollama/LM Studio vs a remote key)
+# instead of the one global active provider. Loopback-gated (router dep).
+
+
+class _LLMSkillBody(BaseModel):
+    enabled: bool | None = Field(None, description="None leaves the toggle unchanged")
+    provider_override: str | None = Field(
+        None,
+        description="provider id to route this skill to; '' or null clears "
+                    "it (skill follows the active provider). Omit to leave "
+                    "unchanged.",
+    )
+
+
+@router.get("/llm-skills")
+def list_llm_skills():
+    """Every LLM skill with its toggle, routing, and resolved ready status."""
+    from services import llm_skills
+    return {"skills": [llm_skills.describe(s.id) for s in llm_skills.all_skills()]}
+
+
+@router.put("/llm-skills/{skill_id}")
+def set_llm_skill(skill_id: str, body: _LLMSkillBody):
+    """Toggle a skill and/or set its provider routing.
+
+    Field semantics match the providers PUT: an omitted field is left
+    unchanged; ``provider_override: ""``/``null`` clears the override.
+    404 for an unknown skill or an unknown provider id.
+    """
+    from services import llm_skills
+    if llm_skills.get_skill(skill_id) is None:
+        raise HTTPException(status_code=404, detail=f"unknown LLM skill {skill_id!r}")
+    kwargs = {}
+    if body.enabled is not None:
+        kwargs["enabled"] = body.enabled
+    if "provider_override" in body.model_fields_set:
+        kwargs["provider_override"] = body.provider_override
+    try:
+        if kwargs:
+            llm_skills.configure_skill(skill_id, **kwargs)
+    except ValueError as e:
+        raise HTTPException(status_code=404, detail=str(e))
+    return list_llm_skills()
+
+
 # ── License acceptance (Phase 3 Plan 03-01 / TTS-05) ──────────────────────
 # Frontend ``SupertonicLicenseDialog`` flips the engine-license bit via this
 # endpoint. The handler is loopback-gated (router-level dep) and the
@@ -397,6 +639,41 @@ def set_models_dir(body: _ModelsDirBody):
     return {"configured": path, "effective": _effective_models_dir(), "restart_required": True}
 
 
+# ── Storage report (Settings → Storage) ────────────────────────────────────
+# Per-volume disk totals + du-style sizes for everything the app owns (HF
+# model cache, app data subtotals, engine venvs, temp files) with server-side
+# warnings. Heavy directory walks run in a worker thread with per-category
+# deadlines and a 5-minute in-process cache (services.storage_report), so the
+# endpoint stays cheap on repeat Settings visits. Loopback-gated via the
+# router-level dep like every sibling.
+
+
+@router.get("/storage")
+async def get_storage_report(refresh: bool = Query(False)):
+    """Disk + per-category storage usage for the Settings → Storage panel.
+
+    `refresh=1` bypasses the 5-minute cache and rescans. `min_free_gb`
+    reuses the setup wizard's constant so both surfaces warn at the same
+    threshold.
+    """
+    from api.routers.setup.wizard import MIN_FREE_GB
+    from core.config import DATA_DIR
+    from services import storage_report
+
+    try:
+        return await asyncio.to_thread(
+            storage_report.get_report,
+            data_dir=DATA_DIR,
+            hf_cache_dir=_effective_models_dir(),
+            app_venv=storage_report.default_app_venv(),
+            min_free_gb=MIN_FREE_GB,
+            refresh=refresh,
+        )
+    except Exception:
+        logger.exception("storage report failed")
+        raise HTTPException(status_code=500, detail="Failed to compute storage report")
+
+
 # ── HF mirror endpoint (parity program Wave 4.3 / §R4 c) ──────────────────
 # Restricted-network users (e.g. behind the Great Firewall) need to point
 # huggingface_hub at a mirror. HF reads HF_ENDPOINT at import time, so a
@@ -439,6 +716,11 @@ def set_hf_mirror(body: _HFMirrorBody):
     url = (body.url or "").strip().rstrip("/")
     if url and not url.startswith(("http://", "https://")):
         raise HTTPException(status_code=400, detail="Mirror URL must start with http(s)://")
+    # Compare against the currently-persisted value (normalised the same way) so
+    # a no-op save doesn't nag the user to restart. Only a real change to the
+    # persisted endpoint can require a restart.
+    previous = (user_env.get_user_env(_HF_ENDPOINT_ENV) or "").strip().rstrip("/")
+    changed = url != previous
     try:
         if url:
             user_env.set_user_env(_HF_ENDPOINT_ENV, url)
@@ -449,6 +731,53 @@ def set_hf_mirror(body: _HFMirrorBody):
     except Exception:
         logger.exception("set_hf_mirror failed")
         raise HTTPException(status_code=500, detail="Failed to persist mirror setting")
-    # HF endpoint is read at import time by huggingface_hub, so the override
-    # is only guaranteed once the backend restarts.
-    return {"configured": url, "restart_required": True, "presets": _HF_MIRROR_PRESETS}
+    # Model Store downloads pick up the new mirror immediately — the download
+    # path resolves the endpoint per-call and we updated os.environ above. Only
+    # transformers-side model *loads* (which read HF_ENDPOINT at import time)
+    # need a restart, so restart_required is True ONLY when the value actually
+    # changed — a no-op re-save never asks for a restart.
+    return {"configured": url, "restart_required": changed, "presets": _HF_MIRROR_PRESETS}
+
+
+# ── Updates panel: shipped changelog + pre-migration DB backup state ────────
+# (feat/safe-updates). Both are read-only, local-first surfaces for
+# Settings → Updates: the "What's new" viewer reads the CHANGELOG.md that
+# ships with the app, and the backup line shows the newest pre-migration
+# snapshot written by core.db_backup before `alembic upgrade head` runs.
+
+
+@router.get("/changelog")
+def get_changelog(limit_versions: int = Query(5, ge=1, le=50)):
+    """Structured release notes from the shipped CHANGELOG.md (newest first).
+
+    Bullets are raw markdown-lite (bold leads, `code`, (#NNN) refs) — the
+    frontend renders them safely without HTML. `available: false` when this
+    install has no changelog (never an error: the viewer just hides)."""
+    from core import changelog
+
+    path = changelog.changelog_path()
+    if not path:
+        return {"available": False, "releases": []}
+    try:
+        with open(path, encoding="utf-8") as fh:
+            releases = changelog.parse_changelog(fh.read(), limit_versions)
+    except Exception:
+        logger.exception("changelog parse failed")
+        return {"available": False, "releases": []}
+    return {"available": bool(releases), "releases": releases}
+
+
+@router.get("/db-backup")
+def get_db_backup_state():
+    """Newest pre-migration database backup (or none yet). Feeds the
+    "your data is backed up before every update" line in Settings → Updates."""
+    from core import db_backup
+    from core.config import DB_PATH
+
+    latest = db_backup.latest_backup(DB_PATH)
+    return {
+        "available": latest is not None,
+        "latest": latest,
+        "count": len(db_backup.list_backups(DB_PATH)),
+        "keep": db_backup.KEEP_BACKUPS,
+    }

backend/api/routers/setup/download.py

@@ -21,7 +21,18 @@ from pydantic import BaseModel
 from core import prefs
 from utils import hf_progress
 from utils import download_aggregator
-from .models import KNOWN_MODELS, invalidate_cache
+# Weight-floor scan (MM2-07 / #352) lives in ``models.py`` — the lowest module in
+# the setup import graph — so install-time validation here, the first-run
+# install-state detector (#622), and load-time repair share one set of floors and
+# can't drift apart. ``_MIN_WEIGHT_BYTES``/``_WEIGHT_FLOORS`` re-exported for tests.
+from .models import (  # noqa: F401
+    KNOWN_MODELS,
+    invalidate_cache,
+    snapshot_has_weights,
+    disk_space_error,
+    _MIN_WEIGHT_BYTES,
+    _WEIGHT_FLOORS,
+)
 
 logger = logging.getLogger("omnivoice.setup.download")
 router = APIRouter()
@@ -120,11 +131,15 @@ def compute_plan(plan_files) -> dict:
 
 
 def _segmented_enabled() -> bool:
-    """Opt-in IDM-style accelerator (FDL-09), default OFF. Most useful when Xet
-    is inactive (the app's default): the legacy-LFS path is single-stream, so
-    this restores parallel speed AND gives real live byte progress."""
+    """IDM-style multi-connection accelerator (FDL-09), default **ON**. The app
+    forces the legacy-LFS path (HF_HUB_DISABLE_XET=1) for clear progress, but that
+    path is single-stream and slow — this restores parallel byte-range speed AND
+    real live progress, and falls back to snapshot_download on any error so it
+    can never compromise a correct install. Default-on so first-run downloads are
+    fast out of the box (pairs with an HF token for higher rate limits); set
+    OMNIVOICE_SEGMENTED_DOWNLOAD=0 to force the single-stream path."""
     return _truthy(prefs.resolve(
-        "segmented_downloader", env="OMNIVOICE_SEGMENTED_DOWNLOAD", default=False,
+        "segmented_downloader", env="OMNIVOICE_SEGMENTED_DOWNLOAD", default=True,
     ))
 
 
@@ -223,51 +238,26 @@ def _safe_put(queue: asyncio.Queue, event) -> None:
 # model.safetensors" (#352). 5 MB clears every weight format we ship
 # (safetensors/bin shards, onnx, pt, gguf) without false-positiving on
 # config-only aux repos.
-_MIN_WEIGHT_BYTES = 5 * 1024 * 1024
-
-# Per-role weight-file floors (MM2-07). A valid model has at least one
-# recognized weight file at or above its extension's floor. ONNX graphs are
-# legitimately small (a complete model can be well under 5 MB), so a single
-# 5 MB rule false-positives on them as "truncated" (#352 over-trigger); give
-# .onnx a lower floor while still rejecting a 0/KB partial. Tensor formats keep
-# the original 5 MB floor.
-_WEIGHT_FLOORS = {
-    ".safetensors": _MIN_WEIGHT_BYTES,
-    ".bin": _MIN_WEIGHT_BYTES,
-    ".ckpt": _MIN_WEIGHT_BYTES,
-    ".pt": _MIN_WEIGHT_BYTES,
-    ".pth": _MIN_WEIGHT_BYTES,
-    ".gguf": _MIN_WEIGHT_BYTES,
-    ".onnx": 64 * 1024,   # a real ONNX graph is ≥ tens of KB; a truncated one is bytes
-}
-
-
 def _validate_snapshot_has_weights(repo_id: str, snapshot_path: str) -> None:
     """Raise OSError when a finished snapshot has no plausible weight file —
     surfaces the truncated-download class (#352) at install time, where the
     retry loop and the UI's re-download path can deal with it, instead of at
     first synthesis with an opaque transformers error.
 
-    A snapshot is valid if it contains a recognized weight file meeting its
-    per-extension floor (MM2-07) OR any file ≥ the global 5 MB floor (the
-    original lenient catch — kept so this is never stricter than before)."""
+    Delegates the weight check to ``models.snapshot_has_weights`` (single source of
+    the floors); only the install-time error message lives here."""
+    if snapshot_has_weights(snapshot_path):
+        return
+    biggest = 0
     try:
-        biggest = 0
         for root, _dirs, files in os.walk(snapshot_path, followlinks=True):
             for f in files:
                 try:
-                    size = os.path.getsize(os.path.join(root, f))
+                    biggest = max(biggest, os.path.getsize(os.path.join(root, f)))
                 except OSError:
                     continue
-                biggest = max(biggest, size)
-                ext = os.path.splitext(f)[1].lower()
-                floor = _WEIGHT_FLOORS.get(ext)
-                if floor is not None and size >= floor:
-                    return  # a recognized weight file of plausible size
-                if size >= _MIN_WEIGHT_BYTES:
-                    return  # original lenient catch (non-standard weight names)
     except OSError:
-        return  # can't inspect — don't block the install on the checker itself
+        pass
     raise OSError(
         f"{repo_id}: download finished but no model weights were found in the "
         "snapshot (largest file "
@@ -415,6 +405,26 @@ async def install_model(req: InstallModelRequest):
             try:
                 _plan = snapshot_download(**_preflight_kwargs)
                 _summary = compute_plan(_plan)
+                # Disk-space guard (before a single byte flows): the preflight
+                # gives an exact "to download" size, so reject an install that
+                # would overrun the cache volume — with the numbers named —
+                # instead of failing mid-download with a cryptic OSError. No-op
+                # when it fits or the size is unknown. Same on every platform.
+                _disk_err = disk_space_error(_summary["to_download_bytes"])
+                if _disk_err:
+                    logger.info("model install %s: rejected — %s", req.repo_id, _disk_err)
+                    _resolving.set()  # stop the heartbeat thread before we bail
+                    hf_progress.emit({
+                        "repo_id": req.repo_id,
+                        "filename": req.repo_id,
+                        "downloaded": 0, "total": 0, "pct": 0.0,
+                        "phase": "install_error",
+                        "error": _disk_err,
+                    })
+                    # A disk-full is not a transient network failure — don't set
+                    # a cooldown (freeing space, not waiting, is the fix). The
+                    # outer finally still cleans up the aggregator + context.
+                    return
                 download_aggregator.start(
                     req.repo_id,
                     total_bytes=_summary["to_download_bytes"],
@@ -449,10 +459,11 @@ async def install_model(req: InstallModelRequest):
                     raise _InstallCancelled()
                 _attempt += 1
                 try:
-                    # Opt-in segmented accelerator (FDL-09): parallel byte-range
-                    # fetch with real live progress, for the legacy-LFS path.
-                    # Any failure falls through to snapshot_download — the
-                    # accelerator can never compromise a correct install.
+                    # Segmented accelerator (FDL-09, default ON): parallel
+                    # byte-range fetch with real live progress, for the
+                    # legacy-LFS path. Any failure falls through to
+                    # snapshot_download — the accelerator can never compromise a
+                    # correct install.
                     _snapshot_path = None
                     if _attempt == 1 and _segmented_enabled() and not _xet_active():
                         try:
@@ -517,12 +528,16 @@ async def install_model(req: InstallModelRequest):
             logger.info("model install failed for %s: %s", req.repo_id, e)
             import time as _time_fail
             _install_cooldowns[req.repo_id] = _time_fail.time()
+            # #874: when the install failed because the configured HF mirror is
+            # unreachable, name the mirror + the setting instead of leaking the
+            # raw connectivity error. No-op for every other failure.
+            from core.failure import append_hf_mirror_hint
             hf_progress.emit({
                 "repo_id": req.repo_id,
                 "filename": req.repo_id,
                 "downloaded": 0, "total": 0, "pct": 0.0,
                 "phase": "install_error",
-                "error": str(e),
+                "error": append_hf_mirror_hint(str(e)),
             })
         finally:
             _cancelled.discard(req.repo_id)

backend/api/routers/setup/models.py

@@ -123,6 +123,66 @@ def hf_cache_dir() -> str:
     )
 
 
+# ── Disk-space guard (shared, single-sourced) ──────────────────────────────
+# MIN_FREE_GB is the headroom we insist on keeping free on the model-cache
+# volume — the wizard's absolute pre-install floor AND the extra buffer the
+# per-install check demands on top of the download itself, so an "Install all"
+# can't fill the disk to the brim (setup/download.py). Lives here — the lowest
+# module in the setup import graph — so the wizard, the /models header, and the
+# install endpoint can't drift apart (mirrors the weight-floor single-sourcing).
+_GIB = 1024 ** 3
+MIN_FREE_GB = 10
+
+
+def disk_free_bytes(path: "str | None" = None) -> int:
+    """Free bytes on the volume backing *path* (defaults to the HF cache).
+
+    Walks up to the nearest existing ancestor so a not-yet-created cache dir
+    still probes the correct mount point. ``shutil.disk_usage`` is cross-platform
+    (macOS/Windows/Linux) so this behaves identically everywhere. Never raises.
+    """
+    import shutil
+    try:
+        p = Path(path or hf_cache_dir()).resolve()
+        while not p.exists():
+            parent = p.parent
+            if parent == p:  # reached the volume root
+                break
+            p = parent
+        return int(shutil.disk_usage(str(p)).free)
+    except Exception:
+        return 0
+
+
+def disk_space_error(to_download_bytes: "int | None", *, cache_dir: "str | None" = None) -> "str | None":
+    """Actionable message when *to_download_bytes* (+ MIN_FREE_GB headroom) won't
+    fit on the cache volume; ``None`` when it fits, the size is unknown, or the
+    volume can't be probed (never block on missing information).
+
+    Names the three numbers a user needs to act — needs X, headroom Y, have Z —
+    so "Install all" can't silently overrun the disk (issue: no pre-install disk
+    check). Platform-agnostic; applied identically on macOS/Windows/Linux.
+    """
+    if not to_download_bytes or to_download_bytes <= 0:
+        return None  # unknown plan (older/gated repo, mirror without dry-run) → don't block
+    cache = cache_dir or hf_cache_dir()
+    free = disk_free_bytes(cache)
+    if free <= 0:
+        return None  # couldn't probe the volume → don't block on missing info
+    required = int(to_download_bytes) + MIN_FREE_GB * _GIB
+    if free >= required:
+        return None
+
+    def _gb(n: int) -> str:
+        return f"{n / _GIB:.1f} GB"
+
+    return (
+        f"Not enough disk space to install: this download needs {_gb(int(to_download_bytes))} "
+        f"plus {MIN_FREE_GB} GB free headroom ({_gb(required)} total), but only {_gb(free)} "
+        f"is free at {cache}. Free up space (or move the model cache to a bigger volume) and retry."
+    )
+
+
 def _repo_dir_name(repo_id: str) -> str:
     """HF cache dir name for a repo: 'k2-fsa/OmniVoice' → 'models--k2-fsa--OmniVoice'."""
     return "models--" + repo_id.replace("/", "--")
@@ -146,6 +206,94 @@ def _hub_cache_roots() -> list[str]:
     return roots
 
 
+# ── Weight-presence (truncated-cache) detection ─────────────────────────────
+# A cache that downloaded config/tokenizer files but not the weight shard still
+# occupies bytes on disk, so a size-only "installed" check (#352/#581/#606) reads
+# it as installed and the first-run wizard hides the re-download button, stranding
+# the user (#622). These helpers tell a *complete* snapshot from a truncated one by
+# checking for a plausible weight file — the same class `download.py` guards at
+# install time and `model_manager.py` repairs at load time. Shared here (the lowest
+# module in the setup import graph; `download.py` imports from this module) so the
+# floors live in exactly one place and can't drift between the three call sites.
+
+_MIN_WEIGHT_BYTES = 5 * 1024 * 1024  # tensor formats: a real shard is ≥ a few MB
+
+# Per-extension floors. ONNX graphs are legitimately small (a complete model can be
+# well under 5 MB), so they get a lower floor that still rejects a bytes-only partial.
+_WEIGHT_FLOORS = {
+    ".safetensors": _MIN_WEIGHT_BYTES,
+    ".bin": _MIN_WEIGHT_BYTES,
+    ".ckpt": _MIN_WEIGHT_BYTES,
+    ".pt": _MIN_WEIGHT_BYTES,
+    ".pth": _MIN_WEIGHT_BYTES,
+    ".gguf": _MIN_WEIGHT_BYTES,
+    ".onnx": 64 * 1024,
+}
+
+
+def snapshot_has_weights(snapshot_path: str) -> bool:
+    """True when a finished snapshot dir holds a plausible weight file.
+
+    A snapshot is complete if it contains a recognized weight file meeting its
+    per-extension floor OR any file ≥ the global 5 MB floor (the lenient catch for
+    non-standard weight names). Returns True when the path can't be inspected — an
+    un-walkable dir must never be reported as truncated, only a confirmed weight-less
+    one. `getsize` follows symlinks, so HF's snapshot→blob links resolve correctly;
+    a broken link (missing blob) raises OSError and is skipped, i.e. counts as absent.
+    """
+    try:
+        for root, _dirs, files in os.walk(snapshot_path, followlinks=True):
+            for f in files:
+                try:
+                    size = os.path.getsize(os.path.join(root, f))
+                except OSError:
+                    continue
+                ext = os.path.splitext(f)[1].lower()
+                floor = _WEIGHT_FLOORS.get(ext)
+                if floor is not None and size >= floor:
+                    return True
+                if size >= _MIN_WEIGHT_BYTES:
+                    return True
+    except OSError:
+        return True  # can't inspect — don't mislabel as truncated
+    return False
+
+
+def _snapshot_dirs(repo_id: str) -> list[str]:
+    """Existing snapshot revision dirs for a repo across the candidate cache roots."""
+    name = _repo_dir_name(repo_id)
+    dirs: list[str] = []
+    for root in _hub_cache_roots():
+        snaps = os.path.join(root, name, "snapshots")
+        try:
+            for rev in os.listdir(snaps):
+                rev_dir = os.path.join(snaps, rev)
+                if os.path.isdir(rev_dir):
+                    dirs.append(rev_dir)
+        except OSError:
+            continue
+    return dirs
+
+
+def cache_is_complete(model: dict) -> bool:
+    """True when this model's on-disk cache is usable (not a truncated download).
+
+    Config-only repos (``config_only: true`` in models.yaml — e.g. pyannote's
+    diarisation pipeline, whose real weights live in referenced sub-repos) carry no
+    weight file of their own, so the weight check would false-positive them as
+    incomplete (#622 caveat). They're exempt: cache presence alone means complete.
+    A weight-bearing repo is complete only if at least one of its snapshots has
+    weights; if no snapshot dir is found on disk we can't prove truncation, so we
+    don't downgrade (the size-based caller already decided it's cached).
+    """
+    if model.get("config_only"):
+        return True
+    dirs = _snapshot_dirs(model["repo_id"])
+    if not dirs:
+        return True
+    return any(snapshot_has_weights(d) for d in dirs)
+
+
 def _is_cached_on_disk(repo_id: str) -> bool:
     """Direct-filesystem fallback for is_cached when scan_cache_dir is unavailable.
 
@@ -286,9 +434,15 @@ def list_models():
     out = []
     for m in KNOWN_MODELS:
         cached = cached_by_repo.get(m["repo_id"])
+        on_disk = cached is not None and cached["size_on_disk"] > 0
+        # A size-positive cache can still be a truncated download (config landed,
+        # weight shard didn't). Treat that as not-installed + incomplete so the
+        # wizard re-offers the download instead of stranding the user (#622).
+        incomplete = on_disk and not cache_is_complete(m)
         out.append({
             **m,
-            "installed": cached is not None and cached["size_on_disk"] > 0,
+            "installed": on_disk and not incomplete,
+            "incomplete": incomplete,
             "size_on_disk_bytes": cached["size_on_disk"] if cached else 0,
             "nb_files": cached["nb_files"] if cached else 0,
             "supported": _model_supported(m),
@@ -297,6 +451,10 @@ def list_models():
         "models": out,
         "total_installed_bytes": sum(m["size_on_disk_bytes"] for m in out),
         "hf_cache_dir": hf_cache_dir(),
+        # Free space on the cache volume, so the Model Store header can warn
+        # BEFORE an "Install all" overruns the disk (pairs with the per-install
+        # disk_space_error guard in setup/download.py).
+        "disk_free_gb": round(disk_free_bytes() / _GIB, 1),
         "platform_tags": _current_platform_tags(),
     }
     _set_cache("models", response)
@@ -383,6 +541,9 @@ def recommendations():
     entries = []
     for rid in recommended_ids:
         meta = known_by_id.get(rid, {})
+        # Mirror /models: a truncated cache (weights missing) is not installed, so
+        # the wizard counts it toward the remaining download instead of "all set".
+        installed = rid in cached_ids and cache_is_complete(meta or {"repo_id": rid})
         entries.append({
             "repo_id": rid,
             "label": meta.get("label", rid),
@@ -390,7 +551,7 @@ def recommendations():
             "size_gb": meta.get("size_gb", 0),
             "required": bool(meta.get("required", False)),
             "note": meta.get("note"),
-            "installed": rid in cached_ids,
+            "installed": installed,
         })
 
     to_download_gb = sum(e["size_gb"] for e in entries if not e["installed"])

backend/api/routers/setup/wizard.py

@@ -18,33 +18,20 @@ import sys
 from fastapi import APIRouter
 
 from api.schemas import SetupStatusResponse, PreflightResponse
-from .models import REQUIRED_MODELS, hf_cache_dir, is_cached
+# MIN_FREE_GB + disk_free_bytes are single-sourced in ``.models`` (the lowest
+# module in the setup import graph) so the wizard gate, the /models header, and
+# the per-install disk guard can't drift apart.
+from .models import REQUIRED_MODELS, hf_cache_dir, is_cached, MIN_FREE_GB, disk_free_bytes
 
 logger = logging.getLogger("omnivoice.setup.wizard")
 router = APIRouter()
 
-MIN_FREE_GB = 10
-
 
 def _disk_free_gb(path: str) -> float:
-    """Return free GB on the volume containing *path*.
-
-    If *path* doesn't exist yet (e.g. after a fresh wipe), walk up to the
-    nearest existing ancestor so ``shutil.disk_usage`` can still probe the
-    correct mount point.
-    """
-    try:
-        from pathlib import Path
-        p = Path(path).resolve()
-        # Walk up until we find a directory that exists
-        while not p.exists():
-            parent = p.parent
-            if parent == p:  # root
-                break
-            p = parent
-        return _shutil.disk_usage(str(p)).free / (1024 ** 3)
-    except Exception:
-        return 0.0
+    """Free GB on the volume containing *path* (thin GB wrapper over the shared
+    ``models.disk_free_bytes``, which walks up to the nearest existing ancestor
+    for a not-yet-created path)."""
+    return disk_free_bytes(path) / (1024 ** 3)
 
 
 # ── Setup Status ───────────────────────────────────────────────────────────

backend/api/routers/system.py

@@ -18,7 +18,7 @@ import shutil
 
 from core.config import OUTPUTS_DIR, DATA_DIR, CRASH_LOG_PATH, LOG_PATH, IDLE_TIMEOUT_SECONDS
 from core.version import APP_VERSION
-from services.model_manager import get_model_status, get_best_device
+from services.model_manager import get_model_status, get_best_device, resolve_omnivoice_checkpoint
 from services.ffmpeg_utils import find_ffmpeg, run_ffmpeg
 
 # Router-level loopback gate. Every route mounted on `router` (GET + POST,
@@ -208,7 +208,7 @@ def system_info():
             "outputs_dir": OUTPUTS_DIR,
             "crash_log_path": CRASH_LOG_PATH,
             "idle_timeout_seconds": IDLE_TIMEOUT_SECONDS,
-            "model_checkpoint": os.environ.get("OMNIVOICE_MODEL", "k2-fsa/OmniVoice"),
+            "model_checkpoint": resolve_omnivoice_checkpoint(),  # #693: show the effective checkpoint, not a leaked raw value
             "asr_model": os.environ.get("ASR_MODEL", "Systran/faster-whisper-large-v3"),
             "translate_provider": os.environ.get("TRANSLATE_PROVIDER", "google"),
             "has_hf_token": _has_hf_token(),

backend/api/routers/tts_stream.py

@@ -182,8 +182,8 @@ async def ws_tts(websocket: WebSocket):
                     sentences = [text]
 
                 # Run generation in the GPU pool
-                from services.model_manager import _gpu_pool
-                loop = asyncio.get_running_loop()
+                import functools
+                from services.model_manager import run_on_gpu_pool_guarded
 
                 def _generate(sentence_text):
                     from services.audio_dsp import apply_mastering, normalize_audio
@@ -204,8 +204,13 @@ async def ws_tts(websocket: WebSocket):
                 started = False
 
                 for sentence in sentences:
-                    wav_tensor, sr = await loop.run_in_executor(
-                        _gpu_pool, _generate, sentence
+                    # Bounded + pool-reset on hang so a wedged generate can't
+                    # starve the GPU pool and brick the backend (#730 class). On
+                    # timeout GpuJobTimeoutError propagates to the handler below,
+                    # which sends an actionable error frame.
+                    wav_tensor, sr = await run_on_gpu_pool_guarded(
+                        functools.partial(_generate, sentence),
+                        what="TTS generate",
                     )
 
                     if not started:

backend/config/models.yaml

@@ -14,6 +14,10 @@
 #   required   (optional) — true if the app needs this model to function
 #   platforms  (optional) — restrict to specific OS+arch tags (e.g. darwin-arm64, cuda)
 #   note       (optional) — shown in the UI as a tooltip/footnote
+#   config_only (optional) — true for pipeline repos that ship no weight file of
+#                            their own (weights live in referenced sub-repos). Such
+#                            a cache is legitimately tiny, so the truncated-download
+#                            (weights-missing) detector must NOT flag it incomplete.
 # ─────────────────────────────────────────────────────────────────────────
 
 models:
@@ -116,12 +120,83 @@ models:
     size_gb: 0.05
     note: "Smallest/fastest Moonshine, sub-200ms latency. Lower accuracy than base. Requires moonshine-onnx."
 
+  # ── sherpa-onnx live dictation (ONNX, CPU, streaming + offline) ────────
+  # Live faster-than-real-time dictation via the k2-fsa/sherpa-onnx runtime.
+  # `engine: sherpa-onnx`, `dictation_id` (backend model id), and `tag`
+  # (offline | streaming) are extra fields the model-store list passes through
+  # so the dictation UI can filter/group these (role=ASR, engine=sherpa-onnx).
+  # Requires `uv add sherpa-onnx` (CPU wheels, all platforms).
+
+  - repo_id: "csukuangfj/sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8"
+    label: "Parakeet TDT v3 (sherpa-onnx — dictation, 25 EU langs)"
+    role: ASR
+    size_gb: 0.18
+    engine: sherpa-onnx
+    dictation_id: sherpa-parakeet-tdt-v3
+    tag: offline
+    note: "Recommended live-dictation default. CPU, int8 ONNX. Requires sherpa-onnx."
+
+  - repo_id: "csukuangfj/sherpa-onnx-nemo-parakeet-tdt-0.6b-v2-int8"
+    label: "Parakeet TDT v2 (sherpa-onnx — dictation, English)"
+    role: ASR
+    size_gb: 0.17
+    engine: sherpa-onnx
+    dictation_id: sherpa-parakeet-tdt-v2
+    tag: offline
+    note: "English live dictation. CPU, int8 ONNX. Requires sherpa-onnx."
+
+  - repo_id: "csukuangfj/sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20"
+    label: "Zipformer Bilingual (sherpa-onnx — streaming, zh+en)"
+    role: ASR
+    size_gb: 0.13
+    engine: sherpa-onnx
+    dictation_id: sherpa-zipformer-bilingual-zh-en
+    tag: streaming
+    note: "True streaming partials as you speak (zh+en). CPU. Requires sherpa-onnx."
+
+  - repo_id: "csukuangfj/sherpa-onnx-streaming-paraformer-bilingual-zh-en"
+    label: "Paraformer Bilingual (sherpa-onnx — streaming, zh+en)"
+    role: ASR
+    size_gb: 0.115
+    engine: sherpa-onnx
+    dictation_id: sherpa-paraformer-bilingual-zh-en
+    tag: streaming
+    note: "True streaming partials (zh+en). CPU. Requires sherpa-onnx."
+
+  - repo_id: "csukuangfj/sherpa-onnx-streaming-zipformer-en-20M-2023-02-17"
+    label: "Zipformer Streaming EN 20M (sherpa-onnx — streaming, English)"
+    role: ASR
+    size_gb: 0.128
+    engine: sherpa-onnx
+    dictation_id: sherpa-zipformer-en-20m
+    tag: streaming
+    note: "Tiny English streaming model, very low latency. CPU. Requires sherpa-onnx."
+
+  - repo_id: "csukuangfj/sherpa-onnx-streaming-zipformer-zh-14M-2023-02-23"
+    label: "Zipformer Streaming ZH 14M (sherpa-onnx — streaming, Chinese)"
+    role: ASR
+    size_gb: 0.074
+    engine: sherpa-onnx
+    dictation_id: sherpa-zipformer-zh-14m
+    tag: streaming
+    note: "Tiny Chinese streaming model, very low latency. CPU. Requires sherpa-onnx."
+
+  - repo_id: "csukuangfj/sherpa-onnx-whisper-tiny"
+    label: "Whisper Tiny (sherpa-onnx — dictation, 90+ langs)"
+    role: ASR
+    size_gb: 0.116
+    engine: sherpa-onnx
+    dictation_id: sherpa-whisper-tiny
+    tag: offline
+    note: "Multilingual offline dictation (auto-detect). CPU, int8 ONNX. Requires sherpa-onnx."
+
   # ── Diarisation ───────────────────────────────────────────────────────
 
   - repo_id: "pyannote/speaker-diarization-3.1"
     label: "pyannote speaker diarisation (multi-speaker videos)"
     role: Diarisation
     size_gb: 0.8
+    config_only: true  # pipeline repo; real weights live in referenced sub-repos
     note: "Needs an HF_TOKEN with license accepted."
 
   # ── Optional TTS ──────────────────────────────────────────────────────

backend/core/changelog.py

@@ -0,0 +1,138 @@
+"""Parse the shipped CHANGELOG.md into structured release notes.
+
+Feeds ``GET /api/settings/changelog`` — the Settings → Updates "What's new"
+viewer. Local-first by design: the changelog ships with the app (repo root in
+dev; copied into the packaged project dir by the Tauri bootstrap alongside
+README.md), so the viewer works fully offline.
+
+The house format (see CHANGELOG.md / the release-notes hard rule):
+
+    ## [X.Y.Z] — DATE
+    one-paragraph headline (the "intro")
+    ### Added / Fixed / Changed / ...
+    - **Bold one-line lead.** 1-3 lines of plain-English why. (#NNN)
+
+Bullets may be a single long line (recent sections) *or* hard-wrapped across
+indented continuation lines (older sections) — the parser normalizes both to
+one logical line per bullet. Bullets stay raw markdown-lite; the frontend's
+safe renderer handles **bold** / `code` / (#NNN) refs.
+"""
+from __future__ import annotations
+
+import os
+import re
+
+#: ``## [0.3.9] — 2026-07-02`` (em/en dash or hyphen; date optional).
+_RELEASE_RE = re.compile(r"^##\s+\[(?P<version>[^\]]+)\]\s*(?:[—–-]\s*(?P<date>.+?))?\s*$")
+_SECTION_RE = re.compile(r"^###\s+(?P<title>.+?)\s*$")
+_BULLET_RE = re.compile(r"^\s*[-*]\s+(?P<text>.*\S)\s*$")
+
+
+def changelog_path() -> str | None:
+    """The shipped CHANGELOG.md, or None when this install doesn't have one.
+
+    ``backend/core/changelog.py`` → two levels up is the project root: the
+    repo root in dev, and ``<env>/project`` in packaged installs (where the
+    bootstrap copies CHANGELOG.md next to README.md). ``OMNIVOICE_CHANGELOG``
+    overrides for tests/containers.
+    """
+    override = os.environ.get("OMNIVOICE_CHANGELOG")
+    if override:
+        return override if os.path.isfile(override) else None
+    here = os.path.dirname(os.path.abspath(__file__))
+    candidate = os.path.join(os.path.dirname(os.path.dirname(here)), "CHANGELOG.md")
+    return candidate if os.path.isfile(candidate) else None
+
+
+def _looks_like_release_version(version: str) -> bool:
+    """Only released ``X.Y.Z...`` sections (skip ``[Unreleased]`` etc.)."""
+    return bool(re.match(r"^v?\d", version.strip()))
+
+
+def parse_changelog(text: str, limit_versions: int = 5) -> list[dict]:
+    """CHANGELOG.md text → newest-first list of releases::
+
+        {"version": "0.3.9", "date": "2026-07-02", "intro": "…",
+         "sections": [{"title": "Fixed", "bullets": ["…", …]}, …]}
+
+    Tolerates both single-line bullets and older hard-wrapped bullets
+    (continuation lines are joined with a space). Content between the version
+    heading and the first ``###`` becomes ``intro`` (paragraphs joined by
+    blank lines).
+    """
+    releases: list[dict] = []
+    release: dict | None = None
+    section: dict | None = None
+    intro_parts: list[str] = []
+    bullet_open = False   # last bullet may still absorb continuation lines
+    intro_new_para = True
+
+    def close_release():
+        nonlocal release, section, intro_parts, bullet_open, intro_new_para
+        if release is not None:
+            release["intro"] = "\n\n".join(p for p in intro_parts if p)
+            release["sections"] = [s for s in release["sections"] if s["bullets"]]
+            releases.append(release)
+        release = None
+        section = None
+        intro_parts = []
+        bullet_open = False
+        intro_new_para = True
+
+    for raw in text.splitlines():
+        m = _RELEASE_RE.match(raw)
+        if m:
+            close_release()
+            if len(releases) >= limit_versions:
+                break
+            version = m.group("version").strip().lstrip("v")
+            if not _looks_like_release_version(version):
+                continue  # e.g. [Unreleased] — skip until the next heading
+            release = {
+                "version": version,
+                "date": (m.group("date") or "").strip(),
+                "intro": "",
+                "sections": [],
+            }
+            continue
+        if release is None:
+            continue
+
+        line = raw.strip()
+        if not line:
+            bullet_open = False
+            intro_new_para = True
+            continue
+
+        sm = _SECTION_RE.match(raw)
+        if sm:
+            section = {"title": sm.group("title"), "bullets": []}
+            release["sections"].append(section)
+            bullet_open = False
+            continue
+
+        bm = _BULLET_RE.match(raw)
+        if bm:
+            if section is None:
+                # Rare: a bullet before any ### heading — group it untitled.
+                section = {"title": "", "bullets": []}
+                release["sections"].append(section)
+            section["bullets"].append(bm.group("text"))
+            bullet_open = True
+            continue
+
+        if section is not None:
+            if bullet_open and section["bullets"]:
+                # Hard-wrapped bullet continuation (older sections) → join.
+                section["bullets"][-1] += " " + line
+            continue
+
+        # Headline paragraph(s) before the first ### section.
+        if intro_new_para or not intro_parts:
+            intro_parts.append(line)
+        else:
+            intro_parts[-1] += " " + line
+        intro_new_para = False
+
+    close_release()
+    return releases[:limit_versions]

backend/core/db.py

@@ -3,6 +3,8 @@ import sqlite3
 import logging
 from contextlib import contextmanager
 from core.config import DB_PATH
+from core import db_backup
+from core.version import APP_VERSION
 
 logger = logging.getLogger("omnivoice.db")
 
@@ -157,6 +159,22 @@ _BASE_SCHEMA = """
         last_seen_at REAL,
         created_at REAL
     );
+
+    -- Expressive-TTS Spec 01 Phase 1: user pronunciation dictionary. A
+    -- per-language word→respelling map applied as pure text substitution
+    -- before synthesis (Settings → Pronunciation). Fresh installs create it
+    -- here; existing DBs get it via alembic 0008_pronunciation_dictionary.
+    -- Both paths converge on this identical schema (dual-path discipline).
+    CREATE TABLE IF NOT EXISTS pronunciation_entries (
+        id TEXT PRIMARY KEY,
+        term TEXT NOT NULL,
+        replacement TEXT NOT NULL DEFAULT '',
+        type TEXT NOT NULL DEFAULT 'respelling',
+        language TEXT NOT NULL DEFAULT '*',
+        enabled INTEGER NOT NULL DEFAULT 1,
+        created_at REAL
+    );
+    CREATE INDEX IF NOT EXISTS idx_pron_lang ON pronunciation_entries(language);
 """
 
 # Only tables/columns this module is allowed to ALTER. Prevents SQL injection via
@@ -206,6 +224,72 @@ def _migrate(conn, current: int) -> int:
     return current
 
 
+def _reconcile_additive_columns(conn) -> None:
+    """Make the live schema converge to ``_BASE_SCHEMA`` by ADDing any column the
+    canonical schema declares but an existing table is missing — the belt for
+    when alembic can't run on an upgraded DB.
+
+    ``CREATE TABLE IF NOT EXISTS`` (init_db) never adds columns to a table that
+    already exists, the legacy ``_migrate`` only knows pre-0.3 columns, and
+    ``_run_alembic_upgrade`` swallows failures. So a DB whose ``alembic_version``
+    is stamped at a removed revision (e.g. after running a preview build), or
+    where alembic isn't importable in the bundled interpreter, would otherwise
+    lose every alembic-era additive column forever — the ``no such column:
+    consent_audio_path`` 500 (#552/#547), and the same class for
+    ``kind``/``vd_states``/``is_demo``/.... Additive only: never drops or retypes
+    a column, so it is safe and backward-compatible with existing user data. The
+    canonical names/types/defaults come solely from ``_BASE_SCHEMA`` (developer
+    controlled), so the ALTER is injection-safe.
+    """
+    canon = sqlite3.connect(":memory:")
+    try:
+        canon.executescript(_BASE_SCHEMA)
+        _tables_sql = "SELECT name FROM sqlite_master WHERE type='table' AND name NOT LIKE 'sqlite_%'"
+        live_tables = {r[0] for r in conn.execute(_tables_sql)}
+        for table in (r[0] for r in canon.execute(_tables_sql)):
+            if table not in live_tables:
+                continue  # whole table missing → init_db's CREATE already made it
+            have = {r[1] for r in conn.execute(f"PRAGMA table_info({table})")}
+            # (cid, name, type, notnull, dflt_value, pk)
+            for _cid, name, ctype, notnull, dflt, _pk in canon.execute(f"PRAGMA table_info({table})"):
+                if name in have or not _IDENT_RE.match(name):
+                    continue
+                ddl = f'ALTER TABLE "{table}" ADD COLUMN "{name}" {ctype or "TEXT"}'
+                if dflt is not None:
+                    ddl += f" DEFAULT {dflt}"
+                elif notnull:
+                    ddl += " DEFAULT ''"  # SQLite requires a default to ADD a NOT NULL column
+                try:
+                    conn.execute(ddl)
+                    logger.info("schema reconcile: added missing column %s.%s", table, name)
+                except sqlite3.OperationalError as exc:
+                    if "duplicate column" not in str(exc).lower():
+                        logger.warning("schema reconcile ALTER %s.%s failed: %s", table, name, exc)
+        conn.commit()
+    finally:
+        canon.close()
+
+
+def ensure_schema() -> None:
+    """Idempotently ensure the base tables + additive columns exist.
+
+    A runtime self-heal for a DB that somehow missed init — e.g. a write hitting
+    ``no such table: generation_history`` (#710) because ``init_db()``'s
+    ``executescript`` never took on that DB. Safe to call anytime: it's just
+    ``CREATE ... IF NOT EXISTS`` plus the additive-only column reconcile, so it
+    never drops or retypes anything and is backward-compatible with user data.
+    Cheaper than ``init_db()`` (skips the legacy ``_migrate`` + alembic), so a
+    write path can call it on a schema error and retry without a 500.
+    """
+    conn = get_db()
+    try:
+        conn.executescript(_BASE_SCHEMA)
+        _reconcile_additive_columns(conn)
+        conn.commit()
+    finally:
+        conn.close()
+
+
 def init_db():
     conn = get_db()
     try:
@@ -214,6 +298,11 @@ def init_db():
         new_version = _migrate(conn, version)
         if new_version != version:
             conn.execute(f"PRAGMA user_version = {new_version}")
+        # Converge any alembic-era additive columns that CREATE TABLE IF NOT
+        # EXISTS + the legacy _migrate don't add to a pre-existing table
+        # (consent_audio_path, kind, ...). Runs regardless of whether alembic
+        # below succeeds, so an unrunnable alembic can't leave a 500-ing schema.
+        _reconcile_additive_columns(conn)
         conn.commit()
     finally:
         conn.close()
@@ -225,12 +314,88 @@ def init_db():
     _run_alembic_upgrade()
 
 
+class MigrationError(RuntimeError):
+    """A schema migration failed *while executing*. Startup must NOT continue
+    on a possibly half-migrated database — the caller lets this propagate so
+    the process stops with an actionable message naming the pre-migration
+    backup (see ``core.db_backup``). Restore is deliberately manual: silently
+    auto-restoring the snapshot could itself discard user data."""
+
+
+def _reconcile_after_alembic_skip() -> None:
+    """Converge the schema directly when alembic can't run at all (not
+    importable, or stamped at a removed revision — #552/#547) so additive
+    columns still land instead of 500-ing on `no such column`. Only for the
+    "nothing was applied" classes; a mid-migration failure must NOT reach
+    here (see MigrationError)."""
+    try:
+        conn = get_db()
+        try:
+            _reconcile_additive_columns(conn)
+        finally:
+            conn.close()
+    except Exception as exc:  # noqa: BLE001
+        logger.warning("schema reconcile after alembic skip also failed: %s", exc)
+
+
+def _stamped_revisions(db_path: str) -> set | None:
+    """Revisions recorded in ``alembic_version`` (empty set = never stamped),
+    or None when the DB can't be read."""
+    try:
+        conn = sqlite3.connect(db_path)
+        try:
+            try:
+                return {r[0] for r in conn.execute("SELECT version_num FROM alembic_version")}
+            except sqlite3.OperationalError:
+                return set()  # table absent — nothing ever stamped
+        finally:
+            conn.close()
+    except Exception:  # noqa: BLE001
+        return None
+
+
+def _plan_alembic(cfg) -> str:
+    """Decide what an ``upgrade head`` run would actually do:
+
+    - ``up_to_date``       — stamped at head; upgrade is a no-op.
+    - ``pending``          — migrations WILL execute (snapshot the DB first).
+    - ``unknown_revision`` — stamped at a revision this build doesn't ship
+      (preview→stable downgrade, #552/#547); upgrade would fail before
+      applying anything, so skip it and reconcile additively instead.
+    - ``indeterminate``    — can't tell; treat like pending (snapshot, run).
+    """
+    try:
+        from alembic.script import ScriptDirectory
+
+        script = ScriptDirectory.from_config(cfg)
+        known = {rev.revision for rev in script.walk_revisions()}
+        heads = set(script.get_heads())
+        stamped = _stamped_revisions(DB_PATH)
+        if stamped is None:
+            return "indeterminate"
+        if stamped and not stamped <= known:
+            return "unknown_revision"
+        if stamped == heads:
+            return "up_to_date"
+        return "pending"
+    except Exception:  # noqa: BLE001
+        return "indeterminate"
+
+
 def _run_alembic_upgrade() -> None:
-    """Best-effort `alembic upgrade head` on startup. Non-fatal: if alembic
-    isn't reachable (e.g. user running a stripped-down install or migrations
-    were already applied out-of-band), log a warning and move on. The
-    _BASE_SCHEMA CREATE TABLE IF NOT EXISTS above guarantees the runtime
-    schema is correct regardless."""
+    """`alembic upgrade head` on startup, wrapped in the data-safety net.
+
+    Failure classes are handled differently on purpose:
+
+    - alembic unavailable / stamped at an unknown revision → **non-fatal**
+      (nothing was applied; warn + `_reconcile_additive_columns` keeps the
+      schema converged, exactly the pre-existing #552/#547 behavior).
+    - migrations actually pending → the DB is snapshotted first
+      (``omnivoice.db.backup-<version>-<n>``, newest 3 kept), then upgraded.
+    - a migration fails **while executing** → raise :class:`MigrationError`:
+      startup stops with a message naming the backup, instead of silently
+      running the app on a half-migrated DB.
+    """
     try:
         import os
         from alembic import command
@@ -246,8 +411,62 @@ def _run_alembic_upgrade() -> None:
             return
         cfg = Config(ini)
         cfg.set_main_option("sqlalchemy.url", f"sqlite:///{DB_PATH}")
+    except Exception as exc:  # noqa: BLE001 — alembic not importable / bad ini
+        logger.warning("alembic upgrade head skipped: %s", exc)
+        _reconcile_after_alembic_skip()
+        return
+
+    plan = _plan_alembic(cfg)
+    if plan == "up_to_date":
+        return
+    if plan == "unknown_revision":
+        logger.warning(
+            "alembic_version is stamped at a revision this build doesn't ship "
+            "(preview/newer build ran on this DB) — skipping alembic and "
+            "reconciling the schema additively (#552/#547)"
+        )
+        _reconcile_after_alembic_skip()
+        return
+
+    # Migrations may actually execute: snapshot the DB first so a failed or
+    # interrupted migration can never cost user data. A backup problem alone
+    # must not brick startup (the >500 MB skip is by design), so log and go on.
+    # ``db_backup``/``APP_VERSION`` are module-level imports (top of file), not
+    # re-imported here: a test that patches ``core.db_backup.MAX_BACKUP_DB_BYTES``
+    # on the object it imported at collection must see the same object this
+    # function uses. A lazy ``from core import db_backup`` would re-resolve
+    # through the (possibly re-imported) ``core`` package and silently miss the
+    # patch after another suite purged ``core.*`` from ``sys.modules``.
+    backup_path = None
+    try:
+        backup_path = db_backup.snapshot_before_migration(DB_PATH, APP_VERSION)
+    except Exception:  # noqa: BLE001
+        logger.exception("Pre-migration DB backup failed — continuing without one")
+
+    try:
         command.upgrade(cfg, "head")
     except Exception as exc:
-        # Don't block startup on a migration tooling problem. The runtime
-        # schema is already correct via _BASE_SCHEMA.
-        logger.warning("alembic upgrade head skipped: %s", exc)
+        if "Can't locate revision" in str(exc):
+            # Belt for an unknown-revision case _plan_alembic missed: alembic
+            # bails before applying anything, so the old non-fatal path is safe.
+            logger.warning("alembic upgrade head skipped: %s", exc)
+            _reconcile_after_alembic_skip()
+            return
+        backup_note = (
+            f"A backup of your data from just before the migration is at: {backup_path}"
+            if backup_path
+            else "No pre-migration backup was written this run (see the log above)"
+        )
+        msg = (
+            f"Database migration failed while running: {exc}. "
+            f"OmniVoice stopped instead of running on a partially migrated database, "
+            f"and nothing was auto-restored (your database at {DB_PATH} was left "
+            f"exactly as the failed migration left it). "
+            f"{backup_note}. "
+            "What to do: relaunch to retry; if it keeps failing, report it at "
+            "https://github.com/debpalash/OmniVoice-Studio/issues (keep the backup file). "
+            "To roll back manually: quit the app, replace omnivoice.db with the backup "
+            "file, and reinstall the previous version."
+        )
+        logger.error(msg)
+        raise MigrationError(msg) from exc

backend/core/db_backup.py

@@ -0,0 +1,169 @@
+"""Pre-migration SQLite safety net (data-safe updates).
+
+Before ``alembic upgrade head`` applies *pending* migrations at startup —
+which is exactly the first launch of a new app version that changed the
+schema — the live database is snapshotted next to itself as
+``omnivoice.db.backup-<version>-<n>`` so a failed or interrupted migration
+can never cost user data (voices, projects, history, settings).
+
+Design rules (owner intent: "never corrupt/erase user data on update"):
+
+- Snapshots use the SQLite online-backup API (``sqlite3.Connection.backup``),
+  not a file copy — the live DB runs in WAL mode, so a plain copy could miss
+  everything still sitting in ``omnivoice.db-wal``.
+- Only the most recent ``KEEP_BACKUPS`` snapshots are kept; older ones are
+  pruned so backups can't grow without bound.
+- DBs larger than ``MAX_BACKUP_DB_BYTES`` are skipped with a log line (a
+  multi-hundred-MB copy on every schema upgrade is worse than the risk it
+  hedges on those installs).
+- Restore is NEVER automatic. On migration failure the caller
+  (``core.db._run_alembic_upgrade``) stops startup and names the backup path
+  so the user (or a support thread) decides — a silent auto-restore could
+  itself discard data written after the snapshot.
+"""
+from __future__ import annotations
+
+import logging
+import os
+import re
+import sqlite3
+import time
+
+logger = logging.getLogger("omnivoice.db.backup")
+
+#: Keep this many snapshots; older ones are pruned after each new snapshot.
+KEEP_BACKUPS = 3
+
+#: Skip the snapshot (with a log line) when the DB exceeds this size.
+MAX_BACKUP_DB_BYTES = 500 * 1024 * 1024
+
+#: ``<db name>.backup-<version>-<n>`` — ``<version>`` may itself contain
+#: dashes (preview builds stamp ``0.3.9-41``), so the counter is the final
+#: ``-<digits>`` group.
+_BACKUP_SUFFIX_RE = re.compile(r"\.backup-(?P<version>.+)-(?P<n>\d+)$")
+
+
+def _sanitize_version(version: str) -> str:
+    """Version string → filesystem-safe fragment (defense in depth; real
+    versions are semver and already safe)."""
+    safe = re.sub(r"[^A-Za-z0-9._-]", "_", str(version).strip()) or "unknown"
+    return safe[:64]
+
+
+def list_backups(db_path: str) -> list[str]:
+    """All backup files for ``db_path``, newest first (mtime desc)."""
+    directory = os.path.dirname(os.path.abspath(db_path)) or "."
+    base = os.path.basename(db_path)
+    try:
+        names = os.listdir(directory)
+    except OSError:
+        return []
+    out = []
+    for name in names:
+        if not name.startswith(base + ".backup-"):
+            continue
+        if not _BACKUP_SUFFIX_RE.search(name[len(base):]):
+            continue
+        out.append(os.path.join(directory, name))
+    out.sort(key=lambda p: (_mtime(p), p), reverse=True)
+    return out
+
+
+def _mtime(path: str) -> float:
+    try:
+        return os.path.getmtime(path)
+    except OSError:
+        return 0.0
+
+
+def latest_backup(db_path: str) -> dict | None:
+    """Newest backup as ``{"path", "created_at", "size_bytes"}`` or None."""
+    backups = list_backups(db_path)
+    if not backups:
+        return None
+    path = backups[0]
+    try:
+        st = os.stat(path)
+    except OSError:
+        return None
+    return {"path": path, "created_at": st.st_mtime, "size_bytes": st.st_size}
+
+
+def _next_counter(db_path: str, safe_version: str) -> int:
+    """Next free ``<n>`` for this version so a re-run never overwrites an
+    earlier snapshot of the same version."""
+    base = os.path.basename(db_path)
+    prefix = f"{base}.backup-{safe_version}-"
+    highest = 0
+    for path in list_backups(db_path):
+        name = os.path.basename(path)
+        if not name.startswith(prefix):
+            continue
+        tail = name[len(prefix):]
+        if tail.isdigit():
+            highest = max(highest, int(tail))
+    return highest + 1
+
+
+def prune_backups(db_path: str, keep: int = KEEP_BACKUPS) -> list[str]:
+    """Delete all but the ``keep`` newest backups. Returns deleted paths."""
+    deleted = []
+    for path in list_backups(db_path)[keep:]:
+        try:
+            os.remove(path)
+            deleted.append(path)
+            logger.info("Pruned old DB backup %s", path)
+        except OSError as exc:
+            logger.warning("Could not prune old DB backup %s: %s", path, exc)
+    return deleted
+
+
+def snapshot_before_migration(db_path: str, version: str) -> str | None:
+    """Snapshot ``db_path`` to ``<db>.backup-<version>-<n>``.
+
+    Returns the backup path, or None when skipped (no DB yet, or DB larger
+    than ``MAX_BACKUP_DB_BYTES``). Raises on an actual backup failure so the
+    caller can decide (the caller treats that as "continue without a backup",
+    logged loudly — a backup problem must not brick startup by itself).
+    """
+    if not os.path.isfile(db_path):
+        logger.debug("No DB at %s yet — nothing to back up", db_path)
+        return None
+    size = os.path.getsize(db_path)
+    if size > MAX_BACKUP_DB_BYTES:
+        logger.info(
+            "Skipping pre-migration DB backup: %s is %.0f MB (> %.0f MB limit)",
+            db_path, size / (1024 * 1024), MAX_BACKUP_DB_BYTES / (1024 * 1024),
+        )
+        return None
+
+    safe_version = _sanitize_version(version)
+    target = f"{db_path}.backup-{safe_version}-{_next_counter(db_path, safe_version)}"
+    tmp = f"{target}.part-{os.getpid()}"
+    src = sqlite3.connect(db_path)
+    try:
+        dst = sqlite3.connect(tmp)
+        try:
+            # Online backup: consistent snapshot including WAL contents.
+            src.backup(dst)
+            dst.commit()
+        finally:
+            dst.close()
+    except BaseException:
+        try:
+            os.remove(tmp)
+        except OSError:
+            pass
+        raise
+    finally:
+        src.close()
+    os.replace(tmp, target)
+    # A same-second rotation must still rank the new file newest.
+    try:
+        now = time.time()
+        os.utime(target, (now, now))
+    except OSError:
+        pass
+    logger.info("Pre-migration DB backup written: %s (%.1f MB)", target, size / (1024 * 1024))
+    prune_backups(db_path)
+    return target

backend/core/error_journal.py

@@ -76,6 +76,12 @@ _CLASS_RULES: tuple[tuple[str, tuple[str, ...]], ...] = (
         "connection refused",
         "connection reset",
         "connection aborted",
+        # transformers' download-failure wording ("We couldn't connect to
+        # '<endpoint>' to load the files") — the #874 mirror-down class was
+        # journaled as UNKNOWN without these.
+        "couldn't connect to",
+        "could not connect to",
+        "max retries exceeded",
         "timed out",
         "timeout",
         "name or service not known",

backend/core/failure.py

@@ -21,6 +21,7 @@ import re
 import sys
 from pathlib import Path
 from typing import Any, Optional
+from urllib.parse import urlsplit
 
 from core import error_docs_map
 from core.logging_filter import REDACTED, _HF_TOKEN_RE
@@ -37,9 +38,136 @@ _HINTS: dict[str, str] = {
     "APPIMAGE_WEBKIT_WHITESCREEN": "Launch with WEBKIT_DISABLE_DMABUF_RENDERER=1 set.",
     "HF_AUTH_FAILED": "Set a valid HF_TOKEN in Settings → Hugging Face and retry.",
     "PYANNOTE_LICENSE_REQUIRED": "Accept the pyannote model licenses on Hugging Face, then retry.",
+    "COMPUTE_TYPE_UNSUPPORTED": "Your GPU doesn't support float16 — OmniVoice retried on int8. If transcription still fails, set OMNIVOICE/ASR_COMPUTE_TYPE=int8 or use CPU.",
+    "TRANSFORMERS_IMPORT": "Your transformers install is incomplete. Reinstall it (`uv pip install --reinstall transformers`) or switch ASR to faster-whisper (Settings → Models).",
+    "OS_INVALID_ARGUMENT": "The OS rejected a file operation (Errno 22 / invalid argument) — in the transcribe path this is the temporary WAV write before ASR. It's almost always the temp directory: missing, read-only, on a full or removed drive, or blocked by antivirus. Check that your system TEMP/TMP folder exists and is writable and the drive has free space (add an OmniVoice antivirus exclusion if you use one), then retry.",
+    "UNSUPPORTED_VIDEO_URL": "This link isn't a directly downloadable video. Paste a direct video page (e.g. a youtube.com/watch?v=… or douyin.com/video/<id> link), not a share/profile/feed link — or download the file and drop it in directly.",
+    "VIDEO_DOWNLOAD_NETWORK": "The connection to the video server dropped mid-download (often a transient CDN/network blip or a regional rate-limit). Just retry — OmniVoice already cleaned up the partial download. If it keeps failing, check your network/VPN.",
+    "BROKEN_VENV": "The Python backend environment was moved or damaged. OmniVoice rebuilds it automatically on the next launch; if it keeps failing, use Clean & Retry on the setup screen.",
+    # HF_MIRROR_UNREACHABLE has a DYNAMIC hint (it names the configured mirror)
+    # — see hf_mirror_hint(); build_failure special-cases it.
 }
 
 
+# ── HF mirror connectivity (#874) ────────────────────────────────────────────
+# When a non-default HF_ENDPOINT (a mirror, e.g. hf-mirror.com — set via
+# Settings → Models → Hugging Face mirror) is configured and a model
+# download/load fails with a connectivity error, the raw transformers/hf_hub
+# message ("We couldn't connect to 'https://hf-mirror.com' to load the files…")
+# gives the user no next step. This is the single classifier for that class,
+# shared by every surface: build_failure() (model status, dub/task events),
+# the global 500 handler (main.py — covers /generate and every other route
+# that can leak a model-load error), and the model-install SSE
+# (setup/download.py).
+
+_OFFICIAL_HF_ENDPOINTS = {"https://huggingface.co", "https://hf.co"}
+
+# Connectivity signatures across the layers an HF download failure surfaces
+# from: transformers' wording, huggingface_hub errors, requests/urllib3, and
+# raw socket/DNS failures (Linux/macOS/Windows variants).
+_HF_CONNECTIVITY_SIGNATURES = (
+    "couldn't connect to",             # transformers: "We couldn't connect to '<endpoint>' …"
+    "could not connect to",
+    "connection error",                # huggingface_hub / requests
+    "connection refused",
+    "connection reset",
+    "connection aborted",
+    "max retries exceeded",            # urllib3 via requests
+    "failed to establish a new connection",
+    "name or service not known",       # Linux DNS
+    "temporary failure in name resolution",
+    "nodename nor servname provided",  # macOS DNS
+    "getaddrinfo failed",              # Windows DNS
+    "timed out",
+    "an error happened while trying to locate the file on the hub",  # LocalEntryNotFoundError
+    "we cannot find the requested files",                            # LocalEntryNotFoundError
+)
+
+# The failure must also be Hugging-Face-shaped — the configured endpoint/host
+# named in the message, or HF-download wording — so a random socket error
+# (e.g. a local LLM provider being down) doesn't get the mirror hint just
+# because a mirror happens to be configured.
+_HF_CONTEXT_MARKERS = (
+    "huggingface",
+    "hf_hub",
+    "hf-hub",
+    "load the files",          # transformers
+    "cached files",            # transformers
+    "the requested files",     # LocalEntryNotFoundError
+    "locate the file on the hub",
+    "snapshot_download",
+)
+
+
+def configured_hf_mirror() -> str:
+    """The non-default Hugging Face endpoint (mirror) in effect, or "".
+
+    Same resolution the download paths use: ``HF_ENDPOINT`` env (what
+    Settings → Models → Hugging Face mirror persists via user_env, and what
+    the HF libraries read) with the ``hf_endpoint`` pref as fallback
+    (mirrors setup/download.py's ``prefs.resolve``). Never raises.
+    """
+    ep = (os.environ.get("HF_ENDPOINT") or "").strip()
+    if not ep:
+        try:
+            from core import prefs
+
+            ep = str(prefs.get("hf_endpoint", "") or "").strip()
+        except Exception:
+            ep = ""
+    ep = ep.rstrip("/")
+    if not ep or ep.lower() in _OFFICIAL_HF_ENDPOINTS:
+        return ""
+    return ep
+
+
+def hf_mirror_hint(reason: Optional[str]) -> str:
+    """Actionable hint when ``reason`` is an HF-download connectivity failure
+    and a non-default mirror endpoint is configured; "" otherwise.
+
+    The hint names the configured mirror, says it may be down, points at the
+    setting (Settings → Models → Hugging Face mirror), suggests the official
+    endpoint when the model isn't cached yet, and notes the restart
+    requirement (HF reads HF_ENDPOINT at import time — see the hf-mirror
+    endpoints in api/routers/settings.py). Never raises.
+    """
+    mirror = configured_hf_mirror()
+    if not mirror:
+        return ""
+    low = (reason or "").lower()
+    if not any(sig in low for sig in _HF_CONNECTIVITY_SIGNATURES):
+        return ""
+    try:
+        host = (urlsplit(mirror).netloc or "").lower()
+    except Exception:
+        host = ""
+    if not (
+        mirror.lower() in low
+        or (host and host in low)
+        or any(m in low for m in _HF_CONTEXT_MARKERS)
+    ):
+        return ""
+    return (
+        f"Your Hugging Face mirror is set to {mirror}, which couldn't be "
+        "reached — the mirror may be down or blocked on your network. If the "
+        'model isn\'t in your local cache yet, switch to "Hugging Face '
+        '(official)" in Settings → Models → Hugging Face mirror (or wait for '
+        "the mirror to recover), then restart OmniVoice — the mirror setting "
+        "is applied when the app starts."
+    )
+
+
+def append_hf_mirror_hint(text: str) -> str:
+    """``"{text} — {hint}"`` when the mirror-connectivity class applies;
+    ``text`` unchanged otherwise. For surfaces that hand a raw error string to
+    the UI (the global 500 handler, the model-install SSE). Never raises."""
+    try:
+        hint = hf_mirror_hint(text)
+    except Exception:
+        return text
+    return f"{text} — {hint}" if hint else text
+
+
 def classify(reason: str) -> str:
     """Map a failure reason to a docs-taxonomy key, or "" when unknown.
 
@@ -55,10 +183,78 @@ def classify(reason: str) -> str:
         return "APPIMAGE_WEBKIT_WHITESCREEN"
     if "pyannote" in low or ("gated" in low and "model" in low) or "accept the" in low:
         return "PYANNOTE_LICENSE_REQUIRED"
+    # ASR robustness (#551 / #549): name the class so the no-segments toast is
+    # actionable. Place before the generic returns so a compute-type/transformers
+    # failure gets its hint rather than falling through to "".
+    if "compute type" in low or "efficient float16" in low:
+        return "COMPUTE_TYPE_UNSUPPORTED"
+    # #763: a bare OS-level EINVAL ("[Errno 22] Invalid argument") while writing
+    # the per-chunk temp WAV for transcription (tempfile.NamedTemporaryFile /
+    # soundfile.write on the system temp dir) used to collapse into a dead-end
+    # "produced no segments. [Errno 22] Invalid argument" toast with no next
+    # step. errno 22 is EINVAL on every platform; in this path it's almost always
+    # a temp dir that's missing, read-only, on a full/removed drive, or blocked
+    # by antivirus. Name the class so build_failure attaches an actionable hint
+    # instead of a raw errno. Matching the errno (not the generic "invalid
+    # argument" wording) keeps this from mislabelling unrelated failures; the
+    # transformers "errno 2" rule below is unaffected — it also requires the
+    # transformers + site-packages markers, which this signature lacks.
+    if "errno 22" in low:
+        return "OS_INVALID_ARGUMENT"
+    if (
+        "could not import module" in low
+        or "autofeatureextractor" in low
+        # A corrupted/incomplete transformers install: a model load lazily
+        # resolves a module file that's MISSING from site-packages (an
+        # interrupted `uv sync`, antivirus removal, or a partial update), e.g.
+        # `[Errno 2] No such file or directory:
+        #  '.../site-packages/transformers/models/qwen3/modeling_qwen3.py'`.
+        # That's a FileNotFoundError, not an ImportError, so the matches above
+        # miss it and the user got a useless "try restarting". Substring-match
+        # the package + the missing-file signal (separately, so it works on both
+        # POSIX `/` and Windows `\` paths).
+        or (
+            ("no such file" in low or "errno 2" in low)
+            and "transformers" in low
+            and "site-packages" in low
+        )
+    ):
+        return "TRANSFORMERS_IMPORT"
     if ("huggingface" in low or "hf_token" in low or "401" in low or "unauthorized" in low) and (
         "token" in low or "auth" in low or "401" in low or "unauthorized" in low
     ):
         return "HF_AUTH_FAILED"
+    # #874: a model download that failed because the CONFIGURED HF mirror is
+    # unreachable. Env-aware by design — the class only exists when a
+    # non-default HF_ENDPOINT is configured. Checked BEFORE the video-download
+    # network class so a model download's "timed out"/"connection reset"
+    # names the mirror instead of the "video server".
+    if hf_mirror_hint(reason):
+        return "HF_MIRROR_UNREACHABLE"
+    # Video download (#554/#536): a non-downloadable URL shape vs a transient
+    # network drop — both previously surfaced as a bare yt-dlp string with no
+    # next step. UNSUPPORTED first (more specific) so "Unable to download video:
+    # Broken pipe" still classifies as a network blip.
+    if "unsupported url" in low or "no video formats" in low or "is not a valid url" in low:
+        return "UNSUPPORTED_VIDEO_URL"
+    if (
+        "broken pipe" in low
+        or "connection reset" in low
+        or "unable to download video" in low
+        or "remote end closed" in low
+        or "timed out" in low
+    ):
+        return "VIDEO_DOWNLOAD_NETWORK"
+    # A relocated/corrupted venv whose interpreter can't bootstrap its stdlib —
+    # the Rust self-heal rebuilds it; this names the class for the toast.
+    if "no module named 'encodings'" in low:
+        return "BROKEN_VENV"
+    # #564: the interpreter starts fine but the backend can't import its OWN
+    # `omnivoice` package (a venv missing the editable install). Same self-heal
+    # class — Clean & Retry / the bootstrap repair rebuilds it. The trailing
+    # quote keeps a legitimately-named `omnivoice_*` helper from matching.
+    if "no module named 'omnivoice'" in low:
+        return "BROKEN_VENV"
     return ""
 
 
@@ -154,12 +350,15 @@ def build_failure(
 
     reason = sanitize(raw) or error_class
     docs_topic = classify(raw)
+    # HF_MIRROR_UNREACHABLE's hint is dynamic (it names the configured mirror)
+    # so it can't live in the static _HINTS table.
+    hint = hf_mirror_hint(raw) if docs_topic == "HF_MIRROR_UNREACHABLE" else _HINTS.get(docs_topic, "")
     fields: dict[str, Any] = {
         "reason": reason,
         "error": reason,  # backward-compat mirror for older frontends
         "error_class": error_class,
         "stage": stage,
-        "hint": _HINTS.get(docs_topic, ""),
+        "hint": hint,
         "docs_topic": docs_topic,
         "docs_url": error_docs_map.ERROR_DOCS.get(docs_topic, ""),
         "detail": sanitize(raw),

backend/core/omnivoice_path.py

@@ -0,0 +1,77 @@
+"""Resolve the project's own ``omnivoice`` package from source when the venv's
+editable install is missing (#564).
+
+``omnivoice`` is normally an editable install in the backend venv. An interrupted
+or offline ``uv sync`` can install dependencies yet never lay the editable record
+(``_editable_impl_omnivoice.pth``), or an antivirus quarantine can remove it —
+leaving a venv that starts uvicorn but cannot ``import omnivoice``, so it boots
+fine and only fails at the first model call (``No module named 'omnivoice'``).
+
+The desktop layout always copies ``omnivoice/`` next to ``backend/``, so we fall
+back to importing it from there. The bootstrap now also gates on omnivoice being
+importable (re-syncing to re-lay the editable install), but this keeps the
+backend resilient even when that repair hasn't run yet.
+"""
+import os
+import sys
+
+
+def find_omnivoice_source_root(candidates):
+    """Return the first candidate dir holding ``omnivoice/__init__.py``, else None."""
+    for root in candidates:
+        if root and os.path.isfile(os.path.join(root, "omnivoice", "__init__.py")):
+            return root
+    return None
+
+
+def _candidate_roots(backend_dir):
+    """Source roots to probe, most-specific first.
+
+    ``OMNIVOICE_PROJECT_ROOT`` lets the launcher point at the staged project dir
+    explicitly; otherwise the desktop layout puts ``omnivoice/`` beside
+    ``backend/`` (parent of ``backend_dir``).
+    """
+    roots = []
+    env = os.environ.get("OMNIVOICE_PROJECT_ROOT")
+    if env:
+        roots.append(env)
+    roots.append(os.path.dirname(os.path.abspath(backend_dir)))
+    return roots
+
+
+def _already_importable():
+    import importlib.util
+    try:
+        return importlib.util.find_spec("omnivoice") is not None
+    except (ImportError, ValueError):
+        # A half-laid spec (e.g. a stale .pth pointing at a deleted dir) raises
+        # rather than returning None — treat it as "not importable" so we fall
+        # back to the on-disk source.
+        return False
+
+
+def ensure_omnivoice_importable(backend_dir, logger=None):
+    """Make ``import omnivoice`` work, falling back to the sibling source tree.
+
+    No-op when the editable/site-packages install already resolves it. Otherwise
+    appends the first source root containing ``omnivoice/`` to ``sys.path``
+    (appended, never inserted, so a real install keeps precedence). Returns the
+    root that was added, or ``None`` if none was needed or found.
+    """
+    if _already_importable():
+        return None
+    root = find_omnivoice_source_root(_candidate_roots(backend_dir))
+    if root and root not in sys.path:
+        sys.path.append(root)
+        if logger:
+            logger.warning(
+                "omnivoice not importable from the venv (missing/broken editable "
+                "install) — resolving it from source at %s (#564)", root,
+            )
+    elif logger and root is None:
+        logger.error(
+            "omnivoice is not importable and no source tree was found next to "
+            "%s — the install is incomplete; relaunch to let the bootstrap "
+            "repair the venv (#564)", backend_dir,
+        )
+    return root

backend/core/onboarding.py

@@ -61,9 +61,15 @@ def seed_sample_project():
         if count > 0:
             return  # Not first run — skip
 
-        # Check if demo audio exists
+        # The demo clip is committed at backend/assets/samples/demo_voice.wav and
+        # bundled with the app (#621). If it's somehow absent (e.g. a partial
+        # checkout), skip the seed gracefully rather than seeding a profile that
+        # points at a missing file — run scripts/build_demos.sh to regenerate it.
         if not os.path.isfile(_DEMO_AUDIO):
-            logger.warning("Demo audio not found at %s — skipping onboarding seed", _DEMO_AUDIO)
+            logger.warning(
+                "Demo audio not found at %s — skipping onboarding seed "
+                "(regenerate with scripts/build_demos.sh)", _DEMO_AUDIO,
+            )
             return
 
         # Copy demo audio to voices directory

backend/core/scrub.py

@@ -36,18 +36,39 @@ _TOKEN_PATTERNS = (
     re.compile(r"github_pat_[A-Za-z0-9_]{20,}"),   # GitHub fine-grained PAT
     re.compile(r"gh[pousr]_[A-Za-z0-9]{30,}"),     # GitHub classic tokens
     re.compile(r"sk-[A-Za-z0-9_\-]{20,}"),         # OpenAI-style API keys
+    # A backend error can carry a secret from *any* provider (the LLM-providers
+    # feature ships a dozen), so match the common credential shapes too, not
+    # just the four vendors above — a leaked key in a public issue is real harm.
+    re.compile(r"eyJ[A-Za-z0-9_\-]{8,}\.[A-Za-z0-9_\-]{8,}\.[A-Za-z0-9_\-]{6,}"),  # JWT (Bearer)
+    re.compile(r"AIza[0-9A-Za-z_\-]{35}"),         # Google API key
+    re.compile(r"xox[baprs]-[A-Za-z0-9\-]{10,}"),  # Slack token
+    re.compile(r"AKIA[0-9A-Z]{16}"),               # AWS access key id
+    re.compile(r"(?i)bearer\s+[A-Za-z0-9._\-]{16,}"),  # opaque bearer tokens
+)
+
+# Secrets carried in a URL query string (`?token=…`, `&api_key=…`). Redact the
+# VALUE while keeping the param name + separator so the URL stays legible. Bare
+# `key=` is intentionally excluded — too common in non-secret text; shaped keys
+# are already caught above and named env vars by the sweep below.
+_URL_SECRET_RE = re.compile(
+    r"((?:access[_-]?token|api[_-]?key|apikey|auth[_-]?token|token|secret|password|passwd|pwd)=)"
+    r"([^&\s\"'#]{6,})",
+    re.IGNORECASE,
 )
 
 # Home-directory shapes for all three supported platforms. Matched
 # pattern-wise (not just this machine's $HOME) so paths quoted from a
 # user's pasted log on another OS get cleaned too.
+# IGNORECASE because Windows is case-insensitive and tools routinely emit the
+# lowercase `c:\users\<name>` form, which the CLAUDE.md redaction spec still
+# requires to become `~`. `Users`/`users`, `Home`/`home` all match.
 _HOME_PATTERNS = (
     # Windows-with-forward-slashes must run BEFORE the bare macOS shape, or
     # `/Users/<name>` inside `C:/Users/<name>` gets eaten first, leaving `C:~`.
-    re.compile(r"[A-Za-z]:/Users/[^/\s\"']+"),       # Windows, forward slashes (file URLs, normalized traces)
-    re.compile(r"/Users/[^/\s\"']+"),                # macOS
-    re.compile(r"/home/[^/\s\"']+"),                 # Linux
-    re.compile(r"[A-Za-z]:\\Users\\[^\\\s\"']+"),    # Windows, backslashes
+    re.compile(r"[A-Za-z]:/Users/[^/\s\"']+", re.IGNORECASE),   # Windows, forward slashes
+    re.compile(r"/Users/[^/\s\"']+", re.IGNORECASE),           # macOS
+    re.compile(r"/home/[^/\s\"']+", re.IGNORECASE),            # Linux
+    re.compile(r"[A-Za-z]:\\Users\\[^\\\s\"']+", re.IGNORECASE),  # Windows, backslashes
 )
 
 # Values shorter than this are too entropy-poor to be real secrets and too
@@ -85,19 +106,25 @@ def scrub_text(text: str | None) -> str:
     except Exception:
         pass
 
-    # 2. Credential-shaped substrings.
+    # 2. Credential-shaped substrings + URL query secrets.
     for pat in _TOKEN_PATTERNS:
         try:
             s = pat.sub(REDACTED, s)
         except Exception:
             pass
+    try:
+        s = _URL_SECRET_RE.sub(lambda m: m.group(1) + REDACTED, s)
+    except Exception:
+        pass
 
     # 3. This process's real home dir (covers symlinked/nonstandard homes
-    #    the generic patterns miss), then the per-OS shapes.
+    #    the generic patterns miss), then the per-OS shapes. Boundary-aware so
+    #    a home of `/Users/john` doesn't rewrite `/Users/johnny` to `~ny`
+    #    (leaking the fragment + mangling the path).
     try:
         home = os.path.expanduser("~")
         if home and home not in ("/", "~"):
-            s = s.replace(home, "~")
+            s = re.sub(re.escape(home) + r"(?=[/\\\s\"']|$)", "~", s)
     except Exception:
         pass
     for pat in _HOME_PATTERNS:
@@ -107,3 +134,24 @@ def scrub_text(text: str | None) -> str:
             pass
 
     return s
+
+
+def scrub_provider_error(detail: object, api_key: str | None = None) -> str:
+    """UI-safe text for an LLM/translation provider failure.
+
+    Some OpenAI-compatible providers echo the caller's key or a stable
+    ``user_id`` back inside their error bodies, and a raw ``str(exc)`` on the
+    translate / glossary paths would surface that verbatim. This redacts the
+    exact resolved ``api_key`` first (in the provider-registry case it isn't a
+    shaped/known-env secret, so ``scrub_text`` alone can miss it) then runs the
+    generic secret + home-path scrub. Never raises — scrubbing must not mask a
+    failure with a new one. Mirrors ``settings._scrub_llm_detail`` so every
+    surface redacts identically.
+    """
+    s = str(detail if detail is not None else "")
+    try:
+        if api_key and api_key != "local" and len(api_key) >= _MIN_SECRET_LEN:
+            s = s.replace(api_key, REDACTED)
+    except Exception:
+        pass
+    return scrub_text(s)

backend/core/version.py

@@ -2,14 +2,43 @@
 
 Read from the installed package metadata (driven by ``pyproject.toml``) so the
 FastAPI/API version and exported-bundle metadata never drift to a stale literal
-again (the prior "0.4.0" / "0.2.7" bug). Falls back to a literal only when
-running from a raw source checkout that was never ``uv sync``'d.
+— the prior "0.4.0" / "0.2.7" bug, and the v0.3.6 desktop build that reported
+"0.3.5" because the *frozen* backend couldn't read its own metadata.
+
+Resolution order:
+  1. installed package metadata — correct in any ``uv sync``'d env and, thanks
+     to ``copy_metadata('omnivoice')`` in ``backend.spec``, in the frozen build;
+  2. ``pyproject.toml`` walked up from this file — correct for a raw source
+     checkout that was never installed;
+  3. ``_FALLBACK_VERSION`` — a last resort, kept in lockstep with the four
+     version files by ``tests/test_app_version.py`` so it can never silently
+     drift again.
 """
 from __future__ import annotations
 
+import re
 from importlib.metadata import PackageNotFoundError, version
+from pathlib import Path
+
+# Last-resort literal. Guarded by
+# tests/test_app_version.py::test_all_version_files_in_lockstep and bumped by
+# release.yml's version-bump job, so it stays equal to
+# pyproject/tauri.conf/Cargo/package.json.
+_FALLBACK_VERSION = "0.3.9"
+
+
+def _fallback_version() -> str:
+    """Version for contexts where package metadata is unavailable."""
+    for parent in Path(__file__).resolve().parents:
+        pyproject = parent / "pyproject.toml"
+        if pyproject.is_file():
+            match = re.search(r'(?m)^version\s*=\s*"([^"]+)"', pyproject.read_text())
+            if match:
+                return match.group(1)
+    return _FALLBACK_VERSION
+
 
 try:
     APP_VERSION = version("omnivoice")
-except PackageNotFoundError:  # non-installed source checkout
-    APP_VERSION = "0.3.5"
+except PackageNotFoundError:  # frozen build w/o metadata, or non-installed checkout
+    APP_VERSION = _fallback_version()

backend/engines/_asr_sidecar/main.py

@@ -50,6 +50,22 @@ def _recv(stream):
     return json.loads(bytes(body).decode("utf-8"))
 
 
+# NOTE: keep this compute_type fallback in lockstep with
+# services/asr_backend.py:_compute_type_candidates / _is_compute_type_error.
+# This sidecar runs in a child proc with a clean import path, so we duplicate a
+# tiny copy rather than cross-importing the heavy services package (#551).
+def _ct_candidates(device):
+    override = os.environ.get("ASR_COMPUTE_TYPE")
+    if override:
+        return [override]
+    return ["float16", "int8_float16", "int8"] if device == "cuda" else ["int8", "float32"]
+
+
+def _is_ct_error(msg):
+    low = msg.lower()
+    return "compute type" in low or "efficient float16" in low
+
+
 def _get_model():
     global _model
     if _model is None:
@@ -60,8 +76,20 @@ def _get_model():
             device = "cuda" if torch.cuda.is_available() else "cpu"
         except Exception:
             device = "cpu"
-        compute = "float16" if device == "cuda" else "int8"
-        _model = WhisperModel(name, device=device, compute_type=compute)
+        # Degrade fp16 → int8 rather than crash on GPUs without efficient fp16
+        # (older Maxwell/Pascal, GTX 16xx, CTranslate2/cuDNN mismatch) (#551).
+        last_err = None
+        for compute in _ct_candidates(device):
+            try:
+                _model = WhisperModel(name, device=device, compute_type=compute)
+                break
+            except (ValueError, RuntimeError) as e:
+                last_err = e
+                if _is_ct_error(str(e)):
+                    continue
+                raise
+        else:
+            raise last_err
     return _model
 
 

backend/engines/confucius4/__init__.py

@@ -0,0 +1,134 @@
+"""Confucius4-TTS sidecar package (issue #590).
+
+Confucius4-TTS (netease-youdao) is an LLM-based multilingual / cross-lingual
+zero-shot voice-cloning TTS: 14 languages, **no reference transcript required**,
+cross-lingual voice transfer, Apache-2.0 (https://github.com/netease-youdao/Confucius4-TTS).
+
+Like IndexTTS / MOSS-TTS-v1.5 / dots.tts it runs in its **own subprocess venv**
+(upstream: Python 3.10 + CUDA 12.6 + its own deps), isolated from the OmniVoice
+parent. It is **opt-in** — selected in the engine picker and enabled only when
+the user points ``OMNIVOICE_CONFUCIUS4_TTS_DIR`` at a clone — so it can never
+become a broken default on any platform (the strict default-parity rule).
+
+Status (#590): **validated end-to-end** (2026-07-02, Apple Silicon, CPU) — the
+synthesis API (``confuciustts.cli.inference.ConfuciusTTS`` →
+``.generate(text, lang, prompt_wav)`` → tensor, ``model.sample_rate``) produced
+audible speech at 22 050 Hz; the sidecar's pure logic is unit-tested
+(``tests/test_confucius4_sidecar.py``). CPU inference is slow (~17× realtime),
+so CUDA is the recommended path. Gated off by default, so this affects no one
+until they opt in.
+
+Three entry points: ``Confucius4Backend`` (this module), ``main.py`` (the sidecar,
+runs under the Confucius4 venv — never imported by the parent), and
+``bootstrap.py`` (venv probe + lazy bootstrap).
+"""
+from __future__ import annotations
+
+import logging
+from typing import TYPE_CHECKING
+
+from services.subprocess_backend import SubprocessBackend
+
+if TYPE_CHECKING:
+    import torch  # noqa: F401
+
+logger = logging.getLogger("omnivoice.confucius4")
+
+
+class Confucius4Backend(SubprocessBackend):
+    """Confucius4-TTS (netease-youdao) — LLM-based, 14 langs, zero-shot clone.
+
+    Runs in a long-lived sidecar over length-prefixed JSON-over-stdio in a
+    dedicated venv. First synthesize cold-loads the checkpoint; subsequent calls
+    reuse the process.
+
+    Installation::
+
+        git clone https://github.com/netease-youdao/Confucius4-TTS.git
+        cd Confucius4-TTS
+        uv venv --python 3.10 && uv pip install -r requirements.txt
+
+    (Upstream ships no pyproject.toml/setup.py, so there is nothing to
+    ``pip install -e`` — the sidecar sys.path-inserts the clone instead.)
+    Then set ``OMNIVOICE_CONFUCIUS4_TTS_DIR`` to the clone root and restart.
+    License: Apache-2.0. CUDA recommended; CPU validated but ~17× realtime.
+    """
+
+    id = "confucius4-tts"
+    display_name = (
+        "Confucius4-TTS (LLM, 14 langs, cross-lingual zero-shot clone, CUDA/CPU, Apache-2.0)"
+    )
+    supports_voice_design = False  # timbre comes from a reference clip
+    # Upstream vocoder rate (config target_sample_rate) — confirmed 22 050 Hz by
+    # a live run (2026-07-02); still re-read from the sidecar's ready/audio frames.
+    _DEFAULT_SAMPLE_RATE = 22050
+    # CUDA fast path + CPU fallback, both exercised (CPU end-to-end validated).
+    # No MPS claim — upstream has no Metal path.
+    gpu_compat = ("cuda", "cpu")
+
+    @classmethod
+    def is_available(cls) -> tuple[bool, str]:
+        # Verify the venv on disk only — do NOT import the engine here (separate
+        # interpreter). A real health-check runs on the user's "Test engine"
+        # action in Settings.
+        from engines.confucius4.bootstrap import (
+            CONFUCIUS4_SIDECAR_SCRIPT,
+            is_confucius4_installed,
+        )
+        if not is_confucius4_installed():
+            return False, (
+                "Confucius4-TTS venv not found. Set OMNIVOICE_CONFUCIUS4_TTS_DIR "
+                "to your Confucius4-TTS clone (the directory containing "
+                "requirements.txt) and restart OmniVoice. CUDA GPU recommended "
+                "(CPU works but is slow). See docs/engines/confucius4-tts.md."
+            )
+        if not CONFUCIUS4_SIDECAR_SCRIPT.exists():
+            return False, (
+                "Confucius4-TTS sidecar script missing at "
+                f"{CONFUCIUS4_SIDECAR_SCRIPT} — reinstall OmniVoice."
+            )
+        return True, "ok"
+
+    @classmethod
+    def venv_python(cls):
+        from engines.confucius4.bootstrap import resolve_confucius4_venv
+        return resolve_confucius4_venv()
+
+    @classmethod
+    def sidecar_script(cls):
+        from engines.confucius4.bootstrap import CONFUCIUS4_SIDECAR_SCRIPT
+        return CONFUCIUS4_SIDECAR_SCRIPT
+
+    @property
+    def sample_rate(self) -> int:
+        return self._DEFAULT_SAMPLE_RATE
+
+    @property
+    def supported_languages(self) -> list[str]:
+        # 14 languages with the caller's language passed through at synthesize
+        # time; "multi" on the protocol surface.
+        return ["multi"]
+
+    def generate(self, text: str, **kw) -> "torch.Tensor":
+        """Synthesize one utterance through the Confucius4 sidecar.
+
+        kwargs honored:
+          * ``ref_audio`` — reference clip path → ``prompt_wav`` (zero-shot
+            cloning). Optional but recommended for a specific voice.
+          * ``language`` — ISO code / name → ``lang`` (cross-lingual transfer).
+          * ``ref_text`` is intentionally ignored — Confucius4 is unconstrained
+            cloning (no reference transcript needed).
+
+        Returns a tensor of shape (1, n_samples) at :attr:`sample_rate`.
+        """
+        forwarded: dict = {}
+        ref_audio = kw.get("ref_audio")
+        if ref_audio:
+            forwarded["ref_audio"] = ref_audio
+        language = kw.get("language")
+        if language:
+            forwarded["language"] = str(language)
+        return super().generate(text, **forwarded)
+
+
+__all__ = ["Confucius4Backend"]

backend/engines/confucius4/bootstrap.py

@@ -0,0 +1,217 @@
+"""Confucius4-TTS venv probe + lazy bootstrap (issue #590).
+
+Confucius4-TTS (netease-youdao) is an LLM-based multilingual zero-shot cloning
+TTS — 14 languages, no reference transcript required, Apache-2.0. Like the other
+heavyweight opt-in engines (IndexTTS / MOSS-TTS-v1.5 / dots.tts) it runs in its
+**own subprocess venv**: upstream targets Python 3.10 + CUDA 12.6 with its own
+dependency set, which we keep off the parent interpreter.
+
+Probe order (existing power-user installs win — zero migration):
+
+    1. ``${OMNIVOICE_CONFUCIUS4_TTS_DIR}/.venv/`` — the user's clone-level venv.
+    2. ``backend/engines/confucius4/.venv/`` — this package's own venv.
+    3. Bootstrap: ``uv venv`` then ``uv pip install -r <clone>/requirements.txt``
+       (+ ``uv pip install -e <clone>`` only if upstream ever ships packaging).
+
+Validated end-to-end 2026-07-02 (Apple Silicon, CPU): upstream ships **no
+pyproject.toml/setup.py**, so ``confuciustts`` is importable only with the
+clone root on ``sys.path`` — the import probe and the sidecar both handle
+that. The engine is opt-in (env-dir gated) and never touched unless
+``OMNIVOICE_CONFUCIUS4_TTS_DIR`` is set, so this can't affect the default
+install on any platform.
+"""
+from __future__ import annotations
+
+import logging
+import os
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+from typing import Optional
+
+logger = logging.getLogger("omnivoice.confucius4.bootstrap")
+
+#: Absolute path to the sidecar entrypoint.
+CONFUCIUS4_SIDECAR_SCRIPT: Path = Path(__file__).parent / "main.py"
+
+#: This package's owned venv (Probe 2).
+_ENGINES_VENV_DIR: Path = Path(__file__).parent / ".venv"
+
+#: Env var pointing at the user's Confucius4-TTS clone root.
+_CLONE_DIR_ENV: str = "OMNIVOICE_CONFUCIUS4_TTS_DIR"
+
+#: The package importable from the clone (verify against upstream).
+_IMPORT_PROBE = "confuciustts"
+
+_resolved_python: Optional[Path] = None
+
+_IMPORT_PROBE_TIMEOUT_S = 15
+_UV_VENV_TIMEOUT_S = 120
+_UV_PIP_INSTALL_TIMEOUT_S = 1800
+
+
+def invalidate() -> None:
+    """Clear the resolved-python cache. Tests call this between scenarios."""
+    global _resolved_python
+    _resolved_python = None
+
+
+def is_confucius4_installed() -> bool:
+    """Cheap file-existence check for a usable venv (no subprocess spawn)."""
+    return any(cand.is_file() for cand in _probe_paths())
+
+
+def resolve_confucius4_venv() -> Path:
+    """Resolve the sidecar's Python interpreter (probe order in the docstring).
+    Memoised. Raises :exc:`RuntimeError` if none can be located and bootstrap
+    is unavailable."""
+    global _resolved_python
+    if _resolved_python is not None:
+        return _resolved_python
+
+    clone_dir = os.environ.get(_CLONE_DIR_ENV)
+
+    if clone_dir:
+        cand = _venv_python_path(Path(clone_dir) / ".venv")
+        if cand.is_file() and _venv_can_import(cand):
+            logger.info("Confucius4 venv resolved from %s: %s", _CLONE_DIR_ENV, cand)
+            _resolved_python = cand
+            return cand
+
+    cand = _venv_python_path(_ENGINES_VENV_DIR)
+    if cand.is_file() and _venv_can_import(cand):
+        logger.info("Confucius4 venv resolved from engines path: %s", cand)
+        _resolved_python = cand
+        return cand
+
+    if not clone_dir:
+        raise RuntimeError(
+            "Confucius4-TTS is not installed. Set the "
+            f"{_CLONE_DIR_ENV} environment variable to your Confucius4-TTS clone "
+            "(the directory that contains requirements.txt), then restart "
+            "OmniVoice. See docs/engines/confucius4-tts.md."
+        )
+
+    cand = _bootstrap_engines_venv(Path(clone_dir))
+    _resolved_python = cand
+    return cand
+
+
+def _venv_python_path(venv_dir: Path) -> Path:
+    if sys.platform == "win32":
+        return venv_dir / "Scripts" / "python.exe"
+    return venv_dir / "bin" / "python"
+
+
+def _probe_paths() -> list[Path]:
+    out: list[Path] = []
+    clone_dir = os.environ.get(_CLONE_DIR_ENV)
+    if clone_dir:
+        out.append(_venv_python_path(Path(clone_dir) / ".venv"))
+    out.append(_venv_python_path(_ENGINES_VENV_DIR))
+    return out
+
+
+def _import_probe_code() -> str:
+    """Probe snippet mirroring the sidecar's import semantics: upstream is not
+    pip-installable, so ``confuciustts`` resolves via the clone on sys.path."""
+    clone = os.environ.get(_CLONE_DIR_ENV, "")
+    if clone:
+        return f"import sys; sys.path.insert(0, {clone!r}); import {_IMPORT_PROBE}"
+    return f"import {_IMPORT_PROBE}"
+
+
+def _venv_can_import(python_path: Path) -> bool:
+    """Spawn the candidate python and verify ``import confuciustts`` works."""
+    try:
+        proc = subprocess.run(
+            [str(python_path), "-c", _import_probe_code()],
+            capture_output=True, timeout=_IMPORT_PROBE_TIMEOUT_S,
+        )
+    except (subprocess.TimeoutExpired, OSError) as exc:
+        logger.debug("Confucius4 import probe failed for %s: %s", python_path, exc)
+        return False
+    if proc.returncode != 0:
+        logger.debug(
+            "Confucius4 import probe non-zero for %s: %s",
+            python_path, proc.stderr.decode("utf-8", errors="replace")[:200],
+        )
+        return False
+    return True
+
+
+def _locate_uv() -> Optional[str]:
+    bundled = os.environ.get("OMNIVOICE_BUNDLED_UV")
+    if bundled and Path(bundled).is_file():
+        return bundled
+    return shutil.which("uv")
+
+
+def _bootstrap_engines_venv(clone_dir: Path) -> Path:
+    """Create engines/confucius4/.venv and install the user's clone."""
+    uv = _locate_uv()
+    if not uv:
+        raise RuntimeError(
+            "uv is required to bootstrap the Confucius4-TTS venv but was not "
+            "found on PATH (and OMNIVOICE_BUNDLED_UV was not set). Install uv "
+            "from https://docs.astral.sh/uv/ and re-launch OmniVoice."
+        )
+
+    logger.info(
+        "Bootstrapping Confucius4 venv at %s from %s (several minutes on first "
+        "launch)", _ENGINES_VENV_DIR, clone_dir,
+    )
+    try:
+        subprocess.run(
+            [uv, "venv", "--python", "3.10", str(_ENGINES_VENV_DIR)],
+            check=True, timeout=_UV_VENV_TIMEOUT_S, capture_output=True,
+        )
+    except subprocess.CalledProcessError as exc:
+        raise RuntimeError(
+            f"uv venv failed for Confucius4 bootstrap at {_ENGINES_VENV_DIR}: "
+            f"{exc.stderr.decode('utf-8', errors='replace') if exc.stderr else exc}"
+        ) from exc
+
+    python_path = _venv_python_path(_ENGINES_VENV_DIR)
+    requirements = clone_dir / "requirements.txt"
+    try:
+        if requirements.is_file():
+            subprocess.run(
+                [uv, "pip", "install", "--python", str(python_path),
+                 "-r", str(requirements)],
+                check=True, timeout=_UV_PIP_INSTALL_TIMEOUT_S, capture_output=True,
+            )
+        # Editable install only if upstream ever ships packaging metadata —
+        # as of 2026-07 there is none, and `uv pip install -e` on a bare clone
+        # fails outright. Import resolution is handled via sys.path instead.
+        if (clone_dir / "pyproject.toml").is_file() or (clone_dir / "setup.py").is_file():
+            subprocess.run(
+                [uv, "pip", "install", "--python", str(python_path), "-e", str(clone_dir)],
+                check=True, timeout=_UV_PIP_INSTALL_TIMEOUT_S, capture_output=True,
+            )
+    except subprocess.CalledProcessError as exc:
+        raise RuntimeError(
+            "uv pip install failed during Confucius4 bootstrap "
+            f"({clone_dir}): "
+            f"{exc.stderr.decode('utf-8', errors='replace') if exc.stderr else exc}. "
+            "See docs/engines/confucius4-tts.md."
+        ) from exc
+
+    if not _venv_can_import(python_path):
+        raise RuntimeError(
+            f"Confucius4 bootstrap completed but `import {_IMPORT_PROBE}` still "
+            f"fails from {python_path}. Verify {clone_dir} is a valid clone. "
+            "See docs/engines/confucius4-tts.md."
+        )
+
+    logger.info("Confucius4 venv bootstrap successful: %s", python_path)
+    return python_path
+
+
+__all__ = [
+    "CONFUCIUS4_SIDECAR_SCRIPT",
+    "invalidate",
+    "is_confucius4_installed",
+    "resolve_confucius4_venv",
+]

backend/engines/confucius4/main.py

@@ -0,0 +1,216 @@
+"""Confucius4-TTS sidecar entry point (issue #590).
+
+Runs inside ``engines/confucius4/.venv`` (or the user's
+``${OMNIVOICE_CONFUCIUS4_TTS_DIR}/.venv``), isolated from the OmniVoice parent.
+Same isolation rationale as the IndexTTS / MOSS-TTS-v1.5 / dots.tts sidecars.
+
+Stdlib-only at import time; ``confuciustts`` + torch are imported lazily on the
+first synthesize op so the ``ready`` frame fits inside the parent's 30 s spawn
+handshake.
+
+Wire protocol — length-prefixed JSON over stdin/stdout, byte-identical to
+``backend/services/subprocess_backend.py``::
+
+    [ 4-byte big-endian uint32 length ][ N bytes UTF-8 JSON ]
+
+Op flow: ready → ping/pong → synthesize (→ progress, → audio) → shutdown.
+
+Status (#590): the model API below
+(``confuciustts.cli.inference.ConfuciusTTS(config_path=…, device=…)`` and
+``model.generate(text=, lang=, prompt_wav=)`` → audio tensor, ``model.sample_rate``)
+is **validated end-to-end** (2026-07-02, Apple Silicon, CPU): live generate()
+produced audible speech at 22 050 Hz. This sidecar's pure logic is unit-tested
+in ``tests/test_confucius4_sidecar.py``. Opt-in, so it affects no one until
+enabled.
+
+Restrictions: NO imports from OmniVoice parent code. NO logging of os.environ.
+"""
+from __future__ import annotations
+
+import base64
+import json
+import os
+import struct
+import sys
+import traceback
+
+MAX_FRAME_BYTES = 64 * 1024 * 1024
+
+#: Upstream BigVGAN vocoder rate — ``target_sample_rate: 22050`` in
+#: ``config/inference_config.yaml``, confirmed by a live end-to-end run
+#: (2026-07-02). The real value is still re-read from ``model.sample_rate``
+#: on each generate() so a future upstream change can't corrupt audio.
+CONFUCIUS_SAMPLE_RATE = 22050
+
+
+def _send(stream, obj: dict) -> None:
+    body = json.dumps(obj, separators=(",", ":")).encode("utf-8")
+    stream.write(struct.pack("!I", len(body)))
+    stream.write(body)
+    stream.flush()
+
+
+def _recv(stream):
+    header = stream.read(4)
+    if len(header) < 4:
+        return None  # EOF
+    (n,) = struct.unpack("!I", header)
+    if n > MAX_FRAME_BYTES:
+        raise IOError(f"frame too large: {n}")
+    body = bytearray()
+    while len(body) < n:
+        chunk = stream.read(n - len(body))
+        if not chunk:
+            raise IOError("short read")
+        body.extend(chunk)
+    return json.loads(bytes(body).decode("utf-8"))
+
+
+def _measure_vram_mb() -> float:
+    try:
+        import torch
+        if torch.cuda.is_available():
+            return round(torch.cuda.memory_allocated() / (1024 ** 2), 1)
+    except Exception:
+        pass
+    return 0.0
+
+
+_model = None
+
+
+def _config_path() -> str:
+    """Locate Confucius4's inference config (``config/inference_config.yaml``)
+    under the clone, or an explicit override."""
+    explicit = os.environ.get("OMNIVOICE_CONFUCIUS4_CONFIG")
+    if explicit:
+        return explicit
+    clone = os.environ.get("OMNIVOICE_CONFUCIUS4_TTS_DIR", "")
+    return os.path.join(clone, "config", "inference_config.yaml")
+
+
+def _ensure_clone_on_sys_path() -> None:
+    """Make ``import confuciustts`` resolve from the user's clone.
+
+    Upstream Confucius4-TTS is **not pip-installable** (no pyproject.toml /
+    setup.py as of 2026-07); its own ``example.py`` sys.path-inserts the repo
+    root instead. Mirror that here so the sidecar works from a plain
+    ``uv pip install -r requirements.txt`` venv. Inserted at position 0 so the
+    clone the user pointed at always wins over any stale installed copy.
+    """
+    clone = os.environ.get("OMNIVOICE_CONFUCIUS4_TTS_DIR", "")
+    if clone and clone not in sys.path:
+        sys.path.insert(0, clone)
+
+
+def _load_model(stdout):
+    """Cold-construct the Confucius4 model (CUDA, else CPU — both validated)."""
+    global _model
+    if _model is not None:
+        return _model
+
+    _send(stdout, {"op": "progress", "stage": "loading_model", "percent": 0})
+
+    _ensure_clone_on_sys_path()
+    import torch
+    from confuciustts.cli.inference import ConfuciusTTS  # type: ignore[import-not-found]
+
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    _send(stdout, {"op": "progress", "stage": "loading_model", "percent": 50})
+
+    _model = ConfuciusTTS(config_path=_config_path(), device=device)
+
+    _send(stdout, {"op": "progress", "stage": "loading_model", "percent": 100})
+    return _model
+
+
+def _tensor_to_pcm_b64(audio, sample_rate: int) -> tuple[str, int, int]:
+    import numpy as np
+    arr = audio.detach().to("cpu").float().numpy() if hasattr(audio, "detach") else np.asarray(audio)
+    arr = np.asarray(arr, dtype=np.float32).squeeze()
+    if arr.ndim > 1:
+        arr = arr.mean(axis=0)
+    arr = np.clip(arr, -1.0, 1.0)
+    pcm = (arr * 32767.0).astype(np.int16).tobytes()
+    return base64.b64encode(pcm).decode("ascii"), int(sample_rate), int(arr.shape[0])
+
+
+def _normalize_language(raw):
+    """Confucius4 expects an ISO-ish language code (e.g. 'en', 'zh'). Empty /
+    'auto' → 'en' as a safe default (the API requires a lang)."""
+    if not raw or not isinstance(raw, str):
+        return "en"
+    s = raw.strip().lower()
+    if not s or s == "auto":
+        return "en"
+    return s[:2] if (len(s) >= 2 and s[:2].isalpha()) else s
+
+
+def _handle_synthesize(msg: dict, stdout) -> None:
+    text = msg.get("text")
+    if not text or not isinstance(text, str):
+        raise ValueError("synthesize: missing or non-string 'text'")
+
+    model = _load_model(stdout)
+
+    gen_kwargs: dict = {"text": text, "lang": _normalize_language(msg.get("language"))}
+    ref_audio = msg.get("ref_audio")
+    if ref_audio:
+        gen_kwargs["prompt_wav"] = ref_audio
+
+    audio = model.generate(**gen_kwargs)
+    sample_rate = int(getattr(model, "sample_rate", CONFUCIUS_SAMPLE_RATE))
+
+    pcm_b64, sr, n_samples = _tensor_to_pcm_b64(audio, sample_rate)
+    _send(stdout, {
+        "op": "audio",
+        "audio_pcm_b64": pcm_b64,
+        "sample_rate": sr,
+        "n_samples": n_samples,
+    })
+
+
+def main() -> int:
+    stdin = sys.stdin.buffer
+    stdout = sys.stdout.buffer
+
+    _send(stdout, {
+        "op": "ready",
+        "engine": "confucius4-tts",
+        "sample_rate": CONFUCIUS_SAMPLE_RATE,
+    })
+
+    while True:
+        try:
+            msg = _recv(stdin)
+        except Exception as exc:
+            _send(stdout, {
+                "op": "error", "stage": "recv",
+                "message": f"{type(exc).__name__}: {exc}",
+                "traceback": traceback.format_exc(),
+            })
+            return 1
+        if msg is None:
+            return 0
+
+        op = msg.get("op") if isinstance(msg, dict) else None
+        try:
+            if op == "ping":
+                _send(stdout, {"op": "pong", "vram_mb": _measure_vram_mb()})
+            elif op == "synthesize":
+                _handle_synthesize(msg, stdout)
+            elif op == "shutdown":
+                return 0
+            else:
+                _send(stdout, {"op": "error", "stage": "dispatch",
+                               "message": f"unknown op: {op!r}"})
+        except Exception as exc:
+            _send(stdout, {
+                "op": "error", "stage": op or "unknown",
+                "message": f"{type(exc).__name__}: {exc}",
+                "traceback": traceback.format_exc(),
+            })
+
+
+if __name__ == "__main__":
+    sys.exit(main())

backend/engines/dots_tts/__init__.py

@@ -0,0 +1,187 @@
+"""dots.tts sidecar package (issue #498).
+
+dots.tts is rednote-hilab's 2B fully-continuous autoregressive TTS — widely
+cited as among the strongest open zero-shot voice-cloning models. 24
+languages, 48 kHz output, Apache-2.0 (code + checkpoints).
+
+It runs in its own subprocess **and its own venv**, isolated from the
+OmniVoice parent, for the same ``transformers`` reason as IndexTTS and
+MOSS-TTS-v1.5: dots.tts pins ``transformers==4.57.0`` (verified against
+``constraints/recommended.txt``), while OmniVoice pins
+``transformers>=5.3.0``. The two cannot share one interpreter.
+
+Cross-platform honesty (the strict default-parity rule): dots.tts's
+upstream package declares **Linux + macOS** classifiers only — **no
+Windows** — and its device code is **CUDA-or-CPU with no MPS branch**
+(verified in ``runtime.py``). So:
+
+  * It is **opt-in** (engine-picker selection + a user-provided clone),
+    never a default — so it never becomes a broken default on any platform.
+  * ``is_available()`` returns ``False`` with a clear reason on **Windows**
+    rather than offering an engine that can't run there. Windows users are
+    pointed at WSL2 / a Linux or macOS host.
+  * ``gpu_compat = ("cuda", "cpu")`` — no MPS claim. On Apple Silicon the
+    upstream package runs on CPU (slow but correct); the faster MLX path is
+    a community port we deliberately don't auto-wire here.
+
+Three public entry points: ``DotsTTSBackend`` (this module), ``main.py``
+(sidecar, runs under dots.tts's ``transformers==4.57`` venv — never imported
+by the parent), and ``bootstrap.py`` (venv probe + lazy bootstrap).
+"""
+from __future__ import annotations
+
+import logging
+import sys
+from typing import TYPE_CHECKING
+
+from services.subprocess_backend import SubprocessBackend
+
+if TYPE_CHECKING:
+    import torch  # noqa: F401
+
+logger = logging.getLogger("omnivoice.dots_tts")
+
+
+class DotsTTSBackend(SubprocessBackend):
+    """dots.tts (rednote-hilab) — 2B, 24 langs, zero-shot clone, CUDA/CPU.
+
+    Runs in a long-lived sidecar over length-prefixed JSON-over-stdio in a
+    dedicated venv (``transformers==4.57.0``). First synthesize cold-loads
+    the ~9 GB checkpoint (bf16 on CUDA); subsequent calls reuse the process.
+
+    Installation (OmniVoice prefers a user's existing ``${DIR}/.venv``)::
+
+        git clone https://github.com/rednote-hilab/dots.tts.git
+        cd dots.tts
+        uv venv && uv pip install -e . -c constraints/recommended.txt
+
+    Set ``OMNIVOICE_DOTS_TTS_DIR`` to the clone root. OmniVoice creates
+    ``backend/engines/dots_tts/.venv`` lazily on first launch if no venv
+    exists yet; the user's existing ``${DIR}/.venv`` is preferred if present.
+
+    Best cloning quality uses the ``dots.tts-soar`` checkpoint (the default)
+    and BOTH a reference clip and its exact transcript (continuation
+    cloning). License: Apache-2.0.
+    """
+
+    id = "dots-tts"
+    display_name = (
+        "dots.tts (2B, 24 langs, zero-shot clone, CUDA/CPU, 48 kHz, Apache-2.0)"
+    )
+    supports_voice_design = False  # requires ref audio for timbre cloning
+    # dots.tts emits 48 kHz (verified via checkpoint vocoder.sample_rate).
+    _DEFAULT_SAMPLE_RATE = 48000
+    # CUDA + CPU only; no MPS branch in upstream runtime.py.
+    gpu_compat = ("cuda", "cpu")
+
+    # ── availability ───────────────────────────────────────────────────────
+
+    @classmethod
+    def is_available(cls) -> tuple[bool, str]:
+        # Cross-platform parity: dots.tts upstream is Linux/macOS-only (no
+        # Windows classifier, no Windows install path). Refuse cleanly on
+        # Windows instead of advertising an engine that can't run.
+        if sys.platform == "win32":
+            return False, (
+                "dots.tts is not supported on Windows — upstream targets "
+                "Linux and macOS only. Run OmniVoice under WSL2, or use a "
+                "Linux/macOS host. See docs/engines/dots-tts.md."
+            )
+
+        # Do NOT import dots_tts here: it pins transformers==4.57, which can't
+        # coexist with the parent's transformers>=5.3 in one interpreter —
+        # the reason for the subprocess isolation. Verify the venv on disk
+        # only; a real health-check is gated on the user's "Test engine"
+        # action in Settings.
+        from engines.dots_tts.bootstrap import (
+            DOTS_TTS_SIDECAR_SCRIPT,
+            is_dots_tts_installed,
+        )
+        if not is_dots_tts_installed():
+            return False, (
+                "dots.tts venv not found. Set OMNIVOICE_DOTS_TTS_DIR to your "
+                "dots.tts clone (the directory containing pyproject.toml) and "
+                "restart OmniVoice. CUDA or CPU only (no MPS). See "
+                "docs/engines/dots-tts.md for the full install walk-through."
+            )
+        if not DOTS_TTS_SIDECAR_SCRIPT.exists():
+            return False, (
+                "dots.tts sidecar script missing at "
+                f"{DOTS_TTS_SIDECAR_SCRIPT} — reinstall OmniVoice."
+            )
+        return True, "ok (CUDA when present, else CPU)"
+
+    @classmethod
+    def venv_python(cls):
+        from engines.dots_tts.bootstrap import resolve_dots_tts_venv
+        return resolve_dots_tts_venv()
+
+    @classmethod
+    def sidecar_script(cls):
+        from engines.dots_tts.bootstrap import DOTS_TTS_SIDECAR_SCRIPT
+        return DOTS_TTS_SIDECAR_SCRIPT
+
+    # ── TTSBackend protocol ────────────────────────────────────────────────
+
+    @property
+    def sample_rate(self) -> int:
+        return self._DEFAULT_SAMPLE_RATE
+
+    @property
+    def supported_languages(self) -> list[str]:
+        # 24 languages with auto-detect; expose "multi" on the protocol
+        # surface and translate the caller's language at synthesize time.
+        return ["multi"]
+
+    # ── generate (parent-side arbitration) ─────────────────────────────────
+
+    def generate(self, text: str, **kw) -> "torch.Tensor":
+        """Synthesize one utterance through the dots.tts sidecar.
+
+        kwargs honored:
+          * ``ref_audio`` — reference clip path → ``prompt_audio_path``
+                            (zero-shot cloning). Optional.
+          * ``ref_text``  — the reference transcript → ``prompt_text``.
+                            Best cloning fidelity ("continuation"). Upstream
+                            REQUIRES ``prompt_audio_path`` when ``prompt_text``
+                            is set, so we drop a stray ref_text with no
+                            ref_audio rather than let the sidecar raise.
+          * ``language``  — ISO code / name / None (auto-detect).
+          * ``num_step``  — flow-matching steps → ``num_steps`` (default 10;
+                            use 4 for the ``dots.tts-mf`` checkpoint).
+          * ``guidance_scale`` — CFG (default 1.2; >2 amplifies energy).
+
+        Returns a tensor of shape (1, n_samples) at :attr:`sample_rate`.
+        """
+        forwarded: dict = {}
+
+        ref_audio = kw.get("ref_audio")
+        if ref_audio:
+            forwarded["ref_audio"] = ref_audio
+            ref_text = kw.get("ref_text")
+            if ref_text:
+                # continuation cloning — only valid alongside ref_audio.
+                forwarded["ref_text"] = ref_text
+        elif kw.get("ref_text"):
+            logger.info(
+                "dots-tts: ref_text supplied without ref_audio; ignoring "
+                "(upstream requires prompt_audio_path when prompt_text is set)."
+            )
+
+        language = kw.get("language")
+        if language:
+            forwarded["language"] = str(language)
+
+        # OmniVoice's generic num_step default is 16; dots.tts's own default
+        # is 10. Honor an explicit value, else use the dots-appropriate 10.
+        num_step = kw.get("num_step")
+        forwarded["num_steps"] = int(num_step) if num_step is not None else 10
+
+        # dots.tts's own CFG default is 1.2 (the generic 2.0 over-energises).
+        guidance = kw.get("guidance_scale")
+        forwarded["guidance_scale"] = float(guidance) if guidance is not None else 1.2
+
+        return super().generate(text, **forwarded)
+
+
+__all__ = ["DotsTTSBackend"]

backend/engines/dots_tts/bootstrap.py

@@ -0,0 +1,226 @@
+"""dots.tts venv probe + lazy bootstrap (issue #498).
+
+Resolves which Python interpreter runs the dots.tts sidecar. Mirrors
+``engines.indextts.bootstrap`` / ``engines.moss_tts_v15.bootstrap`` because
+dots.tts has the same shape of problem: a hard ``transformers==4.57.0`` pin
+that conflicts with the parent's ``transformers>=5.3`` — so it runs in its
+own venv.
+
+Probe order (priority — existing power-user installs win, zero migration):
+
+    1. ``${OMNIVOICE_DOTS_TTS_DIR}/.venv/`` — the user's clone-level venv.
+    2. ``backend/engines/dots_tts/.venv/`` — this package's own venv.
+    3. Bootstrap: ``uv venv`` then ``uv pip install -e <clone> -c
+       <clone>/constraints/recommended.txt`` (the upstream-pinned stack:
+       torch==2.8.0, transformers==4.57.0, …).
+
+Caching: memoised after first success. Tests reset via :func:`invalidate`.
+
+Security: same posture as IndexTTS — bootstrap never touches HF_TOKEN; the
+sidecar's stderr is redacted by the parent's ``HFTokenRedactor``; the
+editable install comes from a user-controlled clone they already trust.
+"""
+from __future__ import annotations
+
+import logging
+import os
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+from typing import Optional
+
+logger = logging.getLogger("omnivoice.dots_tts.bootstrap")
+
+#: Absolute path to the sidecar entrypoint.
+DOTS_TTS_SIDECAR_SCRIPT: Path = Path(__file__).parent / "main.py"
+
+#: This package's owned venv (Probe 2).
+_ENGINES_VENV_DIR: Path = Path(__file__).parent / ".venv"
+
+#: Env var pointing at the user's dots.tts clone root.
+_CLONE_DIR_ENV: str = "OMNIVOICE_DOTS_TTS_DIR"
+
+#: Per-process resolution cache. Cleared by :func:`invalidate` for tests.
+_resolved_python: Optional[Path] = None
+
+_IMPORT_PROBE_TIMEOUT_S = 15
+_UV_VENV_TIMEOUT_S = 120
+_UV_PIP_INSTALL_TIMEOUT_S = 1800
+
+
+# ── public API ────────────────────────────────────────────────────────────
+
+
+def invalidate() -> None:
+    """Clear the resolved-python cache. Tests call this between scenarios."""
+    global _resolved_python
+    _resolved_python = None
+
+
+def is_dots_tts_installed() -> bool:
+    """Cheap file-existence check for a usable dots.tts venv. Does NOT spawn
+    the venv Python — that's saved for :func:`resolve_dots_tts_venv`."""
+    for cand in _probe_paths():
+        if cand.is_file():
+            return True
+    return False
+
+
+def resolve_dots_tts_venv() -> Path:
+    """Resolve the sidecar's Python interpreter (probe order in the module
+    docstring). Memoised. Raises :exc:`RuntimeError` if none can be located
+    and the bootstrap path is unavailable."""
+    global _resolved_python
+    if _resolved_python is not None:
+        return _resolved_python
+
+    clone_dir = os.environ.get(_CLONE_DIR_ENV)
+
+    # Probe 1 — user's clone-level venv.
+    if clone_dir:
+        cand = _venv_python_path(Path(clone_dir) / ".venv")
+        if cand.is_file() and _venv_can_import_dots(cand):
+            logger.info(
+                "dots.tts venv resolved from %s: %s", _CLONE_DIR_ENV, cand,
+            )
+            _resolved_python = cand
+            return cand
+
+    # Probe 2 — this package's own venv.
+    cand = _venv_python_path(_ENGINES_VENV_DIR)
+    if cand.is_file() and _venv_can_import_dots(cand):
+        logger.info("dots.tts venv resolved from engines path: %s", cand)
+        _resolved_python = cand
+        return cand
+
+    # Probe 3 — bootstrap.
+    if not clone_dir:
+        raise RuntimeError(
+            "dots.tts is not installed. Set the "
+            f"{_CLONE_DIR_ENV} environment variable to your dots.tts clone "
+            "(the directory that contains pyproject.toml and constraints/), "
+            "then restart OmniVoice. See docs/engines/dots-tts.md for the "
+            "full install walk-through."
+        )
+
+    cand = _bootstrap_engines_venv(Path(clone_dir))
+    _resolved_python = cand
+    return cand
+
+
+# ── internals ─────────────────────────────────────────────────────────────
+
+
+def _venv_python_path(venv_dir: Path) -> Path:
+    if sys.platform == "win32":
+        return venv_dir / "Scripts" / "python.exe"
+    return venv_dir / "bin" / "python"
+
+
+def _probe_paths() -> list[Path]:
+    out: list[Path] = []
+    clone_dir = os.environ.get(_CLONE_DIR_ENV)
+    if clone_dir:
+        out.append(_venv_python_path(Path(clone_dir) / ".venv"))
+    out.append(_venv_python_path(_ENGINES_VENV_DIR))
+    return out
+
+
+def _venv_can_import_dots(python_path: Path) -> bool:
+    """Spawn the candidate python and verify ``import dots_tts.runtime`` works.
+    Bounded by ``_IMPORT_PROBE_TIMEOUT_S``. False on any failure."""
+    try:
+        proc = subprocess.run(
+            [str(python_path), "-c", "import dots_tts.runtime"],
+            capture_output=True,
+            timeout=_IMPORT_PROBE_TIMEOUT_S,
+        )
+    except (subprocess.TimeoutExpired, OSError) as exc:
+        logger.debug("dots.tts import probe failed for %s: %s", python_path, exc)
+        return False
+    if proc.returncode != 0:
+        logger.debug(
+            "dots.tts import probe non-zero for %s: %s",
+            python_path,
+            proc.stderr.decode("utf-8", errors="replace")[:200],
+        )
+        return False
+    return True
+
+
+def _locate_uv() -> Optional[str]:
+    bundled = os.environ.get("OMNIVOICE_BUNDLED_UV")
+    if bundled and Path(bundled).is_file():
+        return bundled
+    return shutil.which("uv")
+
+
+def _bootstrap_engines_venv(clone_dir: Path) -> Path:
+    """Create engines/dots_tts/.venv and editable-install the user's clone
+    with the upstream constraints file."""
+    uv = _locate_uv()
+    if not uv:
+        raise RuntimeError(
+            "uv is required to bootstrap the dots.tts venv but was not found "
+            "on PATH (and OMNIVOICE_BUNDLED_UV was not set). Install uv from "
+            "https://docs.astral.sh/uv/ and re-launch OmniVoice, or set "
+            "OMNIVOICE_BUNDLED_UV to the absolute path of a uv binary."
+        )
+
+    logger.info(
+        "Bootstrapping dots.tts venv at %s from %s (this can take several "
+        "minutes on first launch)", _ENGINES_VENV_DIR, clone_dir,
+    )
+
+    try:
+        subprocess.run(
+            [uv, "venv", str(_ENGINES_VENV_DIR)],
+            check=True, timeout=_UV_VENV_TIMEOUT_S, capture_output=True,
+        )
+    except subprocess.CalledProcessError as exc:
+        raise RuntimeError(
+            f"uv venv failed for dots.tts bootstrap at {_ENGINES_VENV_DIR}: "
+            f"{exc.stderr.decode('utf-8', errors='replace') if exc.stderr else exc}"
+        ) from exc
+
+    python_path = _venv_python_path(_ENGINES_VENV_DIR)
+    install_cmd = [
+        uv, "pip", "install",
+        "--python", str(python_path),
+        "-e", str(clone_dir),
+    ]
+    # Apply the upstream pin set when it ships with the clone.
+    constraints = clone_dir / "constraints" / "recommended.txt"
+    if constraints.is_file():
+        install_cmd += ["-c", str(constraints)]
+    try:
+        subprocess.run(
+            install_cmd, check=True,
+            timeout=_UV_PIP_INSTALL_TIMEOUT_S, capture_output=True,
+        )
+    except subprocess.CalledProcessError as exc:
+        raise RuntimeError(
+            "uv pip install -e failed during dots.tts bootstrap "
+            f"({clone_dir}): "
+            f"{exc.stderr.decode('utf-8', errors='replace') if exc.stderr else exc}. "
+            "See docs/engines/dots-tts.md."
+        ) from exc
+
+    if not _venv_can_import_dots(python_path):
+        raise RuntimeError(
+            "dots.tts bootstrap completed but `import dots_tts.runtime` still "
+            f"fails from {python_path}. Verify that {clone_dir} is a valid "
+            "dots.tts clone. See docs/engines/dots-tts.md."
+        )
+
+    logger.info("dots.tts venv bootstrap successful: %s", python_path)
+    return python_path
+
+
+__all__ = [
+    "DOTS_TTS_SIDECAR_SCRIPT",
+    "invalidate",
+    "is_dots_tts_installed",
+    "resolve_dots_tts_venv",
+]

backend/engines/dots_tts/main.py

@@ -0,0 +1,255 @@
+"""dots.tts sidecar entry point (issue #498).
+
+Runs inside ``engines/dots_tts/.venv`` (or the user's existing
+``${OMNIVOICE_DOTS_TTS_DIR}/.venv``) with ``transformers==4.57.0``, isolated
+from the OmniVoice parent (``transformers>=5.3``). Same isolation rationale
+as the IndexTTS / MOSS-TTS-v1.5 sidecars.
+
+Stdlib-only at import time; ``dots_tts`` + torch are imported lazily on the
+first synthesize op so the ``ready`` frame fits inside the parent's 30 s
+spawn handshake even on a cold filesystem.
+
+Wire protocol — length-prefixed JSON over stdin/stdout, byte-identical to
+``backend/services/subprocess_backend.py``::
+
+    [ 4-byte big-endian uint32 length ][ N bytes UTF-8 JSON ]
+
+Op flow:
+    1. Sidecar -> parent: {"op": "ready", "engine": "dots-tts",
+                           "sample_rate": 48000}
+    2. parent -> sidecar: {"op": "ping"} -> {"op": "pong", "vram_mb": N}
+    3. parent -> sidecar: {"op": "synthesize", "text": "...",
+                            "ref_audio": "/path/ref.wav",
+                            "ref_text": "transcript", "language": "EN",
+                            "num_steps": 10, "guidance_scale": 1.2}
+       -> {"op": "progress", ...} (cold load) then
+       -> {"op": "audio", "audio_pcm_b64": "...", "sample_rate": 48000,
+           "n_samples": N}
+    4. parent -> sidecar: {"op": "shutdown"} -> exit 0
+
+Restrictions: NO imports from OmniVoice parent code (different venv). NO
+logging of ``os.environ`` contents. Single-frame DoS cap matches the
+parent's ``MAX_FRAME_BYTES``.
+"""
+from __future__ import annotations
+
+import base64
+import json
+import os
+import struct
+import sys
+import traceback
+
+
+# Mirrors backend/services/subprocess_backend.py::MAX_FRAME_BYTES.
+MAX_FRAME_BYTES = 64 * 1024 * 1024
+
+#: dots.tts emits 48 kHz (checkpoint vocoder.sample_rate). Advertised in the
+#: ready frame; the real value is re-read from each generate() result.
+DOTS_SAMPLE_RATE = 48000
+
+#: Default checkpoint. ``-soar`` is the best-cloning variant; ``-mf`` is the
+#: fastest (use num_steps=4). Overridable for air-gapped / mirror installs.
+_DEFAULT_REPO = "rednote-hilab/dots.tts-soar"
+
+
+# ── wire protocol ─────────────────────────────────────────────────────────
+
+
+def _send(stream, obj: dict) -> None:
+    body = json.dumps(obj, separators=(",", ":")).encode("utf-8")
+    stream.write(struct.pack("!I", len(body)))
+    stream.write(body)
+    stream.flush()
+
+
+def _recv(stream):
+    header = stream.read(4)
+    if len(header) < 4:
+        return None  # EOF
+    (n,) = struct.unpack("!I", header)
+    if n > MAX_FRAME_BYTES:
+        raise IOError(f"frame too large: {n}")
+    body = bytearray()
+    while len(body) < n:
+        chunk = stream.read(n - len(body))
+        if not chunk:
+            raise IOError("short read")
+        body.extend(chunk)
+    return json.loads(bytes(body).decode("utf-8"))
+
+
+def _measure_vram_mb() -> float:
+    """This sidecar's own GPU memory in MB (MM2-08). 0 on CPU. Never raises."""
+    try:
+        import torch
+        if torch.cuda.is_available():
+            return round(torch.cuda.memory_allocated() / (1024 ** 2), 1)
+    except Exception:
+        pass
+    return 0.0
+
+
+# ── model loading (lazy, on first synthesize) ─────────────────────────────
+
+
+# Module-level singleton — (runtime,). Device is auto-selected inside the
+# dots.tts runtime (cuda-or-cpu, no MPS); we don't pass a device.
+_runtime = None
+
+
+def _load_runtime(stdout):
+    """Cold-construct the dots.tts runtime.
+
+    ``DotsTtsRuntime.from_pretrained`` auto-selects cuda-or-cpu internally
+    (no MPS path). precision is bf16 on CUDA; on CPU we fall back to fp32
+    (bf16 CPU kernels are spotty). Both overridable via env.
+    """
+    global _runtime
+    if _runtime is not None:
+        return _runtime
+
+    _send(stdout, {"op": "progress", "stage": "loading_model", "percent": 0})
+
+    import torch
+    from dots_tts.runtime import DotsTtsRuntime  # type: ignore[import-not-found]
+
+    repo = os.environ.get("OMNIVOICE_DOTS_TTS_MODEL", _DEFAULT_REPO)
+    default_precision = "bfloat16" if torch.cuda.is_available() else "float32"
+    precision = os.environ.get("OMNIVOICE_DOTS_TTS_PRECISION", default_precision)
+    optimize = os.environ.get("OMNIVOICE_DOTS_TTS_OPTIMIZE", "0") == "1"
+
+    _send(stdout, {"op": "progress", "stage": "loading_model", "percent": 50})
+
+    _runtime = DotsTtsRuntime.from_pretrained(
+        repo,
+        precision=precision,
+        optimize=optimize,
+    )
+
+    _send(stdout, {"op": "progress", "stage": "loading_model", "percent": 100})
+    return _runtime
+
+
+def _tensor_to_pcm_b64(audio, sample_rate: int) -> tuple[str, int, int]:
+    """Convert a torch waveform tensor (1, N) in [-1, 1] to base64 int16 PCM."""
+    import numpy as np
+
+    arr = audio.detach().to("cpu").float().numpy()
+    arr = np.asarray(arr, dtype=np.float32).squeeze()
+    if arr.ndim > 1:
+        arr = arr.mean(axis=0)  # defensive downmix to mono
+    arr = np.clip(arr, -1.0, 1.0)
+    pcm = (arr * 32767.0).astype(np.int16).tobytes()
+    return base64.b64encode(pcm).decode("ascii"), int(sample_rate), int(arr.shape[0])
+
+
+def _normalize_language(raw):
+    """Map OmniVoice's language value to what dots.tts accepts, or None.
+
+    dots.tts accepts None/"auto_detect", ISO codes upper-cased ("EN"/"ZH"),
+    or names ("english"). A 2-letter ISO code is upper-cased; anything else
+    is passed through; empty / "auto" → None (auto-detect)."""
+    if not raw or not isinstance(raw, str):
+        return None
+    s = raw.strip()
+    if not s or s.lower() == "auto":
+        return None
+    if len(s) == 2 and s.isalpha():
+        return s.upper()
+    return s
+
+
+def _handle_synthesize(msg: dict, stdout) -> None:
+    """Dispatch one synthesize request. Emits the audio frame or raises."""
+    text = msg.get("text")
+    if not text or not isinstance(text, str):
+        raise ValueError("synthesize: missing or non-string 'text'")
+
+    runtime = _load_runtime(stdout)
+
+    gen_kwargs: dict = {
+        "text": text,
+        "num_steps": int(msg.get("num_steps", 10)),
+        "guidance_scale": float(msg.get("guidance_scale", 1.2)),
+    }
+
+    ref_audio = msg.get("ref_audio")
+    if ref_audio:
+        gen_kwargs["prompt_audio_path"] = ref_audio
+        ref_text = msg.get("ref_text")
+        if ref_text:
+            # continuation cloning — upstream requires prompt_audio_path when
+            # prompt_text is set (the parent already enforces this).
+            gen_kwargs["prompt_text"] = ref_text
+
+    language = _normalize_language(msg.get("language"))
+    if language:
+        gen_kwargs["language"] = language
+
+    result = runtime.generate(**gen_kwargs)
+    audio = result["audio"]
+    sample_rate = int(result.get("sample_rate", DOTS_SAMPLE_RATE))
+
+    pcm_b64, sr, n_samples = _tensor_to_pcm_b64(audio, sample_rate)
+    _send(stdout, {
+        "op": "audio",
+        "audio_pcm_b64": pcm_b64,
+        "sample_rate": sr,
+        "n_samples": n_samples,
+    })
+
+
+# ── main loop ─────────────────────────────────────────────────────────────
+
+
+def main() -> int:
+    stdin = sys.stdin.buffer
+    stdout = sys.stdout.buffer
+
+    # Ready handshake fires BEFORE any heavy import.
+    _send(stdout, {
+        "op": "ready",
+        "engine": "dots-tts",
+        "sample_rate": DOTS_SAMPLE_RATE,
+    })
+
+    while True:
+        try:
+            msg = _recv(stdin)
+        except Exception as exc:
+            _send(stdout, {
+                "op": "error",
+                "stage": "recv",
+                "message": f"{type(exc).__name__}: {exc}",
+                "traceback": traceback.format_exc(),
+            })
+            return 1
+        if msg is None:
+            return 0
+
+        op = msg.get("op") if isinstance(msg, dict) else None
+        try:
+            if op == "ping":
+                _send(stdout, {"op": "pong", "vram_mb": _measure_vram_mb()})
+            elif op == "synthesize":
+                _handle_synthesize(msg, stdout)
+            elif op == "shutdown":
+                return 0
+            else:
+                _send(stdout, {
+                    "op": "error",
+                    "stage": "dispatch",
+                    "message": f"unknown op: {op!r}",
+                })
+        except Exception as exc:
+            _send(stdout, {
+                "op": "error",
+                "stage": op or "unknown",
+                "message": f"{type(exc).__name__}: {exc}",
+                "traceback": traceback.format_exc(),
+            })
+
+
+if __name__ == "__main__":
+    sys.exit(main())

backend/engines/moss_tts_v15/__init__.py

@@ -0,0 +1,194 @@
+"""MOSS-TTS-v1.5 sidecar package (issue #498).
+
+MOSS-TTS-v1.5 is OpenMOSS's 8B flagship TTS — a Qwen3-8B language backbone
+plus a 1.6B audio codec, 31 languages, zero-shot voice cloning, token-level
+duration control and inline ``[pause Ns]`` markers. Apache-2.0.
+
+It runs in its own subprocess **and its own venv**, isolated from the
+OmniVoice parent process, for the *same* reason IndexTTS does: a hard
+``transformers`` version conflict. MOSS-TTS-v1.5's ``torch-runtime`` extra
+pins ``transformers==5.0.0`` (verified against the upstream
+``pyproject.toml``), while OmniVoice pins ``transformers>=5.3.0``. The two
+cannot share one interpreter — so MOSS lives behind ``SubprocessBackend``
+with a dedicated venv, exactly like ``engines.indextts``.
+
+Three public entry points live in this package:
+
+  * ``MossTTSV15Backend`` (this module) — the SubprocessBackend subclass
+    that ``services.tts_backend._LAZY_REGISTRY`` resolves on first access.
+    Defined HERE (not in ``services.tts_backend``) to break the import
+    cycle: ``services.subprocess_backend`` imports ``TTSBackend`` from
+    ``services.tts_backend``, so the backend class must live downstream of
+    that module finishing its import. Same indirection as IndexTTS /
+    Supertonic-3.
+  * ``main.py`` — the sidecar entrypoint (runs under MOSS's venv with
+    ``transformers==5.0.0``; never imported by the parent).
+  * ``bootstrap.py`` — the venv-probe + lazy-bootstrap helper.
+
+Do NOT import ``main.py`` from the parent process — it runs under a
+different venv (``transformers==5.0.0``) and importing it in-process would
+re-introduce the exact conflict this isolation exists to avoid.
+
+Hardware honesty (cross-platform rule): MOSS-TTS-v1.5's upstream documents
+only CUDA and CPU. There is **no documented or tested MPS path** — the
+custom ``trust_remote_code`` modelling code and the separate audio
+tokenizer are unverified on Apple Silicon. We therefore advertise
+``gpu_compat = ("cuda", "cpu")`` and the sidecar selects ``cuda`` when
+present else ``cpu`` — it never silently routes to MPS where it might
+crash. On Apple Silicon the engine honestly resolves to CPU (slow but
+correct), and the engine is opt-in regardless, so it never becomes a
+broken default on any platform.
+"""
+from __future__ import annotations
+
+import logging
+from typing import TYPE_CHECKING
+
+from services.subprocess_backend import SubprocessBackend
+
+if TYPE_CHECKING:
+    import torch  # noqa: F401
+
+logger = logging.getLogger("omnivoice.moss_tts_v15")
+
+#: 1 second of audio ≈ 12.5 codec tokens (MOSS-TTS-v1.5 model card). Used to
+#: translate OmniVoice's ``duration`` (seconds) into the model's ``tokens``
+#: duration-control argument.
+TOKENS_PER_SECOND: float = 12.5
+
+
+class MossTTSV15Backend(SubprocessBackend):
+    """MOSS-TTS-v1.5 (OpenMOSS) — 8B, 31 langs, zero-shot clone, CUDA/CPU.
+
+    Runs in a long-lived sidecar over length-prefixed JSON-over-stdio in a
+    dedicated venv (``transformers==5.0.0``). The first synthesize cold-loads
+    ~16 GB of bf16 weights (CUDA) / fp32 (CPU); subsequent calls reuse the
+    process and the in-memory model.
+
+    Installation (transparent to power users who already cloned MOSS-TTS —
+    OmniVoice prefers their existing ``${DIR}/.venv``)::
+
+        git clone https://github.com/OpenMOSS/MOSS-TTS.git
+        cd MOSS-TTS
+        # CUDA host:
+        uv venv && uv pip install -e ".[torch-runtime]"
+        # non-CUDA host (CPU): install plain torch/transformers instead of +cu128
+
+    Set ``OMNIVOICE_MOSS_TTS_V15_DIR`` to the clone root. OmniVoice creates
+    ``backend/engines/moss_tts_v15/.venv`` lazily on first launch if no venv
+    exists yet (CUDA hosts only — the upstream ``torch-runtime`` extra is
+    ``+cu128``); the user's existing ``${DIR}/.venv`` is preferred if
+    present, so no re-install is needed.
+
+    License: Apache-2.0 (code + weights) — no acceptance gate needed.
+    """
+
+    id = "moss-tts-v15"
+    display_name = (
+        "MOSS-TTS-v1.5 (8B, 31 langs, zero-shot clone, CUDA/CPU, Apache-2.0)"
+    )
+    supports_voice_design = False  # requires ref audio for timbre cloning
+    _DEFAULT_SAMPLE_RATE = 24000
+    # Honest hardware surface: upstream documents CUDA + CPU only. MPS is
+    # undocumented / untested, so we do NOT claim it (cross-platform rule).
+    gpu_compat = ("cuda", "cpu")
+
+    # ── availability ───────────────────────────────────────────────────────
+
+    @classmethod
+    def is_available(cls) -> tuple[bool, str]:
+        # IMPORTANT: do NOT attempt to import MOSS / its transformers==5.0.0
+        # here. The parent pins transformers>=5.3 — co-importing the two in
+        # one interpreter is exactly the conflict this subprocess isolation
+        # exists to avoid. We only verify the venv exists on disk; a real
+        # health-check (spawn + ping) is gated on the user's "Test engine"
+        # action in Settings, same as IndexTTS.
+        from engines.moss_tts_v15.bootstrap import (
+            MOSS_TTS_V15_SIDECAR_SCRIPT,
+            is_moss_tts_v15_installed,
+        )
+        if not is_moss_tts_v15_installed():
+            return False, (
+                "MOSS-TTS-v1.5 venv not found. Set OMNIVOICE_MOSS_TTS_V15_DIR "
+                "to your MOSS-TTS clone (the directory containing pyproject.toml) "
+                "and restart OmniVoice. CUDA or CPU only (no MPS). See "
+                "docs/engines/moss-tts-v15.md for the full install walk-through."
+            )
+        if not MOSS_TTS_V15_SIDECAR_SCRIPT.exists():
+            return False, (
+                "MOSS-TTS-v1.5 sidecar script missing at "
+                f"{MOSS_TTS_V15_SIDECAR_SCRIPT} — reinstall OmniVoice."
+            )
+        return True, "ok (CUDA when present, else CPU)"
+
+    @classmethod
+    def venv_python(cls):
+        from engines.moss_tts_v15.bootstrap import resolve_moss_tts_v15_venv
+        return resolve_moss_tts_v15_venv()
+
+    @classmethod
+    def sidecar_script(cls):
+        from engines.moss_tts_v15.bootstrap import MOSS_TTS_V15_SIDECAR_SCRIPT
+        return MOSS_TTS_V15_SIDECAR_SCRIPT
+
+    # ── TTSBackend protocol ────────────────────────────────────────────────
+
+    @property
+    def sample_rate(self) -> int:
+        return self._DEFAULT_SAMPLE_RATE
+
+    @property
+    def supported_languages(self) -> list[str]:
+        # 31 languages with multilingual handling; expose "multi" on the
+        # protocol surface (same as OmniVoice / CosyVoice / Supertonic-3) and
+        # translate the caller's language at synthesize time.
+        return ["multi"]
+
+    # ── generate (parent-side arbitration) ─────────────────────────────────
+
+    def generate(self, text: str, **kw) -> "torch.Tensor":
+        """Synthesize one utterance through the MOSS-TTS-v1.5 sidecar.
+
+        kwargs honored:
+          * ``ref_audio``  — path to a reference clip. When present, MOSS
+                              runs zero-shot voice cloning (``reference=``).
+                              Optional: without it the model uses its own
+                              default voice.
+          * ``ref_text``   — accepted but unused in clone mode (MOSS's
+                              zero-shot path needs only the audio); kept in
+                              the signature so the common call-site doesn't
+                              need engine-specific knowledge.
+          * ``language``   — ISO code or name; mapped to a MOSS language name
+                              in the sidecar, omitted (auto-detect) if unknown.
+          * ``duration``   — target seconds → ``tokens`` (1 s ≈ 12.5 tokens).
+          * ``max_new_tokens`` — generation cap (default 4096).
+
+        Returns a tensor of shape (1, n_samples) at :attr:`sample_rate`.
+        """
+        forwarded: dict = {}
+
+        ref_audio = kw.get("ref_audio")
+        if ref_audio:
+            forwarded["ref_audio"] = ref_audio
+        ref_text = kw.get("ref_text")
+        if ref_text:
+            forwarded["ref_text"] = ref_text
+
+        language = kw.get("language")
+        if language:
+            forwarded["language"] = str(language)
+
+        duration = kw.get("duration")
+        if duration is not None:
+            target_tokens = int(float(duration) * TOKENS_PER_SECOND)
+            if target_tokens > 0:
+                forwarded["tokens"] = target_tokens
+
+        max_new_tokens = kw.get("max_new_tokens")
+        if max_new_tokens is not None:
+            forwarded["max_new_tokens"] = int(max_new_tokens)
+
+        return super().generate(text, **forwarded)
+
+
+__all__ = ["MossTTSV15Backend", "TOKENS_PER_SECOND"]

backend/engines/moss_tts_v15/bootstrap.py

@@ -0,0 +1,272 @@
+"""MOSS-TTS-v1.5 venv probe + lazy bootstrap (issue #498).
+
+The parent process needs to know *which Python interpreter* to spawn the
+MOSS-TTS-v1.5 sidecar under. This module owns that resolution. It mirrors
+``engines.indextts.bootstrap`` because MOSS has the same shape of problem:
+a hard ``transformers`` pin (``==5.0.0``) that conflicts with the parent's
+``transformers>=5.3`` — so MOSS runs in its own venv.
+
+Probe order (priority — existing power-user installs win, zero migration):
+
+    1. ``${OMNIVOICE_MOSS_TTS_V15_DIR}/.venv/`` — the user's clone-level
+       venv. Highest priority: a user who already cloned MOSS-TTS and ran
+       ``uv pip install -e ".[torch-runtime]"`` (per upstream docs) gets
+       reused verbatim, no re-download of the ~16 GB model.
+    2. ``backend/engines/moss_tts_v15/.venv/`` — this package's own venv,
+       created by step 3 if needed.
+    3. Bootstrap: ``uv venv`` then ``uv pip install -e
+       "${DIR}[torch-runtime]"``. Requires ``OMNIVOICE_MOSS_TTS_V15_DIR``.
+       The upstream ``torch-runtime`` extra is CUDA (``+cu128``), so the
+       auto-bootstrap targets CUDA hosts; non-CUDA (CPU/Mac) users set up
+       their own venv per docs/engines/moss-tts-v15.md (Probe 1).
+
+Caching: resolution is memoised after the first successful call. Tests
+reset via :func:`invalidate`.
+
+Security: bootstrap never touches HF_TOKEN; the sidecar's stderr is drained
+by SubprocessBackend through the parent root logger where Phase 1's
+``HFTokenRedactor`` strips token bytes. ``uv pip install -e`` installs from
+a user-controlled clone the user already trusts (same posture as IndexTTS).
+"""
+from __future__ import annotations
+
+import logging
+import os
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+from typing import Optional
+
+logger = logging.getLogger("omnivoice.moss_tts_v15.bootstrap")
+
+#: Absolute path to the sidecar entrypoint. ``MossTTSV15Backend.sidecar_script``
+#: returns this; SubprocessBackend spawns it with the resolved venv python.
+MOSS_TTS_V15_SIDECAR_SCRIPT: Path = Path(__file__).parent / "main.py"
+
+#: This package's owned venv (Probe 2). The MOSS-TTS clone, when bootstrapped,
+#: is installed into this venv via ``uv pip install -e``.
+_ENGINES_VENV_DIR: Path = Path(__file__).parent / ".venv"
+
+#: Env var pointing at the user's MOSS-TTS clone root.
+_CLONE_DIR_ENV: str = "OMNIVOICE_MOSS_TTS_V15_DIR"
+
+#: Per-process resolution cache. Cleared by :func:`invalidate` for tests.
+_resolved_python: Optional[Path] = None
+
+# Timeouts — bounded so a wedged venv never hangs the parent. The bootstrap
+# install can take many minutes on a cold cache (MOSS pulls a CUDA torch
+# build + transformers + an audio codec stack).
+_IMPORT_PROBE_TIMEOUT_S = 15
+_UV_VENV_TIMEOUT_S = 120
+_UV_PIP_INSTALL_TIMEOUT_S = 1800
+
+
+# ── public API ────────────────────────────────────────────────────────────
+
+
+def invalidate() -> None:
+    """Clear the resolved-python cache. Tests call this between scenarios."""
+    global _resolved_python
+    _resolved_python = None
+
+
+def is_moss_tts_v15_installed() -> bool:
+    """Cheap file-existence check for a usable MOSS-TTS-v1.5 venv.
+
+    Returns True if either Probe 1 or Probe 2 has a Python executable on
+    disk. Does NOT spawn the venv Python — that's saved for
+    :func:`resolve_moss_tts_v15_venv`, which is only invoked on the first
+    generate() / health_check(). This fires on every Settings render via
+    ``MossTTSV15Backend.is_available()``, so it stays cheap.
+    """
+    for cand in _probe_paths():
+        if cand.is_file():
+            return True
+    return False
+
+
+def resolve_moss_tts_v15_venv() -> Path:
+    """Resolve the path to the Python interpreter that runs the sidecar.
+
+    Probe order described in the module docstring. Memoised. Raises
+    :exc:`RuntimeError` if no working venv can be located AND the bootstrap
+    path is unavailable.
+    """
+    global _resolved_python
+    if _resolved_python is not None:
+        return _resolved_python
+
+    clone_dir = os.environ.get(_CLONE_DIR_ENV)
+
+    # Probe 1 — user's clone-level venv (highest priority for back-compat).
+    if clone_dir:
+        cand = _venv_python_path(Path(clone_dir) / ".venv")
+        if cand.is_file() and _venv_can_import_moss(cand):
+            logger.info(
+                "MOSS-TTS-v1.5 venv resolved from %s: %s", _CLONE_DIR_ENV, cand,
+            )
+            _resolved_python = cand
+            return cand
+
+    # Probe 2 — this package's own venv.
+    cand = _venv_python_path(_ENGINES_VENV_DIR)
+    if cand.is_file() and _venv_can_import_moss(cand):
+        logger.info("MOSS-TTS-v1.5 venv resolved from engines path: %s", cand)
+        _resolved_python = cand
+        return cand
+
+    # Probe 3 — bootstrap.
+    if not clone_dir:
+        raise RuntimeError(
+            "MOSS-TTS-v1.5 is not installed. Set the "
+            f"{_CLONE_DIR_ENV} environment variable to your MOSS-TTS clone "
+            "(the directory that contains pyproject.toml), then restart "
+            "OmniVoice. See docs/engines/moss-tts-v15.md for the full "
+            "install walk-through."
+        )
+
+    cand = _bootstrap_engines_venv(Path(clone_dir))
+    _resolved_python = cand
+    return cand
+
+
+# ── internals ─────────────────────────────────────────────────────────────
+
+
+def _venv_python_path(venv_dir: Path) -> Path:
+    """Return the python executable path inside a venv directory.
+
+    Handles the Unix (``bin/python``) vs Windows (``Scripts/python.exe``)
+    layout. No filesystem access — caller checks .is_file().
+    """
+    if sys.platform == "win32":
+        return venv_dir / "Scripts" / "python.exe"
+    return venv_dir / "bin" / "python"
+
+
+def _probe_paths() -> list[Path]:
+    """Ordered list of candidate venv-python paths (no .is_file() check)."""
+    out: list[Path] = []
+    clone_dir = os.environ.get(_CLONE_DIR_ENV)
+    if clone_dir:
+        out.append(_venv_python_path(Path(clone_dir) / ".venv"))
+    out.append(_venv_python_path(_ENGINES_VENV_DIR))
+    return out
+
+
+def _venv_can_import_moss(python_path: Path) -> bool:
+    """Spawn the candidate python and verify the MOSS stack imports.
+
+    MOSS-TTS-v1.5 loads via ``transformers`` + ``trust_remote_code`` (no
+    fixed top-level package to import), so the readiness signal is that the
+    venv has a working ``transformers`` + ``torch`` — which only the
+    ``[torch-runtime]`` install provides. Bounded by
+    ``_IMPORT_PROBE_TIMEOUT_S`` so a wedged venv never hangs the parent.
+    Returns False on any failure (non-zero exit, timeout, OSError).
+    """
+    try:
+        proc = subprocess.run(
+            [str(python_path), "-c", "import transformers, torch"],
+            capture_output=True,
+            timeout=_IMPORT_PROBE_TIMEOUT_S,
+        )
+    except (subprocess.TimeoutExpired, OSError) as exc:
+        logger.debug("moss-tts-v15 import probe failed for %s: %s", python_path, exc)
+        return False
+    if proc.returncode != 0:
+        logger.debug(
+            "moss-tts-v15 import probe non-zero for %s: %s",
+            python_path,
+            proc.stderr.decode("utf-8", errors="replace")[:200],
+        )
+        return False
+    return True
+
+
+def _locate_uv() -> Optional[str]:
+    """Find the uv binary — bundled first (Tauri-set env var), else PATH."""
+    bundled = os.environ.get("OMNIVOICE_BUNDLED_UV")
+    if bundled and Path(bundled).is_file():
+        return bundled
+    sys_uv = shutil.which("uv")
+    if sys_uv:
+        return sys_uv
+    return None
+
+
+def _bootstrap_engines_venv(clone_dir: Path) -> Path:
+    """Create engines/moss_tts_v15/.venv and install the user's clone into it.
+
+    Runs ``uv venv <engines_venv>`` then ``uv pip install --python
+    <engines_venv>/bin/python -e "<clone>[torch-runtime]"``. Verifies the
+    result by re-probing the import — a successful uv invocation that still
+    can't import the stack indicates a deeper environment problem (e.g. the
+    ``+cu128`` torch-runtime extra can't resolve on a non-CUDA host) and we
+    raise with whatever stderr we captured plus a docs pointer.
+    """
+    uv = _locate_uv()
+    if not uv:
+        raise RuntimeError(
+            "uv is required to bootstrap the MOSS-TTS-v1.5 venv but was not "
+            "found on PATH (and OMNIVOICE_BUNDLED_UV was not set). Install uv "
+            "from https://docs.astral.sh/uv/ and re-launch OmniVoice, or set "
+            "OMNIVOICE_BUNDLED_UV to the absolute path of a uv binary."
+        )
+
+    logger.info(
+        "Bootstrapping MOSS-TTS-v1.5 venv at %s from %s (this can take "
+        "several minutes on first launch)", _ENGINES_VENV_DIR, clone_dir,
+    )
+
+    try:
+        subprocess.run(
+            [uv, "venv", str(_ENGINES_VENV_DIR)],
+            check=True,
+            timeout=_UV_VENV_TIMEOUT_S,
+            capture_output=True,
+        )
+    except subprocess.CalledProcessError as exc:
+        raise RuntimeError(
+            f"uv venv failed for MOSS-TTS-v1.5 bootstrap at {_ENGINES_VENV_DIR}: "
+            f"{exc.stderr.decode('utf-8', errors='replace') if exc.stderr else exc}"
+        ) from exc
+
+    python_path = _venv_python_path(_ENGINES_VENV_DIR)
+    try:
+        subprocess.run(
+            [
+                uv, "pip", "install",
+                "--python", str(python_path),
+                "-e", f"{clone_dir}[torch-runtime]",
+            ],
+            check=True,
+            timeout=_UV_PIP_INSTALL_TIMEOUT_S,
+            capture_output=True,
+        )
+    except subprocess.CalledProcessError as exc:
+        raise RuntimeError(
+            "uv pip install -e failed during MOSS-TTS-v1.5 bootstrap "
+            f"({clone_dir}). On a non-CUDA host the upstream '[torch-runtime]' "
+            "extra (cu128) cannot resolve — set up the venv manually per "
+            "docs/engines/moss-tts-v15.md. Error: "
+            f"{exc.stderr.decode('utf-8', errors='replace') if exc.stderr else exc}"
+        ) from exc
+
+    if not _venv_can_import_moss(python_path):
+        raise RuntimeError(
+            "MOSS-TTS-v1.5 bootstrap completed but the transformers/torch "
+            f"import still fails from {python_path}. Verify that {clone_dir} "
+            "is a valid MOSS-TTS clone. See docs/engines/moss-tts-v15.md."
+        )
+
+    logger.info("MOSS-TTS-v1.5 venv bootstrap successful: %s", python_path)
+    return python_path
+
+
+__all__ = [
+    "MOSS_TTS_V15_SIDECAR_SCRIPT",
+    "invalidate",
+    "is_moss_tts_v15_installed",
+    "resolve_moss_tts_v15_venv",
+]

backend/engines/moss_tts_v15/main.py

@@ -0,0 +1,303 @@
+"""MOSS-TTS-v1.5 sidecar entry point (issue #498).
+
+Runs inside ``engines/moss_tts_v15/.venv`` (or the user's existing
+``${OMNIVOICE_MOSS_TTS_V15_DIR}/.venv``) with ``transformers==5.0.0``,
+isolated from the OmniVoice parent process which pins ``transformers>=5.3``.
+Same isolation rationale as the IndexTTS sidecar.
+
+Stdlib-only at import time. The model + transformers + torch are imported
+lazily on the first synthesize op so the sidecar emits its ``ready`` frame
+inside the parent's 30 s spawn handshake even on a cold filesystem (an 8B
+model takes well over 30 s to cold-load).
+
+Wire protocol — length-prefixed JSON over stdin/stdout, byte-identical to
+``backend/services/subprocess_backend.py``::
+
+    [ 4-byte big-endian uint32 length ][ N bytes UTF-8 JSON ]
+
+Op flow:
+    1. Sidecar -> parent: {"op": "ready", "engine": "moss-tts-v15",
+                           "sample_rate": 24000}
+    2. parent -> sidecar: {"op": "ping"} -> {"op": "pong", "vram_mb": N}
+    3. parent -> sidecar: {"op": "synthesize", "text": "...",
+                            "ref_audio": "/path/spk.wav", "language": "fr",
+                            "tokens": 325, "max_new_tokens": 4096}
+       -> {"op": "progress", ...} (cold load only) then
+       -> {"op": "audio", "audio_pcm_b64": "...", "sample_rate": 24000,
+           "n_samples": N}
+    4. parent -> sidecar: {"op": "shutdown"} -> exit 0
+
+Restrictions: NO imports from OmniVoice parent code (different venv). NO
+logging of ``os.environ`` contents. Single-frame DoS cap matches the
+parent's ``MAX_FRAME_BYTES``.
+"""
+from __future__ import annotations
+
+import base64
+import json
+import os
+import struct
+import sys
+import traceback
+
+
+# Mirrors backend/services/subprocess_backend.py::MAX_FRAME_BYTES.
+MAX_FRAME_BYTES = 64 * 1024 * 1024
+
+#: Native sample rate MOSS-TTS-v1.5 emits. Advertised in the ready frame so
+#: the parent doesn't have to import MOSS just to learn the rate. Confirmed
+#: via ``processor.model_config.sampling_rate`` (the real value is read from
+#: the loaded model at synthesize time; this is the handshake default).
+MOSS_SAMPLE_RATE = 24000
+
+#: HF repo id for the weights, overridable for air-gapped / mirror installs.
+_DEFAULT_REPO = "OpenMOSS-Team/MOSS-TTS-v1.5"
+
+#: ISO-639-1 → MOSS language name. MOSS's ``build_user_message`` takes a
+#: language *name* ("French"), not a code. Unknown codes are omitted so the
+#: model auto-detects. Covers the high-traffic subset of MOSS's 31 langs.
+_ISO_TO_NAME = {
+    "en": "English", "zh": "Chinese", "ja": "Japanese", "ko": "Korean",
+    "fr": "French", "de": "German", "es": "Spanish", "it": "Italian",
+    "pt": "Portuguese", "ru": "Russian", "ar": "Arabic", "hi": "Hindi",
+    "nl": "Dutch", "pl": "Polish", "tr": "Turkish", "vi": "Vietnamese",
+    "th": "Thai", "id": "Indonesian", "cs": "Czech", "el": "Greek",
+    "he": "Hebrew", "fa": "Persian", "uk": "Ukrainian", "sv": "Swedish",
+}
+
+
+# ── wire protocol ─────────────────────────────────────────────────────────
+
+
+def _send(stream, obj: dict) -> None:
+    body = json.dumps(obj, separators=(",", ":")).encode("utf-8")
+    stream.write(struct.pack("!I", len(body)))
+    stream.write(body)
+    stream.flush()
+
+
+def _recv(stream):
+    header = stream.read(4)
+    if len(header) < 4:
+        return None  # EOF
+    (n,) = struct.unpack("!I", header)
+    if n > MAX_FRAME_BYTES:
+        raise IOError(f"frame too large: {n}")
+    body = bytearray()
+    while len(body) < n:
+        chunk = stream.read(n - len(body))
+        if not chunk:
+            raise IOError("short read")
+        body.extend(chunk)
+    return json.loads(bytes(body).decode("utf-8"))
+
+
+def _measure_vram_mb() -> float:
+    """This sidecar's own GPU memory in MB (MM2-08). The parent can't see a
+    child's VRAM, so we self-report it in the pong. 0 on CPU. Never raises."""
+    try:
+        import torch
+        if torch.cuda.is_available():
+            return round(torch.cuda.memory_allocated() / (1024 ** 2), 1)
+    except Exception:
+        pass
+    return 0.0
+
+
+# ── model loading (lazy, on first synthesize) ─────────────────────────────
+
+
+# Module-level singleton — populated on the first synthesize op and reused.
+# Holds (processor, model, device, sample_rate).
+_state = None
+
+
+def _load_model(stdout):
+    """Cold-construct the MOSS-TTS-v1.5 processor + model.
+
+    Device selection is CUDA-or-CPU only — MOSS's upstream documents no MPS
+    path and the custom ``trust_remote_code`` modelling code is untested on
+    Apple Silicon, so we never route to MPS where it might crash. dtype is
+    bf16 on CUDA, fp32 on CPU (bf16 CPU ops are spotty). Emits progress
+    frames so the parent can surface the multi-GB cold-load latency.
+    """
+    global _state
+    if _state is not None:
+        return _state
+
+    _send(stdout, {"op": "progress", "stage": "loading_model", "percent": 0})
+
+    import torch
+    from transformers import AutoModel, AutoProcessor
+
+    repo = os.environ.get("OMNIVOICE_MOSS_TTS_V15_MODEL", _DEFAULT_REPO)
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    dtype = torch.bfloat16 if device == "cuda" else torch.float32
+    # "sdpa" works on CUDA + CPU and needs no extra dep. flash_attention_2
+    # (Ampere+ CUDA, optional flash-attn) is opt-in via env.
+    attn = os.environ.get("OMNIVOICE_MOSS_TTS_V15_ATTN", "sdpa")
+
+    processor = AutoProcessor.from_pretrained(repo, trust_remote_code=True)
+    # The audio tokenizer is a separate sub-module that must be moved to the
+    # device independently (easy to miss — see upstream README).
+    processor.audio_tokenizer = processor.audio_tokenizer.to(device)
+
+    _send(stdout, {"op": "progress", "stage": "loading_model", "percent": 50})
+
+    model = AutoModel.from_pretrained(
+        repo,
+        trust_remote_code=True,
+        attn_implementation=attn,
+        torch_dtype=dtype,
+    ).to(device)
+    model.eval()
+
+    sample_rate = int(getattr(processor.model_config, "sampling_rate", MOSS_SAMPLE_RATE))
+    _state = (processor, model, device, sample_rate)
+
+    _send(stdout, {"op": "progress", "stage": "loading_model", "percent": 100})
+    return _state
+
+
+def _tensor_to_pcm_b64(audio, sample_rate: int) -> tuple[str, int, int]:
+    """Convert a torch waveform tensor to base64 int16 PCM.
+
+    MOSS returns a float tensor in [-1, 1] (1-D or (1, N)); we squeeze to
+    mono, clip, scale to int16, and base64 so the wire frame stays JSON-safe.
+    """
+    import numpy as np
+
+    arr = audio.detach().to("cpu").float().numpy()
+    arr = np.asarray(arr, dtype=np.float32).squeeze()
+    if arr.ndim > 1:
+        arr = arr.mean(axis=0)  # defensive downmix to mono
+    arr = np.clip(arr, -1.0, 1.0)
+    pcm = (arr * 32767.0).astype(np.int16).tobytes()
+    return base64.b64encode(pcm).decode("ascii"), int(sample_rate), int(arr.shape[0])
+
+
+def _resolve_language(raw):
+    """Map OmniVoice's language value to a MOSS language name, or None.
+
+    Accepts an ISO-639-1 code or a full name. Unknown / empty / "auto"
+    values return None so MOSS auto-detects."""
+    if not raw or not isinstance(raw, str):
+        return None
+    s = raw.strip()
+    if not s or s.lower() == "auto":
+        return None
+    if s.lower() in _ISO_TO_NAME:
+        return _ISO_TO_NAME[s.lower()]
+    # Already a language name (or an unknown code) — pass it through; MOSS
+    # ignores a language it doesn't recognise.
+    return s
+
+
+def _handle_synthesize(msg: dict, stdout) -> None:
+    """Dispatch one synthesize request. Emits the audio frame or raises."""
+    import torch
+
+    text = msg.get("text")
+    if not text or not isinstance(text, str):
+        raise ValueError("synthesize: missing or non-string 'text'")
+
+    processor, model, device, sample_rate = _load_model(stdout)
+
+    user_kwargs: dict = {"text": text}
+
+    ref_audio = msg.get("ref_audio")
+    if ref_audio:
+        # Zero-shot voice cloning: the reference audio alone is enough in
+        # MOSS's clone mode (ref_text is not consumed here). The processor's
+        # audio tokenizer encodes the reference into the prompt.
+        user_kwargs["reference"] = [ref_audio]
+
+    language = _resolve_language(msg.get("language"))
+    if language:
+        user_kwargs["language"] = language
+
+    tokens = msg.get("tokens")
+    if tokens is not None:
+        user_kwargs["tokens"] = int(tokens)
+
+    max_new_tokens = int(msg.get("max_new_tokens", 4096))
+
+    conversations = [[processor.build_user_message(**user_kwargs)]]
+
+    with torch.no_grad():
+        batch = processor(conversations, mode="generation")
+        outputs = model.generate(
+            input_ids=batch["input_ids"].to(device),
+            attention_mask=batch["attention_mask"].to(device),
+            max_new_tokens=max_new_tokens,
+        )
+
+    decoded = processor.decode(outputs)
+    audio = decoded[0].audio_codes_list[0]
+
+    pcm_b64, sr, n_samples = _tensor_to_pcm_b64(audio, sample_rate)
+    _send(stdout, {
+        "op": "audio",
+        "audio_pcm_b64": pcm_b64,
+        "sample_rate": sr,
+        "n_samples": n_samples,
+    })
+
+
+# ── main loop ─────────────────────────────────────────────────────────────
+
+
+def main() -> int:
+    stdin = sys.stdin.buffer
+    stdout = sys.stdout.buffer
+
+    # Ready handshake fires BEFORE any heavy import — nothing above this line
+    # touches transformers/torch, so we make the 30 s spawn window even cold.
+    _send(stdout, {
+        "op": "ready",
+        "engine": "moss-tts-v15",
+        "sample_rate": MOSS_SAMPLE_RATE,
+    })
+
+    while True:
+        try:
+            msg = _recv(stdin)
+        except Exception as exc:
+            _send(stdout, {
+                "op": "error",
+                "stage": "recv",
+                "message": f"{type(exc).__name__}: {exc}",
+                "traceback": traceback.format_exc(),
+            })
+            return 1
+        if msg is None:
+            return 0
+
+        op = msg.get("op") if isinstance(msg, dict) else None
+        try:
+            if op == "ping":
+                _send(stdout, {"op": "pong", "vram_mb": _measure_vram_mb()})
+            elif op == "synthesize":
+                _handle_synthesize(msg, stdout)
+            elif op == "shutdown":
+                return 0
+            else:
+                _send(stdout, {
+                    "op": "error",
+                    "stage": "dispatch",
+                    "message": f"unknown op: {op!r}",
+                })
+        except Exception as exc:
+            # Per-op failure is recoverable — emit the error frame and stay
+            # alive so the parent can retry without paying the respawn +
+            # multi-GB model-load cost again.
+            _send(stdout, {
+                "op": "error",
+                "stage": op or "unknown",
+                "message": f"{type(exc).__name__}: {exc}",
+                "traceback": traceback.format_exc(),
+            })
+
+
+if __name__ == "__main__":
+    sys.exit(main())

backend/main.py

@@ -9,6 +9,16 @@ _backend_dir = os.path.dirname(os.path.abspath(__file__))
 if _backend_dir not in sys.path:
     sys.path.insert(0, _backend_dir)
 
+# #564: also make the project's OWN `omnivoice` package importable from source
+# when the venv's editable install is missing/broken (interrupted/offline
+# `uv sync`, antivirus-quarantined `_editable_impl_omnivoice.pth`, …). Without
+# this the backend boots fine and only fails at the first model call with
+# `No module named 'omnivoice'`. The bootstrap now gates on omnivoice being
+# importable too (re-syncing to re-lay the editable install); this is the
+# runtime safety net. See core/omnivoice_path.py for the full rationale.
+from core.omnivoice_path import ensure_omnivoice_importable
+ensure_omnivoice_importable(_backend_dir)
+
 # Triton is unavailable on Windows — disable torch.compile / dynamo / inductor
 # to prevent TritonMissing errors at inference time. Must be set before torch
 # is imported (it is lazily imported in services/model_manager.py). Uses
@@ -327,6 +337,7 @@ from api.routers import (
     events,
     capture,
     capture_ws,
+    dictation,
     openai_compat,
     tts_stream,
     marketplace,
@@ -334,6 +345,7 @@ from api.routers import (
     sonitranslate,
     audiobook,
     longform_jobs,
+    pronunciation,  # Expressive-TTS Spec 01: user pronunciation dictionary
     settings as settings_router,  # Phase 1 AUTH-03: HF token save/clear/state
 )
 from utils import hf_progress
@@ -375,8 +387,116 @@ def _env_flag(name: str, default: bool = False) -> bool:
     return value.strip().lower() in {"1", "true", "yes", "on"}
 
 
+def _capture_preload_delay_s() -> float:
+    """Seconds after boot before the dictation (capture ASR) model warms.
+
+    Late enough that it never competes with startup I/O or the TTS preload;
+    overridable via OMNIVOICE_CAPTURE_PRELOAD_DELAY (mostly for tests)."""
+    raw = os.environ.get("OMNIVOICE_CAPTURE_PRELOAD_DELAY", "")
+    try:
+        v = float(raw)
+        if v >= 0:
+            return v
+    except (TypeError, ValueError):
+        pass
+    return 30.0
+
+
+def _capture_preload_ram_ok(min_free_bytes: int = 4 * 1024**3) -> bool:
+    """RAM guard for the dictation warm-up: skip below 4 GB free so the
+    background load never pushes a small machine into swap. If free memory
+    can't be measured, warm anyway (the load path has its own error handling)."""
+    try:
+        import psutil
+        return psutil.virtual_memory().available >= min_free_bytes
+    except Exception:
+        return True
+
+
+def _mcp_start_timeout_s() -> float:
+    """Seconds to wait for the MCP session manager to start before giving up
+    and serving without it (#632). Overridable via OMNIVOICE_MCP_START_TIMEOUT_S."""
+    raw = os.environ.get("OMNIVOICE_MCP_START_TIMEOUT_S", "")
+    try:
+        v = float(raw)
+        if v > 0:
+            return v
+    except (TypeError, ValueError):
+        pass
+    return 30.0
+
+
+async def _serve_mcp(session_manager, ready: "asyncio.Event", stop: "asyncio.Event") -> None:
+    """Own the MCP session manager's full enter→exit lifecycle in ONE task.
+
+    FastMCP's ``run()`` opens an anyio task group, and anyio requires the cancel
+    scope to be exited in the *same task* that entered it. So we must NOT enter
+    it via ``wait_for`` (which runs the enter in a throwaway sub-task) or on the
+    lifespan task and exit it elsewhere — either raises "Attempted to exit cancel
+    scope in a different task". This coroutine enters and exits the context
+    itself: it signals ``ready`` once mounted, then idles until ``stop``.
+    """
+    try:
+        async with session_manager.run():
+            ready.set()
+            await stop.wait()
+    except Exception as e:
+        logger.warning("MCP session manager stopped: %s", e)
+    finally:
+        ready.set()  # never leave startup blocked on the readiness wait
+
+
+async def _start_mcp_session_manager(session_manager, *, timeout: float):
+    """Start MCP off the startup critical path; wait up to ``timeout`` for it to
+    signal ready. Returns ``(task, stop_event, mounted)``.
+
+    The MCP layer is best-effort and must never wedge backend startup. On some
+    platforms (observed: Apple-Silicon M1, #632) ``run()`` can *hang* on its
+    anyio task group; the old code awaited the enter before serving, so the hang
+    meant "Application startup complete" never fired and the whole backend was
+    unreachable with no error. Now the enter lives in its own task and we only
+    *optionally* wait on a ready signal — a hang becomes a logged warning + a
+    backend that serves normally without MCP.
+    """
+    stop = asyncio.Event()
+    if session_manager is None:
+        return None, stop, False
+    ready = asyncio.Event()
+    task = asyncio.create_task(_serve_mcp(session_manager, ready, stop))
+    try:
+        await asyncio.wait_for(ready.wait(), timeout=timeout)
+        mounted = not task.done()  # ready is also set on failure → not mounted
+    except asyncio.TimeoutError:
+        logger.warning(
+            "MCP session manager did not signal ready within %.0fs (#632); "
+            "serving without waiting. Set OMNIVOICE_MCP_START_TIMEOUT_S to adjust.",
+            timeout,
+        )
+        mounted = False
+    return task, stop, mounted
+
+
 @asynccontextmanager
 async def lifespan(app: FastAPI):
+    # Startup watchdog (#632): a silent hang during startup (e.g. a model-load /
+    # MCP deadlock on some platforms) means "Application startup complete" never
+    # logs and the app sits forever with no error. If startup hasn't finished
+    # within the window, dump every thread's stack to stderr (→ backend_err.log)
+    # so the hang point is captured instead of invisible. Cancelled the instant
+    # startup completes, so a normal (even slow-download) boot never trips it.
+    # Tune with OMNIVOICE_STARTUP_WATCHDOG_S (seconds; 0 disables). Best-effort —
+    # never let the diagnostic itself break startup.
+    _watchdog_armed = False
+    try:
+        import faulthandler
+        _wd = float(os.environ.get("OMNIVOICE_STARTUP_WATCHDOG_S", "300"))
+        if _wd > 0 and hasattr(faulthandler, "dump_traceback_later"):
+            faulthandler.dump_traceback_later(_wd, repeat=False, exit=False)
+            _watchdog_armed = True
+            logger.info("Startup watchdog armed: thread dump if startup exceeds %.0fs (#632).", _wd)
+    except Exception:
+        pass
+
     init_db()
     # Network sharing is loopback-only by default; the PIN middleware stays
     # inert until enable() sets a PIN. Seed the (disabled) state so the
@@ -425,11 +545,19 @@ async def lifespan(app: FastAPI):
     worker_task = asyncio.create_task(task_manager.worker())
     # Warm the TTS model in the background so first /generate is instant.
     preload_task = asyncio.create_task(preload_model())
-    # Capture ASR is useful to keep warm, but it is another large model in
-    # unified memory on Apple Silicon. Keep launch lean by default; users who
-    # prefer instant dictation can opt in with OMNIVOICE_PRELOAD_CAPTURE_ASR=1.
-    if _env_flag("OMNIVOICE_PRELOAD_CAPTURE_ASR"):
+    # Dictation v2: the capture ASR warms in the background BY DEFAULT — a
+    # deferred (~30s post-boot) load off the event loop, so startup stays
+    # lean and the first dictation is instant instead of a cold model load.
+    # OMNIVOICE_PRELOAD_CAPTURE_ASR=0 opts out; the warm-up is also skipped
+    # under 4 GB free RAM (checked at warm time, not boot time).
+    if _env_flag("OMNIVOICE_PRELOAD_CAPTURE_ASR", default=True):
         async def _preload_capture_asr():
+            await asyncio.sleep(_capture_preload_delay_s())
+            if not _capture_preload_ram_ok():
+                logger.info(
+                    "Capture ASR preload skipped: <4GB free RAM; "
+                    "dictation ASR will load on first use.")
+                return
             loading_detail = None
             prev_loading_detail = None
             try:
@@ -459,23 +587,37 @@ async def lifespan(app: FastAPI):
         logger.info("Capture ASR preload disabled; dictation ASR will load on first use.")
 
     # ── MCP session manager (Wave 2.2) ────────────────────────────────────
-    # FastMCP's Streamable-HTTP transport needs its session manager running
-    # for the lifetime of the app. It's created lazily by streamable_http_app()
-    # (called in mount_mcp below), so we stack its `run()` context into ours
-    # via AsyncExitStack rather than replacing this lifespan. Best-effort: a
-    # missing/broken MCP layer must never stop the rest of the backend.
-    from contextlib import AsyncExitStack
-    async with AsyncExitStack() as _mcp_stack:
-        _sm = getattr(app.state, "mcp_session_manager", None)
-        if _sm is not None:
-            try:
-                await _mcp_stack.enter_async_context(_sm.run())
-                logger.info("MCP server mounted at /mcp")
-            except Exception as e:
-                logger.warning("MCP session manager failed to start: %s", e)
-        yield
+    # FastMCP's Streamable-HTTP transport needs its session manager running for
+    # the lifetime of the app. Run it in its OWN task that owns the full
+    # enter→exit lifecycle (anyio task-affinity, see _serve_mcp) and only wait,
+    # with a timeout, for it to signal ready — so a hang on its anyio group
+    # (observed on M1, #632) can never wedge "Application startup complete".
+    _sm = getattr(app.state, "mcp_session_manager", None)
+    mcp_task, mcp_stop, mcp_mounted = await _start_mcp_session_manager(
+        _sm, timeout=_mcp_start_timeout_s()
+    )
+    if mcp_mounted:
+        logger.info("MCP server mounted at /mcp")
+    # Startup finished — disarm the hang watchdog before serving (#632).
+    if _watchdog_armed:
+        try:
+            import faulthandler
+            faulthandler.cancel_dump_traceback_later()
+        except Exception:
+            pass
+    yield
     # ── Graceful shutdown (SIGTERM from Tauri, Ctrl+C, etc.) ────────────
     logger.info("Shutdown: cleaning up…")
+    # Stop MCP first — signal its task to exit its own anyio context (correct
+    # task-affinity), then bound the wait so a wedged manager can't hang exit.
+    mcp_stop.set()
+    if mcp_task is not None:
+        try:
+            await asyncio.wait_for(mcp_task, timeout=5.0)
+        except (asyncio.TimeoutError, asyncio.CancelledError):
+            pass
+        except Exception:
+            pass
     idle_task.cancel()
     worker_task.cancel()
     # Wait for tasks to finish their current iteration
@@ -573,8 +715,16 @@ async def global_exception_handler(request: Request, exc: Exception):
         headers["Access-Control-Allow-Origin"] = origin
         headers["Access-Control-Allow-Credentials"] = "true"
         headers["Vary"] = "Origin"
+    # #874: a model download that failed because the CONFIGURED Hugging Face
+    # mirror (HF_ENDPOINT) is unreachable used to leak the raw transformers
+    # message ("We couldn't connect to 'https://hf-mirror.com' …") as the 500
+    # detail with no next step. Appending the shared mirror hint HERE covers
+    # every route that can leak a model-load/download error (generate, dub,
+    # archetypes, …), not just TTS generate. append_hf_mirror_hint is a no-op
+    # for every other error and never raises.
+    from core.failure import append_hf_mirror_hint
     return JSONResponse(
-        {"detail": str(exc), "error_class": _entry.get("error_class")},
+        {"detail": append_hf_mirror_hint(str(exc)), "error_class": _entry.get("error_class")},
         status_code=500,
         headers=headers,
     )
@@ -740,6 +890,20 @@ app.add_middleware(NetworkAccessMiddleware)
 # keyed non-loopback client must reach them.
 app.add_middleware(BearerKeyMiddleware)
 
+# Register canonical audio MIME types before any StaticFiles mount.
+# Python's `mimetypes.guess_type()` returns `audio/x-wav` for `.wav` and
+# `audio/x-flac` for `.flac` on most platforms — these are vendor-experimental
+# (x- prefix, never IANA-registered). macOS Chrome/Safari MIME-sniff leniently
+# via CoreAudio so playback works there, but Linux Chrome/Firefox (FFmpeg) and
+# Android Chrome (ExoPlayer) strictly honor the declared type and treat the
+# x- variants as download-only — manifesting as the play button silently
+# doing nothing in the browser app while working in the Tauri desktop shell.
+# `audio/wav` / `audio/flac` are the IANA-canonical types.
+# Ref: https://www.iana.org/assignments/media-types/media-types.xhtml#audio
+import mimetypes as _mimetypes
+_mimetypes.add_type("audio/wav",  ".wav")
+_mimetypes.add_type("audio/flac", ".flac")
+
 app.mount("/audio", StaticFiles(directory=OUTPUTS_DIR), name="audio")
 app.mount("/voice_audio", StaticFiles(directory=VOICES_DIR), name="voice_audio")
 
@@ -789,6 +953,7 @@ app.include_router(watermark.router)
 app.include_router(events.router)
 app.include_router(capture.router)
 app.include_router(capture_ws.router)
+app.include_router(dictation.router)
 app.include_router(openai_compat.router)
 app.include_router(tts_stream.router)
 app.include_router(marketplace.router)
@@ -796,6 +961,7 @@ app.include_router(personas.router)
 app.include_router(sonitranslate.router)
 app.include_router(audiobook.router)
 app.include_router(longform_jobs.router)
+app.include_router(pronunciation.router)  # Expressive-TTS Spec 01: pronunciation dictionary
 app.include_router(settings_router.router)  # Phase 1 AUTH-03 endpoints
 from api.routers import mcp_bindings as _mcp_bindings_router  # noqa: E402
 app.include_router(_mcp_bindings_router.router)  # Wave 2.2 per-agent voice bindings

backend/migrations/env.py

@@ -17,7 +17,13 @@ from core.config import DB_PATH  # noqa: E402 — backend/ is on sys.path via al
 
 config = context.config
 if config.config_file_name is not None:
-    fileConfig(config.config_file_name)
+    # `disable_existing_loggers=False` is deliberate: this env runs *inside* the
+    # live app (startup `alembic upgrade head`), so the default (True) would
+    # disable every already-created application logger — e.g. silence
+    # `omnivoice.db.backup`'s "Skipping pre-migration DB backup" line and the
+    # rest of the app's logging for the remainder of the process. A migration
+    # must never mute the app (or leak that mute across a test session).
+    fileConfig(config.config_file_name, disable_existing_loggers=False)
 
 # SQLite file URL. Honour an externally-set URL (tests pass one via
 # `cfg.set_main_option("sqlalchemy.url", ...)` to point at a fixture DB),

backend/migrations/versions/0006_strip_object_object_instruct.py

@@ -0,0 +1,36 @@
+"""Heal voice_profiles.instruct poisoned with the "[object Object]" sentinel.
+
+Revision ID: 0006_strip_object_object_instruct
+Revises: 0005_unified_profiles
+Create Date: 2026-06-20 00:00:00.000000
+
+A pre-fix Voice Studio build ("Save design as profile") passed the
+``buildDesignInstruct()`` *object* straight to FormData, which string-coerced it
+to the literal ``"[object Object]"`` and persisted that into
+``voice_profiles.instruct`` (#550 #545 #542 #537 #530 #525). On first
+preview/use that value fails the engine instruct validator with a 400. The
+frontend + backend fixes stop any NEW poisoned rows; this migration heals the
+ones already saved on the buggy build (the local-first backward-compat rule —
+existing project data must keep working without manual migration).
+"""
+from typing import Sequence, Union
+
+from alembic import op
+from sqlalchemy import inspect
+
+revision: str = "0006_strip_object_object_instruct"
+down_revision: Union[str, None] = "0005_unified_profiles"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    bind = op.get_bind()
+    if "voice_profiles" in inspect(bind).get_table_names():
+        # Idempotent: only touches rows whose instruct is literally the sentinel.
+        op.execute("UPDATE voice_profiles SET instruct='' WHERE instruct='[object Object]'")
+
+
+def downgrade() -> None:
+    # Irreversible heal — the original garbage sentinel is not worth restoring.
+    pass

backend/migrations/versions/0007_rebuild_poisoned_design_instruct.py

@@ -0,0 +1,118 @@
+"""Rebuild design-profile instructs poisoned with prose / "[object Object]".
+
+Revision ID: 0007_rebuild_poisoned_design_instruct
+Revises: 0006_strip_object_object_instruct
+Create Date: 2026-06-22 00:00:00.000000
+
+Migration 0006 *blanked* the literal ``"[object Object]"`` sentinel. That stops
+the 400 on use, but it also throws away the designed voice: a row that read
+``"[object Object]"`` (or freeform prose like "A gentle, quiet male voice…")
+becomes ``instruct=''`` and then renders with the engine's neutral default —
+which is why an Indonesian *female* designed voice came out *male* (#594), and
+why prose-poisoned designs still 400 (#571 #596).
+
+This migration heals it properly: for every design profile it recomputes a
+validator-safe instruct, preferring any whitelist tags already in the stored
+value and otherwise rebuilding the tags from ``vd_states`` (the authoritative
+category→pick map the Voice Design picker persists). Non-design rows simply get
+their instruct sanitized (poison dropped). Idempotent — a healthy row is left
+byte-for-byte unchanged, so re-running is a no-op.
+
+Self-contained by design: alembic migrations must not import evolving app code
+(``omnivoice`` would also drag in torch at startup), so the tag whitelist is a
+frozen snapshot of ``omnivoice.utils.voice_design._INSTRUCT_ALL_VALID``.
+``tests/test_migration_0007_instruct_rebuild.py`` asserts the snapshot stays in
+sync with the canonical set.
+"""
+import json
+import re
+from typing import Sequence, Union
+
+from alembic import op
+from sqlalchemy import inspect
+
+revision: str = "0007_rebuild_poisoned_design_instruct"
+down_revision: Union[str, None] = "0006_strip_object_object_instruct"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+# Frozen snapshot of the design-instruct whitelist + mutually-exclusive
+# categories (omnivoice/utils/voice_design.py). Kept self-contained so the
+# migration's behaviour is pinned to the data it heals, not to future vocab
+# edits. Parity is guarded by the migration test.
+_CATEGORIES = [
+    {"male", "女", "female", "男"},
+    {"child", "teenager", "young adult", "middle-aged", "elderly",
+     "儿童", "少年", "青年", "中年", "老年"},
+    {"very low pitch", "low pitch", "moderate pitch", "high pitch", "very high pitch",
+     "极低音调", "低音调", "中音调", "高音调", "极高音调"},
+    {"whisper", "耳语"},
+    {"american accent", "british accent", "australian accent", "chinese accent",
+     "canadian accent", "indian accent", "korean accent", "portuguese accent",
+     "russian accent", "japanese accent"},
+    {"河南话", "陕西话", "四川话", "贵州话", "云南话", "桂林话",
+     "济南话", "石家庄话", "甘肃话", "宁夏话", "青岛话", "东北话"},
+]
+_ALL_VALID = set().union(*_CATEGORIES)
+
+
+def _valid_from_items(items) -> str:
+    """One whitelist tag per category, first-seen order; everything else dropped."""
+    seen = set()
+    out = []
+    for raw in items:
+        tag = str(raw if raw is not None else "").strip().lower()
+        if not tag or tag not in _ALL_VALID:
+            continue
+        ci = next((i for i, c in enumerate(_CATEGORIES) if tag in c), -1)
+        if ci in seen:
+            continue
+        seen.add(ci)
+        out.append(tag)
+    return ", ".join(out)
+
+
+def _heal(instruct, vd_states, is_design) -> str:
+    healed = _valid_from_items(re.split(r"\s*[,，]\s*", str(instruct or "").strip()))
+    if healed or not is_design:
+        return healed
+    # Stored instruct was all-poison — recover the design from vd_states.
+    if not vd_states:
+        return ""
+    try:
+        vd = json.loads(vd_states)
+    except (ValueError, TypeError):
+        return ""
+    return _valid_from_items(vd.values()) if isinstance(vd, dict) else ""
+
+
+def upgrade() -> None:
+    bind = op.get_bind()
+    insp = inspect(bind)
+    if "voice_profiles" not in insp.get_table_names():
+        return
+    cols = {c["name"] for c in insp.get_columns("voice_profiles")}
+    has_kind = "kind" in cols
+    has_vd = "vd_states" in cols
+
+    select = "SELECT id, instruct"
+    select += ", kind" if has_kind else ""
+    select += ", vd_states" if has_vd else ""
+    select += " FROM voice_profiles"
+
+    for row in bind.exec_driver_sql(select).mappings().all():
+        instruct = row["instruct"] or ""
+        is_design = (row["kind"] == "design") if has_kind else bool(instruct)
+        vd = row["vd_states"] if has_vd else None
+        healed = _heal(instruct, vd, is_design)
+        if healed != instruct:
+            bind.exec_driver_sql(
+                "UPDATE voice_profiles SET instruct = ? WHERE id = ?",
+                (healed, row["id"]),
+            )
+
+
+def downgrade() -> None:
+    # Irreversible heal — the original poisoned value isn't worth restoring.
+    pass

backend/migrations/versions/0008_pronunciation_dictionary.py

@@ -0,0 +1,67 @@
+"""Expressive-TTS Spec 01 Phase 1: user pronunciation dictionary
+
+Revision ID: 0008_pronunciation_dictionary
+Revises: 0007_rebuild_poisoned_design_instruct
+Create Date: 2026-06-25 00:00:00.000000
+
+Adds the ``pronunciation_entries`` table backing the user-editable, per-language
+pronunciation dictionary (Settings → Pronunciation). Each row maps a ``term`` to
+a ``replacement`` the engine pronounces correctly, scoped global (``language='*'``)
+or to a 2-letter language. Applied as pure text substitution before synthesis, so
+every engine honors it.
+
+  * ``id``          TEXT PRIMARY KEY — stable row id.
+  * ``term``        TEXT — the word/phrase to match (whole-word, case-insensitive).
+  * ``replacement`` TEXT — the respelling (or, for phoneme rows, the markup).
+  * ``type``        TEXT — 'respelling' | 'ipa' | 'cmu'.
+  * ``language``    TEXT — '*' = global, else a language code (e.g. 'en', 'de').
+  * ``enabled``     INTEGER — 1 = applied, 0 = parked.
+  * ``created_at``  REAL.
+
+Additive + idempotent (guarded by sqlite_master), matching 0002/0003/0004, so
+re-running on a fresh-install DB where ``_BASE_SCHEMA`` already created the table
+is a no-op (Backward-compatible project data constraint). The same table is
+mirrored into ``core/db.py::_BASE_SCHEMA`` so fresh installs and migrated DBs
+converge on an identical end-state (the dual-path discipline).
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+revision: str = "0008_pronunciation_dictionary"
+down_revision: Union[str, None] = "0007_rebuild_poisoned_design_instruct"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def _has_table(name: str) -> bool:
+    bind = op.get_bind()
+    row = bind.execute(
+        sa.text("SELECT name FROM sqlite_master WHERE type='table' AND name=:n"),
+        {"n": name},
+    ).fetchone()
+    return row is not None
+
+
+def upgrade() -> None:
+    if _has_table("pronunciation_entries"):
+        return
+    op.create_table(
+        "pronunciation_entries",
+        sa.Column("id", sa.Text(), primary_key=True),
+        sa.Column("term", sa.Text(), nullable=False),
+        sa.Column("replacement", sa.Text(), nullable=False, server_default=""),
+        sa.Column("type", sa.Text(), nullable=False, server_default="respelling"),
+        sa.Column("language", sa.Text(), nullable=False, server_default="*"),
+        sa.Column("enabled", sa.Integer(), nullable=False, server_default="1"),
+        sa.Column("created_at", sa.Float(), nullable=True),
+    )
+    op.create_index("idx_pron_lang", "pronunciation_entries", ["language"])
+
+
+def downgrade() -> None:
+    if _has_table("pronunciation_entries"):
+        op.drop_index("idx_pron_lang", table_name="pronunciation_entries")
+        op.drop_table("pronunciation_entries")

backend/schemas/requests.py

@@ -129,7 +129,7 @@ class TranslateRequest(BaseModel):
     provider: Optional[str] = None
     source_lang: Optional[str] = None  # ISO 639-1; overrides job detection
     job_id: Optional[str] = None  # Dub job id, used to resolve detected source_lang
-    quality: Optional[str] = "fast"  # "fast" (one-shot) | "cinematic" (reflect → adapt)
+    quality: Optional[str] = "fast"  # "fast" (one-shot) | "cinematic" (reflect→adapt) | "autofit" (cinematic + strict fit-to-slot)
     glossary: Optional[List[dict]] = None  # [{"source": "...", "target": "...", "note": "..."}]
     # Optional regional dialect (BCP-47, e.g. "es-AR", "pt-BR") — #280 item 2.
     # Applied by LLM-backed paths (provider="openai" or quality="cinematic"):

backend/services/asr_backend.py

@@ -23,13 +23,186 @@ faster-whisper because it's available on every platform we ship to).
 """
 from __future__ import annotations
 
+import asyncio
 import logging
 import os
 import re
+import threading
 from abc import ABC, abstractmethod
 
 logger = logging.getLogger("omnivoice.asr")
 
+# A single ASR transcribe must never block a request indefinitely. The chunked
+# dub pipeline already bounds each chunk (OMNIVOICE_TRANSCRIBE_CHUNK_TIMEOUT_S);
+# the *whole-file* paths (dub QC re-transcribe, dictation, OpenAI-compat) ran
+# unbounded, so a slow/stuck transcribe — e.g. large-v3 on a VRAM-starved GPU
+# where the resident TTS model contends for memory — hung the request *and* tied
+# up a GPU-pool worker, surfacing in the UI as the misleading "can't reach the
+# local backend" (TamKieu / Vietnam report). Bound them so a hang becomes a fast,
+# actionable error instead. Generous default (whole-file large-v3 on CPU is slow
+# but valid); override with the env var for very long single files.
+ASR_TRANSCRIBE_TIMEOUT_S = float(os.environ.get("OMNIVOICE_ASR_TRANSCRIBE_TIMEOUT_S", "300.0"))
+
+
+class ASRTimeoutError(TimeoutError):
+    """Raised when a whole-file transcribe exceeds ASR_TRANSCRIBE_TIMEOUT_S.
+
+    Carries a user-actionable message: the backend is alive (this is not a
+    connection failure) — the ASR model is too heavy for the available compute.
+    """
+
+
+def reset_pool_after_wedge(executor, *, what: str = "ASR") -> bool:
+    """Abandon a GPU pool whose worker is wedged on a timed-out transcribe (#730).
+
+    Python can't kill the stuck thread, but dropping the poisoned pool means the
+    next submit (a retry, the next chunk, or a concurrent TTS generate) gets a
+    fresh worker instead of queueing behind the wedged one. This is the ONE
+    recovery mechanism shared by every transcribe path — the whole-file guards
+    (via :func:`run_transcribe_guarded`) and the chunked dub stream both route
+    through it, so the semantics can't drift between them again.
+
+    Best-effort: an executor without ``reset()`` (a plain ThreadPoolExecutor in
+    tests) is a no-op, and a failing reset never raises — this runs on the very
+    failure path it's trying to recover from. Returns True when a reset ran.
+    """
+    _reset = getattr(executor, "reset", None)
+    if not callable(_reset):
+        return False
+    try:
+        _reset()
+        logger.warning(
+            "%s transcribe wedged — abandoned the GPU-pool worker to restore "
+            "capacity (#730).", what,
+        )
+        return True
+    except Exception:
+        logger.exception("GPU pool reset after %s timeout failed", what)
+        return False
+
+
+# ── Consecutive-timeout streak → recommend the crash-isolated engine ────────
+# A pool reset restores *capacity*, but the wedged CTranslate2/whisperx thread
+# keeps its VRAM until the process exits. When guarded transcribes keep timing
+# out back-to-back in one session, resets clearly aren't recovering the
+# underlying hang — the durable fix is the crash-isolated sidecar engine
+# (services.subprocess_asr, #393), whose child process CAN be hard-killed to
+# reclaim the hung call and its VRAM. We only *recommend* it (log + error
+# message); we never switch engines automatically (owner rule: no silent
+# behavior divergence).
+_TIMEOUT_STREAK_FOR_ISOLATED_HINT = 2
+_timeout_streak = 0
+_timeout_streak_lock = threading.Lock()
+
+
+def _note_transcribe_timeout() -> int:
+    global _timeout_streak
+    with _timeout_streak_lock:
+        _timeout_streak += 1
+        return _timeout_streak
+
+
+def _note_transcribe_success() -> None:
+    global _timeout_streak
+    with _timeout_streak_lock:
+        _timeout_streak = 0
+
+
+def _isolated_engine_hint(streak: int) -> str:
+    """User-facing recommendation once resets stop recovering (streak ≥ 2).
+
+    Empty when the streak is below the threshold, or when the user is already
+    on the isolated engine (recommending it to itself would be noise — the
+    base message's smaller-model/CPU guidance is all that's left)."""
+    if streak < _TIMEOUT_STREAK_FOR_ISOLATED_HINT:
+        return ""
+    try:
+        if active_backend_id() == "faster-whisper-isolated":
+            return ""
+    except Exception:  # noqa: BLE001 — the hint must never break the error path
+        pass
+    logger.warning(
+        "%d consecutive ASR transcribe timeouts this session — pool resets are "
+        "not recovering the hang. Recommend switching the ASR engine to "
+        "'Faster-Whisper (crash-isolated subprocess)' [faster-whisper-isolated] "
+        "in Settings → Engines. Not switching automatically (#730).", streak,
+    )
+    return (
+        f"This is {streak} transcribe timeouts in a row this session, so pool "
+        "resets aren't recovering the underlying hang. Recommended: switch the "
+        "ASR engine to 'Faster-Whisper (crash-isolated subprocess)' "
+        "(faster-whisper-isolated) in Settings → Engines — it runs "
+        "transcription in a separate process that can be force-killed to "
+        "reclaim a hung transcribe and its VRAM. OmniVoice never switches "
+        "engines automatically."
+    )
+
+
+async def run_transcribe_guarded(executor, fn, *, what: str = "ASR",
+                                 timeout: float = ASR_TRANSCRIBE_TIMEOUT_S,
+                                 timeout_env: str = "OMNIVOICE_ASR_TRANSCRIBE_TIMEOUT_S"):
+    """Run a blocking transcribe ``fn`` in ``executor`` with a hard wall-clock
+    bound. On timeout, raise :class:`ASRTimeoutError` with guidance instead of
+    letting the request hang forever.
+
+    ``run_in_executor`` cannot cancel the underlying thread, so a wedged
+    transcribe (a CTranslate2 / whisperx / VAD hang seen on some Windows + CUDA
+    setups, #730) keeps occupying its GPU-pool worker. With a 1–2 worker pool
+    that starves every *other* request — including TTS generate — and the next
+    thing the user does surfaces as "Can't reach the local backend" even though
+    the process is alive. So on timeout we also ``reset()`` the pool when it
+    supports it (``_ResilientGpuPool``): the wedged thread is abandoned and the
+    next submit gets a fresh worker, restoring capacity without an app restart.
+    The orphaned thread still holds its VRAM until the process exits, which is
+    why the message still recommends a smaller ASR model / Flush as the durable
+    fix. Executors without ``reset`` (a plain ThreadPoolExecutor in tests) just
+    get the bound + actionable error.
+    """
+    loop = asyncio.get_running_loop()
+    fut = loop.run_in_executor(executor, fn)
+    try:
+        result = await asyncio.wait_for(fut, timeout=timeout)
+    except asyncio.TimeoutError:
+        # Free the poisoned pool so a hung transcribe can't keep starving TTS /
+        # other ASR work (the "can't reach backend" symptom, #730).
+        reset_pool_after_wedge(executor, what=what)
+        streak = _note_transcribe_timeout()
+        msg = (
+            f"{what} transcription exceeded {timeout:.0f}s and was abandoned — "
+            "the backend is running, but the ASR model is too heavy for the "
+            "available compute. Most often the GPU is VRAM-starved: the resident "
+            "TTS model and a large ASR model (large-v3) contend for memory. "
+            "Capacity was restored automatically, but for a durable fix Flush the "
+            "TTS model to free VRAM, pick a smaller ASR model in Settings → "
+            f"Models, or set ASR to CPU. (Raise {timeout_env} "
+            "for very long transcribes.)"
+        )
+        hint = _isolated_engine_hint(streak)
+        if hint:
+            msg += " " + hint
+        raise ASRTimeoutError(msg)
+    # A completed transcribe (even a failed-but-returned one) proves the pool
+    # isn't hung — only genuine timeouts count toward the consecutive streak.
+    _note_transcribe_success()
+    return result
+
+
+def _compute_type_candidates(device: str) -> list[str]:
+    """Per-device compute_type fallback chain. int8 is supported by every
+    CTranslate2 CUDA+CPU build; float16/int8_float16 only on GPUs with efficient
+    fp16 — so degrade rather than crash (#551). Honors an ASR_COMPUTE_TYPE env
+    override (power users on exotic hardware can pin int8/float32)."""
+    import os
+    override = os.environ.get("ASR_COMPUTE_TYPE")
+    if override:
+        return [override]
+    return ["float16", "int8_float16", "int8"] if device == "cuda" else ["int8", "float32"]
+
+
+def _is_compute_type_error(msg: str) -> bool:
+    low = msg.lower()
+    return "compute type" in low or "efficient float16" in low
+
 
 def _decode_audio_16k_mono(audio_path: str):
     """Decode `audio_path` to a 16 kHz mono float32 waveform using OmniVoice's
@@ -112,6 +285,22 @@ class ASRBackend(ABC):
         that already speak the shape plug in with zero adapter work.
         """
 
+    def ensure_loaded(self) -> None:
+        """Eagerly load the model weights, raising the real cause on failure.
+
+        Backends load lazily inside ``transcribe()`` by default, so a load
+        failure (missing weights, CUDA/cuDNN mismatch, torch-2.6 weights-only
+        VAD regression, import error) first surfaces buried in per-chunk
+        errors — and is retried on *every* chunk. The transcribe preflight
+        calls this so the genuine cause is surfaced once, up front, as a clean
+        terminal error event instead of N cryptic per-chunk failures (#578).
+
+        Default is a no-op; backends that hold a heavy model override it to
+        trigger their lazy loader. It MUST raise the underlying exception (not
+        swallow it) so the caller can classify and surface it.
+        """
+        pass
+
     def unload(self) -> None:
         """Release the model from memory."""
         pass
@@ -120,6 +309,75 @@ class ASRBackend(ABC):
 # ── WhisperX (cross-platform default — forced-alignment word timing) ────────
 
 
+def _harden_speechbrain_lazy_imports() -> None:
+    """Make speechbrain 1.x's lazy-import guard fire on Windows too (#630/#611/#647).
+
+    speechbrain 1.x exposes optional integrations (``k2_fsa``, ``numba`` losses,
+    ``spacy``/``flair`` nlp) as ``LazyModule`` redirects living in ``sys.modules``.
+    Stray introspection — PyTorch's op-registration machinery, pickling, a
+    ``dir()``/``hasattr`` walk — touches one of these during ``whisperx.load_model``
+    (pyannote → speechbrain), which would *actually* import the optional package.
+    speechbrain guards against that by suppressing the import when the triggering
+    frame is the stdlib ``inspect`` module — but the check is
+    ``filename.endswith("/inspect.py")``, a hardcoded POSIX separator. On Windows
+    the frame filename uses backslashes (``...\\Lib\\inspect.py``), so the guard
+    misses, the redirect imports ``speechbrain.integrations.k2_fsa`` → ``import k2``
+    → k2 isn't installed → ``ImportError: Lazy import of LazyModule(...k2_fsa...)
+    failed``. That bubbles out of WhisperX and aborts transcription with zero
+    segments. WhisperX is the *default* ASR, so this is a Windows-only break of a
+    cross-platform-default feature (P0 parity).
+
+    Fix the whole class — every optional-integration redirect, not just k2 — by
+    re-implementing ``LazyModule.ensure_module`` with an ``os.sep``-agnostic
+    basename check. Idempotent and a no-op on macOS/Linux (basename match is a
+    strict superset of the old forward-slash check) and when speechbrain is
+    absent. A genuine access from real user code with k2 missing still raises
+    ImportError unchanged — only inspect-triggered spurious imports are
+    suppressed, on every platform.
+    """
+    try:
+        from speechbrain.utils import importutils as _iu
+    except Exception:  # speechbrain not installed / import side-effect — nothing to harden
+        return
+    if getattr(_iu.LazyModule, "_omnivoice_xplat_guard", False):
+        return
+    import importlib as _importlib
+    import inspect as _inspect
+    import sys as _sys
+    import warnings as _warnings
+
+    def ensure_module(self, stacklevel):
+        importer_frame = None
+        try:
+            importer_frame = _inspect.getframeinfo(_sys._getframe(stacklevel + 1))
+        except AttributeError:
+            _warnings.warn(
+                "Failed to inspect frame to check if we should ignore importing a "
+                "module lazily (OmniVoice cross-platform guard)."
+            )
+        if importer_frame is not None:
+            # Normalise BOTH separators explicitly (not os.path.basename, which is
+            # host-dependent) so the guard is correct regardless of which os.path
+            # flavour is active. Upstream's `.endswith("/inspect.py")` matched only
+            # POSIX paths — that is the Windows-only bug (#630/#611/#647).
+            base = importer_frame.filename.replace("\\", "/").rsplit("/", 1)[-1]
+            if base == "inspect.py":
+                raise AttributeError()
+        if self.lazy_module is None:
+            try:
+                if self.package is None:
+                    self.lazy_module = _importlib.import_module(self.target)
+                else:
+                    self.lazy_module = _importlib.import_module(f".{self.target}", self.package)
+            except Exception as e:  # noqa: BLE001 — match upstream: wrap as ImportError
+                raise ImportError(f"Lazy import of {repr(self)} failed") from e
+        return self.lazy_module
+
+    _iu.LazyModule.ensure_module = ensure_module
+    _iu.LazyModule._omnivoice_xplat_guard = True
+    logger.debug("speechbrain LazyModule guard hardened for cross-platform inspect.py check")
+
+
 class WhisperXBackend(ASRBackend):
     id = "whisperx"
     display_name = "WhisperX (faster-whisper + wav2vec2 forced alignment)"
@@ -146,6 +404,74 @@ class WhisperXBackend(ASRBackend):
             pass
         return "cpu", "int8"
 
+    # Peak VRAM (GB) to load *and transcribe* whisper large-v3 per CTranslate2
+    # compute type (weights + encoder/decoder workspace, with headroom). #723:
+    # on an 8 GB card with the TTS model resident, loading fp16 large-v3 dies
+    # as a *native* CUDA OOM abort — the process is killed, no Python
+    # exception ever fires, and the UI reports "Can't reach the local
+    # backend". The only defense is to never start that load, so the device
+    # pick is re-checked against actually-free VRAM right before loading.
+    _CUDA_VRAM_BUDGET_GB = {"float16": 5.0, "int8_float16": 3.5, "int8": 3.0}
+
+    #: Budget multiplier by model size (budgets above are for large-v3).
+    _MODEL_VRAM_SCALE = (
+        ("large", 1.0), ("turbo", 0.55), ("medium", 0.5),
+        ("small", 0.25), ("base", 0.15), ("tiny", 0.1),
+    )
+
+    @staticmethod
+    def _free_vram_gb():
+        """Device-wide free VRAM in GB (counts other processes), or None."""
+        try:
+            import torch
+            if torch.cuda.is_available():
+                free, _total = torch.cuda.mem_get_info()
+                return free / 1024**3
+        except Exception:  # noqa: BLE001 — preflight must never block ASR
+            pass
+        return None
+
+    @classmethod
+    def _model_scale(cls, model_name: str) -> float:
+        name = (model_name or "").lower()
+        for key, scale in cls._MODEL_VRAM_SCALE:
+            if key in name:
+                return scale
+        return 1.0  # unknown → assume large
+
+    def _degrade_for_vram(self, device: str, compute_type: str) -> tuple[str, str]:
+        """Downgrade the CUDA compute type (or fall to CPU) if free VRAM can't
+        hold the model — preventing the un-catchable native OOM abort (#723).
+        Opt-out: OMNIVOICE_ASR_VRAM_PREFLIGHT=0."""
+        if device != "cuda" or os.environ.get(
+            "OMNIVOICE_ASR_VRAM_PREFLIGHT", "1"
+        ).strip().lower() in ("0", "false", "no"):
+            return device, compute_type
+        free = self._free_vram_gb()
+        if free is None:
+            return device, compute_type
+        scale = self._model_scale(self._model_name)
+        candidates = list(self._CUDA_VRAM_BUDGET_GB)
+        start = candidates.index(compute_type) if compute_type in candidates else 0
+        for ct in candidates[start:]:
+            if free >= self._CUDA_VRAM_BUDGET_GB[ct] * scale:
+                if ct != compute_type:
+                    logger.warning(
+                        "whisperx VRAM preflight: %.1f GB free < %.1f GB needed "
+                        "for %s %s — degrading to %s (#723)",
+                        free, self._CUDA_VRAM_BUDGET_GB[compute_type] * scale,
+                        self._model_name, compute_type, ct,
+                    )
+                return device, ct
+        logger.warning(
+            "whisperx VRAM preflight: %.1f GB free is too little for %s on CUDA "
+            "(needs ≥%.1f GB even at int8) — using CPU int8 instead. Free VRAM "
+            "(flush the TTS model, or close other GPU apps) for GPU-speed ASR. (#723)",
+            free, self._model_name,
+            self._CUDA_VRAM_BUDGET_GB["int8"] * scale,
+        )
+        return "cpu", "int8"
+
     @classmethod
     def is_available(cls) -> tuple[bool, str]:
         try:
@@ -153,11 +479,36 @@ class WhisperXBackend(ASRBackend):
             return True, "ready"
         except ImportError as e:
             return False, f"whisperx not installed: {e}"
+        except Exception as e:  # noqa: BLE001
+            # The import can fail while loading a native dep — CTranslate2's .so
+            # is rejected by hardened kernels / newer glibc with "cannot enable
+            # executable stack" (#692), an OSError, not an ImportError. An
+            # availability probe must REPORT 'unusable here', never raise, so
+            # engine selection falls back instead of crashing the ASR preflight.
+            return False, f"whisperx failed to load ({type(e).__name__}): {e}"
+
+    def ensure_loaded(self) -> None:
+        # Surface a whisperx/CTranslate2/torch load failure at preflight (once,
+        # with the real cause) instead of buried per-chunk and retried N times
+        # (#578). Re-raises whatever `_ensure_asr` raises after its fp16→int8
+        # and OOM→CPU fallbacks are exhausted.
+        self._ensure_asr()
 
     def _ensure_asr(self):
         if self._asr is not None:
             return
+        # Patch speechbrain's lazy-import guard BEFORE whisperx pulls in pyannote
+        # → speechbrain, or a stray k2_fsa redirect import aborts ASR on Windows
+        # (#630/#611/#647). No-op on macOS/Linux and when speechbrain is absent.
+        _harden_speechbrain_lazy_imports()
         import whisperx
+        # #723: re-check the CUDA pick against *currently free* VRAM — the TTS
+        # model may have claimed the card since __init__. A too-big load dies
+        # as a native abort (whole process, no exception), so it must be
+        # avoided up front rather than caught below.
+        self._device, self._compute_type = self._degrade_for_vram(
+            self._device, self._compute_type
+        )
         logger.info(
             "whisperx loading ASR %s on %s (%s)",
             self._model_name, self._device, self._compute_type,
@@ -189,7 +540,40 @@ class WhisperXBackend(ASRBackend):
                 # vad_method="silero" is the default; keep it so short gaps
                 # get cleaned up before transcription.
             )
-        except RuntimeError as e:
+        except (ValueError, RuntimeError) as e:
+            # #551: GPUs without efficient fp16 (older Maxwell/Pascal, GTX 16xx)
+            # or a CTranslate2/cuDNN binary mismatch raise a *ValueError*
+            # ("Requested float16 compute type, but the target device or backend
+            # do not support efficient float16 computation") at load — not an
+            # OOM, not a RuntimeError. Retry on the SAME device with the next
+            # compute_type candidate (cuda: int8_float16 → int8) before touching
+            # the OOM→CPU path, so we degrade rather than crash every chunk.
+            if _is_compute_type_error(str(e)):
+                candidates = _compute_type_candidates(self._device)
+                try:
+                    nxt = candidates[candidates.index(self._compute_type) + 1:]
+                except ValueError:
+                    nxt = [c for c in candidates if c != self._compute_type]
+                for ct in nxt:
+                    logger.warning(
+                        "whisperx %s unsupported on %s — retrying with %s. Detail: %s",
+                        self._compute_type, self._device, ct, e,
+                    )
+                    self._compute_type = ct
+                    try:
+                        self._asr = whisperx.load_model(
+                            self._model_name,
+                            device=self._device,
+                            compute_type=self._compute_type,
+                        )
+                        return
+                    except (ValueError, RuntimeError) as e2:
+                        if _is_compute_type_error(str(e2)):
+                            e = e2
+                            continue
+                        raise
+                # Exhausted compute-type candidates on this device — re-raise.
+                raise
             # CUDA OOM: a resident TTS model + the GPU worker pool can starve
             # VRAM on small (e.g. 8 GB laptop) GPUs, so loading large-v3 on
             # CUDA dies here — which previously surfaced as a bare 500 from
@@ -462,6 +846,10 @@ class FasterWhisperBackend(ASRBackend):
             "ASR_MODEL_FASTER", "Systran/faster-whisper-large-v3"
         )
         self._model = None  # lazy — first transcribe() loads weights
+        # Set by _ensure_model() to the device/compute_type that actually loaded
+        # (after the #551 compute_type / #255 OOM→CPU fallback chain).
+        self._device: str | None = None
+        self._compute_type: str | None = None
 
     @classmethod
     def is_available(cls) -> tuple[bool, str]:
@@ -470,6 +858,11 @@ class FasterWhisperBackend(ASRBackend):
             return True, "ready"
         except ImportError as e:
             return False, f"faster-whisper not installed: {e}"
+        except Exception as e:  # noqa: BLE001
+            # faster-whisper pulls in CTranslate2, whose .so is rejected by
+            # hardened kernels / newer glibc ("cannot enable executable stack",
+            # #692) — an OSError. Report unavailable so we fall back, not crash.
+            return False, f"faster-whisper failed to load ({type(e).__name__}): {e}"
 
     def _ensure_model(self):
         if self._model is not None:
@@ -490,9 +883,58 @@ class FasterWhisperBackend(ASRBackend):
             "faster-whisper loading %s on %s (%s)",
             self._model_name, device, compute_type,
         )
-        self._model = WhisperModel(
-            self._model_name, device=device, compute_type=compute_type
-        )
+        # Try the per-device compute_type chain (cuda: float16 → int8_float16 →
+        # int8; cpu: int8 → float32). A GPU without efficient fp16 (older
+        # Maxwell/Pascal, GTX 16xx, or a CTranslate2/cuDNN mismatch) raises a
+        # *ValueError* at construction (#551) — degrade to the next candidate
+        # instead of failing every chunk. A genuine CUDA OOM falls back to CPU
+        # (slower, same model/accuracy), preserving the existing #255 behaviour.
+        candidates = _compute_type_candidates(device)
+        if compute_type in candidates:
+            candidates = candidates[candidates.index(compute_type):]
+        last_err: Exception | None = None
+        while True:
+            for ct in candidates:
+                try:
+                    self._model = WhisperModel(
+                        self._model_name, device=device, compute_type=ct
+                    )
+                    self._device, self._compute_type = device, ct
+                    return
+                except (ValueError, RuntimeError) as e:
+                    last_err = e
+                    if _is_compute_type_error(str(e)):
+                        logger.warning(
+                            "faster-whisper %s unsupported on %s — trying next "
+                            "compute_type. Detail: %s", ct, device, e,
+                        )
+                        continue
+                    if device == "cuda" and "out of memory" in str(e).lower():
+                        # Stop scanning GPU candidates; fall back to CPU below.
+                        break
+                    raise
+            # Exhausted candidates for this device. If we were on CUDA and the
+            # last failure was an OOM, retry on CPU with its candidates (#255).
+            if device == "cuda" and last_err is not None and (
+                "out of memory" in str(last_err).lower()
+            ):
+                logger.warning(
+                    "faster-whisper CUDA OOM loading %s — retrying on CPU "
+                    "(slower). Free VRAM (Flush the TTS model) for GPU-speed "
+                    "ASR. Detail: %s", self._model_name, last_err,
+                )
+                try:
+                    import torch
+                    torch.cuda.empty_cache()
+                except Exception:  # noqa: BLE001 — cache clear is best-effort
+                    pass
+                device = "cpu"
+                candidates = _compute_type_candidates(device)
+                compute_type = candidates[0]
+                continue
+            # All candidates exhausted (and no OOM→CPU retry available) — surface
+            # the last error.
+            raise last_err
 
     def transcribe(self, audio_path: str, *, word_timestamps: bool = True) -> dict:
         self._ensure_model()
@@ -681,12 +1123,25 @@ class PyTorchWhisperBackend(ASRBackend):
             "PyTorchWhisperBackend: loading standalone ASR pipeline %s on %s",
             model_name, device,
         )
-        self._pipe = hf_pipeline(
-            "automatic-speech-recognition",
-            model=model_name,
-            dtype=asr_dtype,
-            device_map=device,
-        )
+        try:
+            self._pipe = hf_pipeline(
+                "automatic-speech-recognition",
+                model=model_name,
+                dtype=asr_dtype,
+                device_map=device,
+            )
+        except Exception as e:
+            # #549: an incomplete transformers install fails to build the ASR
+            # pipeline (e.g. "Could not import module 'AutoFeatureExtractor'").
+            # The raw error is opaque; re-raise with an actionable next step so
+            # the toast tells the user how to recover instead of "no segments".
+            raise RuntimeError(
+                "transformers ASR pipeline failed to import (AutoFeatureExtractor) "
+                "— your transformers install is incomplete; reinstall with "
+                "`uv pip install --reinstall transformers`, or use faster-whisper "
+                "(OmniVoice's default ASR) which avoids the transformers pipeline. "
+                f"Underlying: {e}"
+            ) from e
 
     def transcribe(self, audio_path: str, *, word_timestamps: bool = True) -> dict:
         import soundfile as sf
@@ -705,7 +1160,7 @@ class PyTorchWhisperBackend(ASRBackend):
         return result if isinstance(result, dict) else {"chunks": [], "raw": result}
 
 
-# ── NeMo Parakeet TDT (NVIDIA — English SOTA from ASR Leaderboard) ─────────
+# ── NeMo Parakeet TDT (NVIDIA — Open ASR Leaderboard SOTA, 25 langs) ────────
 
 
 class NeMoASRBackend(ASRBackend):
@@ -713,16 +1168,14 @@ class NeMoASRBackend(ASRBackend):
 
     FastConformer encoder + Token-and-Duration Transducer decoder.
     Beats Whisper large-v3 on English benchmarks (~6% WER).
-    Supports 25+ European languages with auto language detection.
-    Requires NVIDIA GPU.
+    Supports 25 (mostly European) languages with auto language detection.
+    CUDA or CPU — parakeet-tdt-0.6b-v3 measured RTF 0.08–0.23 on an Apple
+    Silicon M2 *CPU* (2026-07-02), ~20× faster than faster-whisper large-v3
+    int8 on the same host, so the old hard CUDA gate was a false claim.
     """
     id = "nemo-parakeet"
-    # CUDA-only: is_available() hard-fails without a GPU ("Parakeet TDT requires
-    # NVIDIA GPU (CUDA)"), so declaring a CPU path would be a false claim. On a
-    # CPU host this correctly resolves to routing_status="unavailable", matching
-    # is_available()=False (the matrix suppresses the routing badge there).
-    gpu_compat = ("cuda",)
-    display_name = "Parakeet TDT (NVIDIA NeMo — English SOTA)"
+    gpu_compat = ("cuda", "cpu")
+    display_name = "Parakeet TDT (NVIDIA NeMo — 25 langs, CUDA/CPU)"
 
     def __init__(self):
         self._model_name = os.environ.get(
@@ -732,10 +1185,11 @@ class NeMoASRBackend(ASRBackend):
 
     @classmethod
     def is_available(cls) -> tuple[bool, str]:
+        # No CUDA gate: the 0.6B TDT model is comfortably faster than realtime
+        # on CPU (see class docstring), so availability is a pure dependency
+        # check and engine_routing picks the effective device from gpu_compat.
         try:
-            import torch
-            if not torch.cuda.is_available():
-                return False, "Parakeet TDT requires NVIDIA GPU (CUDA)"
+            import torch  # noqa: F401
         except ImportError:
             return False, "PyTorch not installed"
         try:
@@ -908,6 +1362,164 @@ class MoonshineASRBackend(ASRBackend):
         self._transcriber = None
 
 
+# ── sherpa-onnx live dictation (ONNX, CPU, streaming + offline) ─────────────
+
+
+def _load_audio_16k_mono_f32(audio_path: str):
+    """Decode any audio file to 16 kHz mono float32 in [-1, 1] for sherpa.
+
+    Prefers soundfile (WAV/FLAC — the dictation buffers are already WAV) and
+    resamples to 16 kHz when needed; falls back to OmniVoice's validated ffmpeg
+    for containers soundfile can't read (WebM/Opus). 16 kHz is sherpa's cheapest
+    feed; it resamples internally too, but doing it here keeps the contract tight.
+    """
+    import numpy as np
+    try:
+        import soundfile as sf
+        data, sr = sf.read(audio_path, dtype="float32", always_2d=False)
+        if getattr(data, "ndim", 1) > 1:
+            data = data.mean(axis=1)
+        data = np.ascontiguousarray(data, dtype=np.float32)
+        if sr != 16000:
+            # Lightweight linear resample — adequate for ASR features.
+            n = int(round(len(data) * 16000 / sr))
+            if n > 0:
+                xp = np.linspace(0.0, 1.0, num=len(data), endpoint=False)
+                x = np.linspace(0.0, 1.0, num=n, endpoint=False)
+                data = np.interp(x, xp, data).astype(np.float32)
+            sr = 16000
+        return data, sr
+    except Exception:
+        # Container soundfile can't read (WebM/Opus) — use the validated ffmpeg
+        # path, which already yields 16 kHz mono float32.
+        return _decode_audio_16k_mono(audio_path), 16000
+
+
+class SherpaDictationBackend(ASRBackend):
+    """k2-fsa/sherpa-onnx ONNX dictation engine (CPU, live + offline).
+
+    One :class:`ASRBackend` instance is bound to one of the seven sherpa
+    dictation models (see :mod:`services.sherpa_dictation`). For the offline
+    ``transcribe(path)`` contract it runs an ``OfflineRecognizer`` for offline
+    models and a one-shot ``OnlineRecognizer`` decode for streaming models
+    (so ``POST /transcribe`` works for every sherpa model). The *live* WS path
+    drives the streaming recognizer incrementally — see ``capture_ws.py``.
+
+    CPU provider only (cross-platform default-parity rule); no CUDA dep.
+    """
+    id = "sherpa-onnx-asr"
+    display_name = "Sherpa-ONNX dictation (live, CPU — streaming + offline)"
+    gpu_compat = ("cpu",)
+
+    def __init__(self, model_id: str | None = None):
+        from services import sherpa_dictation as _sd
+        mid = model_id or os.environ.get(
+            "OMNIVOICE_SHERPA_ASR_MODEL", _sd.DEFAULT_MODEL_ID
+        )
+        spec = _sd.get_spec(mid)
+        if spec is None:
+            raise ValueError(
+                f"Unknown sherpa dictation model {mid!r}. Known: "
+                f"{[s.id for s in _sd.list_specs()]}"
+            )
+        self._spec = spec
+        self._rec = None  # lazy OfflineRecognizer / OnlineRecognizer
+        # One backend is shared across live-dictation WS sessions (see
+        # get_sherpa_dictation_backend), so guard the one-time recognizer build
+        # against two sessions racing to construct it concurrently. Each session
+        # still owns its own decode stream — only the recognizer is shared.
+        self._rec_lock = threading.Lock()
+
+    @property
+    def spec(self):
+        return self._spec
+
+    @property
+    def streaming(self) -> bool:
+        return self._spec.streaming
+
+    @classmethod
+    def is_available(cls) -> tuple[bool, str]:
+        from services.sherpa_dictation import sherpa_available
+        return sherpa_available()
+
+    def ensure_loaded(self) -> None:
+        self._ensure_rec()
+
+    def warmup(self) -> None:
+        """Eagerly build the recognizer so the FIRST live-dictation session
+        doesn't pay the 1.3–2.5s ONNX-session load (#888 'instant first
+        dictation'). Called by the background capture-ASR preload; idempotent,
+        and the built recognizer is reused across sessions via
+        get_sherpa_dictation_backend (the same singleton the preload warms)."""
+        self._ensure_rec()
+
+    def _ensure_rec(self):
+        if self._rec is not None:
+            return
+        with self._rec_lock:
+            if self._rec is not None:
+                return
+            from services import sherpa_dictation as _sd
+            if self._spec.streaming:
+                self._rec = _sd.build_online_recognizer(self._spec)
+            else:
+                self._rec = _sd.build_offline_recognizer(self._spec)
+
+    def transcribe(self, audio_path: str, *, word_timestamps: bool = True) -> dict:
+        self._ensure_rec()
+        logger.info(
+            "sherpa-onnx dictation transcribing %s (model=%s, kind=%s)",
+            audio_path, self._spec.id, self._spec.kind,
+        )
+        samples, sr = _load_audio_16k_mono_f32(audio_path)
+        if self._spec.streaming:
+            text = self._decode_online_oneshot(samples, sr)
+        else:
+            text = self._decode_offline(samples, sr)
+        return _sherpa_result(text, samples, sr)
+
+    def _decode_offline(self, samples, sr) -> str:
+        s = self._rec.create_stream()
+        s.accept_waveform(sr, samples)
+        self._rec.decode_stream(s)
+        return (s.result.text or "").strip()
+
+    def _decode_online_oneshot(self, samples, sr) -> str:
+        """One-shot decode of a whole buffer through the streaming recognizer
+        (for the non-streaming ``transcribe()`` / partial re-decode path)."""
+        import numpy as np
+        s = self._rec.create_stream()
+        s.accept_waveform(sr, samples)
+        tail = np.zeros(int(0.5 * sr), dtype=np.float32)
+        s.accept_waveform(sr, tail)
+        s.input_finished()
+        while self._rec.is_ready(s):
+            self._rec.decode_stream(s)
+        return (self._rec.get_result(s) or "").strip()
+
+    def unload(self) -> None:
+        self._rec = None
+        import gc
+        gc.collect()
+
+
+def _sherpa_result(text: str, samples, sr) -> dict:
+    """Normalise a sherpa decode to OmniVoice's ``{chunks, segments, language,
+    text}`` contract. sherpa gives plain text (no VAD split), so emit a single
+    segment spanning the buffer — same shape Moonshine uses."""
+    text = (text or "").strip()
+    try:
+        duration = round(len(samples) / float(sr), 3)
+    except Exception:
+        duration = None
+    segments = []
+    if text:
+        segments.append({"text": text, "start": 0.0, "end": duration, "words": []})
+    chunks = [{"text": s["text"], "timestamp": (s["start"], s["end"])} for s in segments]
+    return {"chunks": chunks, "segments": segments, "language": "auto", "text": text}
+
+
 # ── Registry ────────────────────────────────────────────────────────────────
 
 
@@ -1070,6 +1682,7 @@ _REGISTRY: dict[str, type[ASRBackend]] = _LazyASRRegistry({
     "nemo-parakeet":   NeMoASRBackend,
     "moonshine":       MoonshineASRBackend,
     "funasr":          FunASRBackend,
+    "sherpa-onnx-asr": SherpaDictationBackend,
     # "faster-whisper-isolated": resolved lazily (crash-isolated subprocess).
 })
 
@@ -1084,6 +1697,13 @@ _INSTALL_HINTS: dict[str, str] = {
     "nemo-parakeet":   "pip install nemo_toolkit[asr]  (NVIDIA Parakeet; CUDA or CPU)",
     "moonshine":       "pip install useful-moonshine  (edge/CPU-optimized ASR)",
     "funasr":          "pip install funasr  (SenseVoiceSmall + FSMN-VAD; CUDA or CPU)",
+    "sherpa-onnx-asr": "uv add sherpa-onnx  (ONNX live dictation; CPU, cross-platform)",
+    "faster-whisper-isolated": (
+        "No extra install (reuses faster-whisper). Escape hatch for hanging "
+        "transcribes: runs ASR in a separate process that can be force-killed "
+        "to reclaim a hung transcribe and its VRAM (#730). Slightly slower per "
+        "call than in-process faster-whisper."
+    ),
 }
 
 # Most-recent failure per backend, so a transient probe error survives between
@@ -1138,6 +1758,22 @@ def list_backends() -> list[dict]:
     return out
 
 
+def _probe_available(cls) -> bool:
+    """``is_available()`` that never raises. A probe that explodes (e.g. a native
+    lib that refuses to load — CTranslate2's exec-stack rejection, #692) means the
+    engine is unusable on this host, so treat it as unavailable and fall through
+    to the next candidate rather than crash engine selection."""
+    try:
+        ok, _ = cls.is_available()
+        return bool(ok)
+    except Exception:  # noqa: BLE001
+        logger.warning(
+            "ASR auto-detect: %s.is_available() raised — treating as unavailable",
+            cls.__name__, exc_info=True,
+        )
+        return False
+
+
 def _auto_detect() -> str:
     """Pick the best available ASR engine for the current hardware.
 
@@ -1156,17 +1792,14 @@ def _auto_detect() -> str:
       4. pytorch-whisper — last resort; requires the TTS model to be loaded
                           so it can reuse `_asr_pipe`.
     """
-    ok, _ = WhisperXBackend.is_available()
-    if ok:
+    if _probe_available(WhisperXBackend):
         return "whisperx"
-    ok, _ = FasterWhisperBackend.is_available()
-    if ok:
+    if _probe_available(FasterWhisperBackend):
         return "faster-whisper"
     try:
         import torch
         if hasattr(torch.backends, "mps") and torch.backends.mps.is_available():
-            ok, _ = MLXWhisperBackend.is_available()
-            if ok:
+            if _probe_available(MLXWhisperBackend):
                 return "mlx-whisper"
     except Exception:
         pass
@@ -1184,6 +1817,14 @@ def active_backend_id() -> str:
     return _auto_detect()
 
 
+# Subprocess-isolated backends must be process-wide singletons: their
+# ``__init__`` registers an atexit shutdown hook and the instance owns the
+# sidecar child process, so a fresh instance per request would leak handler
+# entries and respawn the sidecar (reloading its model) on every transcribe.
+# Same rationale as api.routers.engines._ENGINE_INSTANCES.
+_ISOLATED_INSTANCES: dict[str, "ASRBackend"] = {}
+
+
 def get_active_asr_backend(*, asr_pipe=None) -> ASRBackend:
     bid = active_backend_id()
     if bid == "pytorch-whisper":
@@ -1196,7 +1837,14 @@ def get_active_asr_backend(*, asr_pipe=None) -> ASRBackend:
         return WhisperXBackend()
     if bid not in _REGISTRY:
         raise ValueError(f"Unknown ASR backend: {bid!r}. Known: {list(_REGISTRY)}")
-    return _REGISTRY[bid]()
+    cls = _REGISTRY[bid]
+    if getattr(cls, "_is_subprocess_isolated", False):
+        inst = _ISOLATED_INSTANCES.get(bid)
+        if inst is None:
+            inst = cls()
+            _ISOLATED_INSTANCES[bid] = inst
+        return inst
+    return cls()
 
 
 def transcribe_reference(audio_path: str) -> str | None:
@@ -1238,40 +1886,122 @@ def transcribe_reference(audio_path: str) -> str | None:
 
 
 _capture_backend: ASRBackend | None = None
+# The sherpa model id the cached capture backend was built for, so a model
+# switch in Settings rebuilds the singleton instead of serving the old model.
+_capture_backend_key: str | None = None
+# Guards the read-modify-write of the two globals above. Both the background
+# capture-ASR preload (runs in the GPU-pool thread) and the live-dictation WS
+# handlers (run on the event loop) resolve/replace the singleton, so the
+# check-then-build must be atomic to avoid two threads each building a model.
+_capture_backend_lock = threading.Lock()
+
+
+def get_sherpa_dictation_backend(model_id: str) -> "SherpaDictationBackend":
+    """Return a shared, warm-cached :class:`SherpaDictationBackend` for
+    ``model_id``, building it at most once and reusing the recognizer across
+    live-dictation WS sessions.
+
+    Live sessions previously constructed a FRESH backend per WebSocket connect,
+    so every session reloaded the ONNX recognizer (1.3–2.5s "loading…") and the
+    #888 background preload was a no-op. This reuses the SAME module-level
+    ``_capture_backend`` singleton the preload warms (when the ids match), and
+    rebuilds on a model switch — identical invalidation to
+    :func:`get_capture_asr_backend`. Thread-safe: the recognizer is shared;
+    each session creates its own decode stream (see capture_ws)."""
+    global _capture_backend, _capture_backend_key
+    with _capture_backend_lock:
+        if (isinstance(_capture_backend, SherpaDictationBackend)
+                and _capture_backend_key == model_id):
+            return _capture_backend
+        backend = SherpaDictationBackend(model_id=model_id)
+        _capture_backend = backend
+        _capture_backend_key = model_id
+        return backend
+
+
+def dictation_model_id() -> str | None:
+    """The selected sherpa dictation model id, or None when dictation is off /
+    no sherpa model is chosen. Env var wins (power-user pin), then prefs."""
+    explicit = os.environ.get("OMNIVOICE_SHERPA_ASR_MODEL")
+    if explicit:
+        return explicit
+    try:
+        from core import prefs
+        if not prefs.get("dictation.enabled", True):
+            return None
+        mid = prefs.get("dictation.model_id")
+    except Exception:
+        return None
+    from services.sherpa_dictation import is_sherpa_model
+    return mid if is_sherpa_model(mid) else None
 
 
 def get_capture_asr_backend() -> ASRBackend:
     """Pick the fastest ASR engine for capture / dictation.
 
-    Priority order (speed-first — word alignment is unnecessary for
-    dictation, so we skip WhisperX's forced-alignment overhead):
+    Selection order:
 
-      1. mlx-whisper Turbo  — Apple Silicon, ~5× faster than large-v3
-      2. mlx-whisper large  — still native Metal, faster than CPU int8
-      3. faster-whisper     — cross-platform CTranslate2 fallback
-      4. pytorch-whisper    — last resort
+      0. sherpa-onnx dictation — when ``dictation.model_id`` names one of the
+         seven sherpa models (live/CPU; the new live-dictation path).
+      1. mlx-whisper Turbo     — Apple Silicon, ~5× faster than large-v3
+      2. mlx-whisper large     — still native Metal, faster than CPU int8
+      3. faster-whisper        — cross-platform CTranslate2 fallback
+      4. pytorch-whisper       — last resort
 
     The caller should also pass ``word_timestamps=False`` to the returned
     backend to skip per-word timing and shave another ~30% latency.
 
-    Returns a cached singleton so the model stays warm between calls.
+    Returns a cached singleton so the model stays warm between calls; the
+    singleton is rebuilt if the selected sherpa model changes.
     """
-    global _capture_backend
-    if _capture_backend is not None:
-        return _capture_backend
+    global _capture_backend, _capture_backend_key
 
-    # Prefer MLX Turbo on Apple Silicon
-    ok, _ = MLXWhisperBackend.is_available()
-    if ok:
-        _capture_backend = MLXWhisperBackend(model_name=_MLX_MODEL_TURBO)
-        return _capture_backend
+    # Atomic resolve+build so the preload thread and a WS session (which may
+    # call get_sherpa_dictation_backend concurrently) can't both build a model.
+    with _capture_backend_lock:
+        # 0. Honor an explicit sherpa dictation model selection.
+        sherpa_id = dictation_model_id()
+        if sherpa_id:
+            ok, _ = SherpaDictationBackend.is_available()
+            if ok:
+                if not (isinstance(_capture_backend, SherpaDictationBackend)
+                        and _capture_backend_key == sherpa_id):
+                    try:
+                        _capture_backend = SherpaDictationBackend(model_id=sherpa_id)
+                        _capture_backend_key = sherpa_id
+                    except Exception as e:  # noqa: BLE001 — fall through to Whisper
+                        logger.warning(
+                            "sherpa dictation model %r unavailable (%s) — falling "
+                            "back to Whisper capture engine", sherpa_id, e,
+                        )
+                        _capture_backend = None
+                        _capture_backend_key = None
+                if _capture_backend is not None:
+                    return _capture_backend
+            else:
+                logger.info(
+                    "dictation.model_id=%r selected but sherpa-onnx not installed — "
+                    "falling back to Whisper capture engine", sherpa_id,
+                )
 
-    # Fall back to faster-whisper (CPU int8 on non-Apple)
-    ok, _ = FasterWhisperBackend.is_available()
-    if ok:
-        _capture_backend = FasterWhisperBackend()
-        return _capture_backend
+        if _capture_backend is not None and _capture_backend_key is None:
+            return _capture_backend
 
-    # Last resort
-    _capture_backend = PyTorchWhisperBackend()
-    return _capture_backend
+        # Prefer MLX Turbo on Apple Silicon
+        ok, _ = MLXWhisperBackend.is_available()
+        if ok:
+            _capture_backend = MLXWhisperBackend(model_name=_MLX_MODEL_TURBO)
+            _capture_backend_key = None
+            return _capture_backend
+
+        # Fall back to faster-whisper (CPU int8 on non-Apple)
+        ok, _ = FasterWhisperBackend.is_available()
+        if ok:
+            _capture_backend = FasterWhisperBackend()
+            _capture_backend_key = None
+            return _capture_backend
+
+        # Last resort
+        _capture_backend = PyTorchWhisperBackend()
+        _capture_backend_key = None
+        return _capture_backend

backend/services/audiobook.py

@@ -65,10 +65,14 @@ class AudiobookPlan:
     def char_count(self) -> int:
         return sum(c.char_count for c in self.chapters)
 
+    @property
+    def chapter_count(self) -> int:
+        return len(self.chapters)
+
     def to_dict(self) -> dict:
         return {
             "chapters": [c.to_dict() for c in self.chapters],
-            "chapter_count": len(self.chapters),
+            "chapter_count": self.chapter_count,
             "char_count": self.char_count,
         }
 

backend/services/chunked_tts.py

@@ -42,6 +42,46 @@ _ABBREVIATIONS = frozenset({
 # [pause 300ms] markers). The splitter must never cut inside one.
 _BRACKET_TAG_RE = re.compile(r"\[[^\]]*\]")
 
+# Dense scripts (CJK ideographs, kana, Hangul) where ~1 character = 1 syllable,
+# so an N-char chunk is far more *speech* than N Latin chars. Counted by code
+# point (see _dense_char_count) so there are no literal CJK chars in source.
+def _dense_char_count(text: str) -> int:
+    """Number of CJK / kana / Hangul characters in *text* (dense scripts)."""
+    n = 0
+    for ch in text:
+        o = ord(ch)
+        if (0x3040 <= o <= 0x30FF or 0x3400 <= o <= 0x4DBF
+                or 0x4E00 <= o <= 0x9FFF or 0xAC00 <= o <= 0xD7AF
+                or 0xF900 <= o <= 0xFAFF):
+            n += 1
+    return n
+
+# A chunk that is predominantly dense-script (>= this fraction) gets the smaller
+# limit; below it, the text is mostly spaced/Latin and the full limit applies.
+_DENSE_FRACTION_THRESHOLD = 0.3
+# Speech-per-char multiplier for dense scripts vs Latin (~1 ideograph ≈ 2.5
+# Latin chars of audio). Used to scale the char limit down.
+_DENSE_SPEECH_FACTOR = 2.5
+
+
+def _effective_max_chars(text: str, max_chars: int) -> int:
+    """Scale *max_chars* down for dense-script text (#505).
+
+    Long-form (5+ min) generation degrades — repeated / skipped / mispronounced
+    words — when a single chunk's acoustic sequence gets too long. With CJK /
+    kana / Hangul, ~1 char = 1 syllable, so an 800-char chunk is ~4-5 minutes of
+    audio in one shot, well past the model's reliable range. When a chunk is
+    predominantly dense-script, cap it to ``max_chars / _DENSE_SPEECH_FACTOR``
+    (floored) so each chunk's spoken length stays bounded. Latin / spaced text
+    is unchanged. ``max_chars <= 0`` (chunking disabled) is left untouched.
+    """
+    if max_chars <= 0 or not text:
+        return max_chars
+    dense = _dense_char_count(text)
+    if dense and dense / len(text) >= _DENSE_FRACTION_THRESHOLD:
+        return max(120, min(max_chars, round(max_chars / _DENSE_SPEECH_FACTOR)))
+    return max_chars
+
 
 def split_text_into_chunks(text: str, max_chars: int = DEFAULT_MAX_CHUNK_CHARS) -> List[str]:
     """Split *text* at natural boundaries into chunks of at most *max_chars*.
@@ -54,6 +94,9 @@ def split_text_into_chunks(text: str, max_chars: int = DEFAULT_MAX_CHUNK_CHARS)
     text = text.strip()
     if not text:
         return []
+    # #505: dense-script text packs far more speech per char, so cap the chunk
+    # smaller to keep each chunk's spoken length in the model's reliable range.
+    max_chars = _effective_max_chars(text, max_chars)
     if max_chars <= 0 or len(text) <= max_chars:
         return [text]
 

backend/services/director.py

@@ -26,6 +26,10 @@ from services.llm_backend import get_active_llm_backend, OffBackend
 
 logger = logging.getLogger("omnivoice.director")
 
+# LLM Skills registry id — Settings → LLM Skills can disable the LLM parse
+# or route it to a specific provider. Disabled == the heuristic parser.
+_SKILL_ID = "direction_parse"
+
 
 # ── Taxonomy (stable contract) ──────────────────────────────────────────────
 # Additive per dimension — multiple values allowed. Unknown tokens are ignored
@@ -147,7 +151,10 @@ def parse(text: str) -> Direction:
     if not text or not text.strip():
         return Direction(source=text or "")
 
-    llm = get_active_llm_backend()
+    from services import llm_skills
+    # `active=` forwards this module's (monkeypatch-able) name so the
+    # no-override path is byte-identical to the pre-skills behavior.
+    llm = llm_skills.skill_backend(_SKILL_ID, active=lambda: get_active_llm_backend())
     if isinstance(llm, OffBackend):
         return _heuristic_parse(text)
 

backend/services/dub_pipeline.py

@@ -435,6 +435,60 @@ def _ensure_browser_playable_mp4(video_path: str) -> str:
     return video_path
 
 
+# Bounded retry for transient download failures (#579/#598). yt-dlp's own
+# `retries`/`fragment_retries` cover per-fragment HTTP flakes, but a broken
+# pipe ([Errno 32]) raised while the write side of a pipe closes mid-stream
+# (a killed ffmpeg merge child, a CDN reset during muxing) aborts the whole
+# `extract_info` call and is NOT covered by them — so a single transient blip
+# failed the entire ingest with a raw "Broken pipe". We add a small download-
+# level retry on top, cleaning up the partial download between attempts so a
+# half-written `original.*` can't poison the next try.
+_YT_DOWNLOAD_RETRIES = 2  # total attempts = 1 + retries = 3
+
+
+def _is_transient_download_error(exc: BaseException) -> bool:
+    """True when a download failure is worth retrying (broken pipe / net drop).
+
+    Reuses the single failure taxonomy (`VIDEO_DOWNLOAD_NETWORK`) rather than a
+    parallel keyword list, so "what counts as transient" stays single-sourced
+    with the error-hint classification. ``BrokenPipeError``/``ConnectionError``
+    are matched by class too, since a bare instance may be wrapped or re-raised
+    with a stripped message that no longer contains "broken pipe".
+    """
+    if isinstance(exc, (BrokenPipeError, ConnectionError)):
+        return True
+    return failure.classify(str(exc)) == "VIDEO_DOWNLOAD_NETWORK"
+
+
+# YouTube serves some videos' high-quality formats signature-protected to the
+# default player client, so the media download 403s even though extraction
+# worked. Forcing an alternate client commonly bypasses it; on a 403 we escalate
+# through these (in order) before giving up (#625).
+_YT_PLAYER_CLIENTS = ["tv", "android", "web_safari"]
+
+
+def _is_forbidden_download_error(exc: BaseException) -> bool:
+    """True for an HTTP 403 — not transient (the same client keeps 403ing), but
+    often fixable by switching the YouTube player client."""
+    s = str(exc)
+    return "403" in s or "Forbidden" in s
+
+
+def _cleanup_partial_download(job_dir: str) -> None:
+    """Remove any half-written `original.*` files before a retry.
+
+    A partial download left on disk would otherwise be picked up as a "finished"
+    file by the post-download codec probe, or collide with the next attempt's
+    output. Best-effort — never raises on the failure path.
+    """
+    import glob
+    for stale in glob.glob(os.path.join(job_dir, "original.*")):
+        try:
+            os.remove(stale)
+        except OSError:
+            pass
+
+
 def yt_download_sync(
     url: str,
     job_dir: str,
@@ -480,6 +534,12 @@ def yt_download_sync(
         "quiet": True,
         "no_warnings": True,
         "restrictfilenames": True,
+        # Don't stamp the downloaded file's mtime with the video's upload date
+        # (#642): on Windows an out-of-range/invalid timestamp makes the os.utime
+        # call raise `[Errno 22] Invalid argument`, failing the whole ingest. We
+        # download to a throwaway `original.*` and never use its mtime, so skip
+        # it entirely (equivalent to yt-dlp's --no-mtime).
+        "updatetime": False,
         "socket_timeout": 30,
         # Resilience against YouTube CDN flakes: a single empty fragment
         # (commonly the very last one — "Did not get any data blocks")
@@ -491,17 +551,64 @@ def yt_download_sync(
         "extractor_retries": 5,
         "skip_unavailable_fragments": True,
     }
+    # #712: the format selector above pulls separate video+audio streams, so
+    # yt-dlp muxes them via ffmpeg (merge_output_format=mp4). yt-dlp only looks
+    # for ffmpeg on PATH and aborts with "you have requested merging of multiple
+    # formats but ffmpeg is not installed" — but OmniVoice's ffmpeg is often a
+    # bundled Tauri sidecar / imageio-ffmpeg binary that isn't on PATH (common on
+    # Windows). Point yt-dlp at the exact ffmpeg we resolve so the merge works.
+    _ffmpeg_bin = find_ffmpeg()
+    if _ffmpeg_bin:
+        ydl_opts["ffmpeg_location"] = _ffmpeg_bin
     if progress_hook is not None:
         ydl_opts["progress_hooks"] = [progress_hook]
-    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-        info = ydl.extract_info(url, download=True)
-        path = ydl.prepare_filename(info)
-        root, _ = os.path.splitext(path)
-        mp4 = root + ".mp4"
-        if os.path.exists(mp4):
-            video_path = mp4
-        else:
-            video_path = path
+
+    # Download with a bounded retry on transient/broken-pipe-class failures
+    # (#579/#598). A broken pipe mid-mux isn't recoverable inside yt-dlp's own
+    # fragment retries, but a fresh `extract_info` usually succeeds. Between
+    # attempts we wipe the partial `original.*` so a half-written file can't be
+    # mistaken for a finished download.
+    info = None
+    path = None
+    transient_used = 0
+    client_idx = 0
+    while True:
+        try:
+            with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+                info = ydl.extract_info(url, download=True)
+                path = ydl.prepare_filename(info)
+            break
+        except Exception as exc:
+            _cleanup_partial_download(job_dir)
+            # 403 Forbidden: not transient — escalate the YouTube player client,
+            # which commonly bypasses a signature-protected format set (#625).
+            if _is_forbidden_download_error(exc) and client_idx < len(_YT_PLAYER_CLIENTS):
+                client = _YT_PLAYER_CLIENTS[client_idx]
+                client_idx += 1
+                ydl_opts = {**ydl_opts, "extractor_args": {"youtube": {"player_client": [client]}}}
+                logger.warning(
+                    "Download 403 for %s — retrying with player_client=%s (#625)", url, client,
+                )
+                continue
+            # Transient/broken-pipe: a fresh extract_info usually succeeds
+            # (#579/#598). A 403 never counts here — it's escalated above.
+            if (transient_used < _YT_DOWNLOAD_RETRIES
+                    and _is_transient_download_error(exc)
+                    and not _is_forbidden_download_error(exc)):
+                transient_used += 1
+                logger.warning(
+                    "Transient download failure for %s (attempt %d/%d): %s — retrying",
+                    url, transient_used, _YT_DOWNLOAD_RETRIES, exc,
+                )
+                time.sleep(2 * transient_used)  # brief, increasing backoff
+                continue
+            raise
+    root, _ = os.path.splitext(path)
+    mp4 = root + ".mp4"
+    if os.path.exists(mp4):
+        video_path = mp4
+    else:
+        video_path = path
     # Browser-playability guard: WKWebView (Tauri on macOS) refuses to
     # decode VP9/AV1 video and Opus audio even when they're wrapped in an
     # mp4 container, and refuses .webm/.mkv outright. We probe the actual

backend/services/engine_routing.py

@@ -63,7 +63,21 @@ def resolve_routing(gpu_compat: tuple[str, ...], caps: HostCaps) -> RoutingResul
             "routing_reason": _caveat(caps),
         }
 
-    # 3. Host has an accelerator the engine lacks, but engine supports cpu
+    # 3. CPU-native engine (declares ONLY cpu) has nothing to fall back FROM,
+    #    so on ANY accelerator host it is benign cpu_only (neutral), never a
+    #    warn-tone "CPU fallback". This must precede the fallback rule below —
+    #    a ("cpu",) engine matches `"cpu" in targets` too, and would otherwise
+    #    be mis-classed cpu_fallback on a GPU/MPS host. (A cpu host reaches
+    #    rule 5 unchanged, keeping its DirectML note.) Engines that *could*
+    #    accelerate elsewhere (e.g. ("cuda", "cpu")) are untouched.
+    if fam != "cpu" and targets == ("cpu",):
+        return {
+            "effective_device": "cpu",
+            "routing_status": "cpu_only",
+            "routing_reason": None,
+        }
+
+    # 4. Host has an accelerator the engine lacks, but engine supports cpu
     #    → the no-silent-fallback signal.
     if fam != "cpu" and "cpu" in targets:
         if fam == "rocm" and "cuda" in targets and "rocm" not in targets:
@@ -76,7 +90,7 @@ def resolve_routing(gpu_compat: tuple[str, ...], caps: HostCaps) -> RoutingResul
             "routing_reason": reason,
         }
 
-    # 4. Genuine CPU-only host (or DirectML, which the probe reports as cpu)
+    # 5. Genuine CPU-only host (or DirectML, which the probe reports as cpu)
     #    and engine supports cpu → benign; must not warn or block.
     if fam == "cpu" and "cpu" in targets:
         reason = None
@@ -93,7 +107,7 @@ def resolve_routing(gpu_compat: tuple[str, ...], caps: HostCaps) -> RoutingResul
             "routing_reason": reason,
         }
 
-    # 5. Engine needs an accelerator this host lacks and has no cpu path.
+    # 6. Engine needs an accelerator this host lacks and has no cpu path.
     first = targets[0]
     return {
         "effective_device": first,

backend/services/llm_backend.py

@@ -67,8 +67,18 @@ class OpenAICompatBackend(LLMBackend):
     id = "openai-compat"
     display_name = "OpenAI-compatible (real OpenAI, Ollama, LM Studio, …)"
 
-    def __init__(self):
+    def __init__(self, provider=None):
+        """``provider``: optional ``llm_providers.Provider`` to bind this
+        instance to (LLM Skills per-skill routing). None keeps the historical
+        behavior — resolve the ACTIVE provider at call time."""
         self._client = None
+        self._provider = provider
+
+    def _resolve_provider(self):
+        if self._provider is not None:
+            return self._provider
+        from services import llm_providers
+        return llm_providers.active_provider()
 
     @classmethod
     def is_available(cls) -> tuple[bool, str]:
@@ -76,39 +86,50 @@ class OpenAICompatBackend(LLMBackend):
             import openai  # noqa: F401
         except ImportError:
             return False, "openai package missing (install with `pip install openai`)."
-        base_url = os.environ.get("TRANSLATE_BASE_URL")
-        api_key = (
-            os.environ.get("TRANSLATE_API_KEY")
-            or os.environ.get("OPENAI_API_KEY")
-            or ("local" if base_url else None)
-        )
-        if not api_key:
+        # Resolve through the provider registry — the active provider carries
+        # its own base_url/key/model. Legacy single-endpoint setups (a lone
+        # TRANSLATE_BASE_URL) resolve to the "custom" provider, so this stays
+        # backward-compatible with pre-registry configs.
+        from services import llm_providers
+        p = llm_providers.active_provider()
+        if p is None:
             return False, (
-                "No LLM configured. Set TRANSLATE_BASE_URL (+ TRANSLATE_API_KEY) to "
-                "point at OpenAI, Ollama (http://localhost:11434/v1), or any compatible host."
+                "No LLM configured. Add a provider key in Settings → LLM Providers "
+                "(OpenAI/OpenRouter/Groq/… or a local Ollama), or set "
+                "TRANSLATE_BASE_URL (+ TRANSLATE_API_KEY)."
             )
-        return True, "ready"
+        if not llm_providers.resolve_base_url(p):
+            return False, f"{p.display_name}: set a Base URL in Settings → LLM Providers."
+        if not llm_providers.has_key(p):
+            return False, f"{p.display_name}: add an API key in Settings → LLM Providers."
+        return True, f"ready ({p.display_name})"
 
     @property
     def model_name(self) -> str:
+        from services import llm_providers
+        p = self._resolve_provider()
+        if p is not None:
+            return llm_providers.resolve_model(p)
         return os.environ.get("TRANSLATE_MODEL", "gpt-4o-mini")
 
     def _get_client(self):
         if self._client is not None:
             return self._client
         from openai import OpenAI
-        base_url = os.environ.get("TRANSLATE_BASE_URL")
-        api_key = (
-            os.environ.get("TRANSLATE_API_KEY")
-            or os.environ.get("OPENAI_API_KEY")
-            or ("local" if base_url else None)
-        )
+        from services import llm_providers
+        p = self._resolve_provider()
+        if p is None:
+            raise RuntimeError("LLM not configured. See `is_available()` for the hint.")
+        base_url = llm_providers.resolve_base_url(p)
+        api_key = llm_providers.resolve_api_key(p)
         if not api_key:
             raise RuntimeError("LLM not configured. See `is_available()` for the hint.")
         kw = {"api_key": api_key}
         if base_url:
             kw["base_url"] = base_url
-        self._client = OpenAI(**kw)
+        # max_retries=0 so a 429 + Retry-After can't make one chat() sleep
+        # through the Autofit fit-pass wall-clock budget (speech_rate).
+        self._client = OpenAI(max_retries=0, **kw)
         return self._client
 
     def chat(self, *, system: str, user: str, timeout: Optional[float] = None) -> str:

backend/services/llm_providers.py

@@ -0,0 +1,356 @@
+"""LLM provider registry — the OpenAI-compatible providers OmniVoice can use
+for Cinematic / Autofit translation (and any future LLM feature).
+
+Every provider here speaks the OpenAI chat-completions shape, so a single
+client (`llm_backend.OpenAICompatBackend`) drives all of them — the only
+per-provider differences are ``base_url``, ``model``, and the API key. This
+module is the one place that knows those defaults and resolves the live value
+for the *active* provider.
+
+Resolution precedence for every field (key / base_url / model), highest first:
+    1. Environment variable  — power-user / `.env` override, wins always.
+    2. Encrypted settings store (UI-entered) — `settings_store.get_secret` for
+       keys, `get_text` for base_url/model overrides.
+    3. Built-in default from the table below.
+
+Local providers (Ollama, LM Studio) need no key — a "local" sentinel is used
+so the OpenAI client is happy. This keeps the local-first path fully offline:
+nothing is sent anywhere unless the user picks a remote provider *and* a
+feature gate (quality="cinematic"/"autofit") fires.
+
+Keys entered in the UI are stored **encrypted** (never in `.env`, never
+returned to the client). `.env` keys remain a valid override for CI / power
+users.
+"""
+from __future__ import annotations
+
+import os
+from dataclasses import dataclass
+from typing import Optional
+
+# Settings-store row names (non-secret overrides live in the plaintext table;
+# keys live in the encrypted secret table under ``llm_key.<id>``).
+_ACTIVE_PROVIDER_KEY = "llm.active_provider"
+_BASE_URL_KEY = "llm.base_url."   # + provider id
+_MODEL_KEY = "llm.model."         # + provider id
+SECRET_PREFIX = "llm_key."        # + provider id  → settings_store secret name
+
+
+@dataclass(frozen=True)
+class Provider:
+    id: str
+    display_name: str
+    default_base_url: str
+    default_model: str
+    # Env var names checked (in order) for the API key. First one set wins.
+    key_envs: tuple[str, ...] = ()
+    base_url_env: Optional[str] = None
+    model_env: Optional[str] = None
+    local: bool = False           # runs on the user's machine → no key, offline
+    # Key optional when a base_url is set (self-hosted OpenAI-compatible servers
+    # — vLLM, LM Studio behind a custom URL — often ignore the key). Preserves
+    # the pre-registry behaviour where a lone TRANSLATE_BASE_URL was usable
+    # keyless.
+    key_optional: bool = False
+    needs_account: bool = False   # Cloudflare: base_url needs an account id
+    account_env: Optional[str] = None
+    signup_url: str = ""
+    notes: str = ""
+
+
+# Order here is the display order in the settings page. OpenAI first (the
+# canonical), then the free/fast cloud providers from the shipped .env, then
+# the local engines, then Custom.
+_PROVIDERS: tuple[Provider, ...] = (
+    Provider("openai", "OpenAI", "https://api.openai.com/v1", "gpt-4o-mini",
+             key_envs=("OPENAI_API_KEY", "TRANSLATE_API_KEY"),
+             base_url_env="OPENAI_BASE_URL", model_env="OPENAI_MODEL",
+             signup_url="https://platform.openai.com/api-keys",
+             notes="GPT-4o / o-series. Highest quality; paid."),
+    Provider("openrouter", "OpenRouter", "https://openrouter.ai/api/v1",
+             "openai/gpt-4o-mini",
+             key_envs=("OPENROUTER_API_KEY",), base_url_env="OPENROUTER_BASE_URL",
+             model_env="OPENROUTER_MODEL",
+             signup_url="https://openrouter.ai/keys",
+             notes="One key, hundreds of models incl. free tiers."),
+    Provider("groq", "Groq", "https://api.groq.com/openai/v1",
+             "llama-3.3-70b-versatile",
+             key_envs=("GROQ_API_KEY",), base_url_env="GROQ_BASE_URL",
+             model_env="GROQ_MODEL", signup_url="https://console.groq.com/keys",
+             notes="Very fast Llama/Mixtral inference. Generous free tier."),
+    Provider("cerebras", "Cerebras", "https://api.cerebras.ai/v1",
+             "llama-3.3-70b",
+             key_envs=("CEREBRAS_API_KEY",), base_url_env="CEREBRAS_BASE_URL",
+             model_env="CEREBRAS_MODEL", signup_url="https://cloud.cerebras.ai",
+             notes="Fastest Llama inference. Free tier."),
+    Provider("google-ai", "Google AI (Gemini)",
+             "https://generativelanguage.googleapis.com/v1beta/openai",
+             "gemini-2.0-flash",
+             key_envs=("GOOGLE_AI_API_KEY",), base_url_env="GOOGLE_AI_BASE_URL",
+             model_env="GOOGLE_AI_MODEL",
+             signup_url="https://aistudio.google.com/app/apikey",
+             notes="Gemini via OpenAI-compatible endpoint. Free tier."),
+    Provider("mistral", "Mistral", "https://api.mistral.ai/v1",
+             "mistral-small-latest",
+             key_envs=("MISTRAL_API_KEY",), base_url_env="MISTRAL_BASE_URL",
+             model_env="MISTRAL_MODEL", signup_url="https://console.mistral.ai/api-keys",
+             notes="Strong multilingual models. Free tier."),
+    Provider("cohere", "Cohere", "https://api.cohere.ai/compatibility/v1",
+             "command-r-08-2024",
+             key_envs=("COHERE_API_KEY",), base_url_env="COHERE_BASE_URL",
+             model_env="COHERE_MODEL", signup_url="https://dashboard.cohere.com/api-keys",
+             notes="Command models; good for RAG/translation. Free trial keys."),
+    Provider("nvidia", "NVIDIA NIM", "https://integrate.api.nvidia.com/v1",
+             "meta/llama-3.3-70b-instruct",
+             key_envs=("NVIDIA_API_KEY",), base_url_env="NVIDIA_BASE_URL",
+             model_env="NVIDIA_MODEL", signup_url="https://build.nvidia.com",
+             notes="NIM-hosted open models. Free credits."),
+    Provider("github-models", "GitHub Models",
+             "https://models.github.ai/inference", "openai/gpt-4o-mini",
+             key_envs=("GITHUB_MODELS_API_KEY",), base_url_env="GITHUB_MODELS_BASE_URL",
+             model_env="GITHUB_MODELS_MODEL",
+             signup_url="https://github.com/settings/tokens",
+             notes="Uses a GitHub PAT. Free for dev, rate-limited."),
+    Provider("cloudflare", "Cloudflare Workers AI",
+             "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1",
+             "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
+             key_envs=("CLOUDFLARE_API_KEY",), base_url_env="CLOUDFLARE_BASE_URL",
+             model_env="CLOUDFLARE_MODEL", needs_account=True,
+             account_env="CLOUDFLARE_ACCOUNT_ID",
+             signup_url="https://dash.cloudflare.com/profile/api-tokens",
+             notes="Needs an Account ID. Free tier."),
+    Provider("huggingface", "Hugging Face", "https://router.huggingface.co/v1",
+             "meta-llama/Llama-3.3-70B-Instruct",
+             key_envs=("HUGGINGFACE_API_KEY", "HF_TOKEN"),
+             base_url_env="HUGGINGFACE_BASE_URL", model_env="HUGGINGFACE_MODEL",
+             signup_url="https://huggingface.co/settings/tokens",
+             notes="HF Inference router. Reuses your HF token."),
+    Provider("sambanova", "SambaNova", "https://api.sambanova.ai/v1",
+             "Meta-Llama-3.3-70B-Instruct",
+             key_envs=("SAMBANOVA_API_KEY",), base_url_env="SAMBANOVA_BASE_URL",
+             model_env="SAMBANOVA_MODEL", signup_url="https://cloud.sambanova.ai",
+             notes="Fast open models. Free tier."),
+    Provider("siliconflow", "SiliconFlow", "https://api.siliconflow.com/v1",
+             "Qwen/Qwen2.5-7B-Instruct",
+             key_envs=("SILICONFLOW_API_KEY",), base_url_env="SILICONFLOW_BASE_URL",
+             model_env="SILICONFLOW_MODEL", signup_url="https://siliconflow.com",
+             notes="Qwen/DeepSeek and more. Strong for CJK."),
+    Provider("ollama", "Ollama (local)", "http://localhost:11434/v1",
+             "llama3.1", local=True,
+             base_url_env="OLLAMA_BASE_URL", model_env="OLLAMA_MODEL",
+             signup_url="https://ollama.com",
+             notes="Fully offline. Run `ollama pull llama3.1` first."),
+    Provider("lmstudio", "LM Studio (local)", "http://localhost:1234/v1",
+             "local-model", local=True,
+             base_url_env="LMSTUDIO_BASE_URL", model_env="LMSTUDIO_MODEL",
+             signup_url="https://lmstudio.ai",
+             notes="Fully offline. Start the LM Studio local server."),
+    Provider("custom", "Custom (OpenAI-compatible)", "", "",
+             key_envs=("TRANSLATE_API_KEY",), base_url_env="TRANSLATE_BASE_URL",
+             model_env="TRANSLATE_MODEL", key_optional=True,
+             notes="Any OpenAI-compatible host. Set Base URL + Model (+ key)."),
+)
+
+_BY_ID: dict[str, Provider] = {p.id: p for p in _PROVIDERS}
+
+
+def all_providers() -> tuple[Provider, ...]:
+    return _PROVIDERS
+
+
+def get_provider(pid: str) -> Optional[Provider]:
+    return _BY_ID.get(pid)
+
+
+# ── Field resolution (env → store → default) ──────────────────────────────
+
+def _env_first(names: tuple[str, ...]) -> Optional[str]:
+    for n in names:
+        v = os.environ.get(n)
+        if v:
+            return v
+    return None
+
+
+def resolve_account_id(p: Provider) -> str:
+    """The Cloudflare-style account id: env override → stored → empty."""
+    from services import settings_store
+    return (
+        (p.account_env and os.environ.get(p.account_env))
+        or settings_store.get_text(f"llm.account.{p.id}")
+        or ""
+    )
+
+
+def resolve_base_url(p: Provider, *, substitute: bool = True) -> str:
+    """Resolve a provider's base URL (env → stored override → default).
+
+    ``substitute`` interpolates ``{account_id}`` for account-scoped providers
+    (Cloudflare) so the *client* gets a working URL. The UI passes
+    ``substitute=False`` so the field shows/saves the raw template — baking the
+    substituted value back into a stored override would freeze the URL and make
+    later account-id changes silently no-op (the bug this guards against).
+    """
+    from services import settings_store
+    val = (
+        (p.base_url_env and os.environ.get(p.base_url_env))
+        or settings_store.get_text(_BASE_URL_KEY + p.id)
+        or p.default_base_url
+    )
+    if substitute and p.needs_account and val and "{account_id}" in val:
+        val = val.replace("{account_id}", resolve_account_id(p))
+    return val or ""
+
+
+def resolve_model(p: Provider) -> str:
+    from services import settings_store
+    return (
+        (p.model_env and os.environ.get(p.model_env))
+        or settings_store.get_text(_MODEL_KEY + p.id)
+        or p.default_model
+    )
+
+
+def resolve_api_key(p: Provider) -> Optional[str]:
+    """Env key → encrypted stored key → 'local' sentinel for local/keyless."""
+    from services import settings_store
+    env_key = _env_first(p.key_envs)
+    if env_key:
+        return env_key
+    stored = settings_store.get_secret(SECRET_PREFIX + p.id)
+    if stored:
+        return stored
+    if p.local or (p.key_optional and resolve_base_url(p)):
+        return "local"  # self-hosted OpenAI-compatible servers ignore the key
+    return None
+
+
+def has_key(p: Provider) -> bool:
+    """True if a usable key is resolvable (local, or keyless-with-base_url)."""
+    if p.local:
+        return True
+    if _env_first(p.key_envs) or _key_in_store(p.id):
+        return True
+    return bool(p.key_optional and resolve_base_url(p))
+
+
+def _key_in_store(pid: str) -> bool:
+    from services import settings_store
+    return (SECRET_PREFIX + pid) in settings_store.list_secret_names()
+
+
+def is_configured(p: Provider) -> bool:
+    """Usable end-to-end: has a base_url (custom needs one set) and a key."""
+    if not resolve_base_url(p):
+        return False
+    return has_key(p)
+
+
+# ── Active provider selection ─────────────────────────────────────────────
+
+def active_provider_id() -> Optional[str]:
+    """The provider Cinematic/Autofit should use.
+
+    Precedence: env ``LLM_DEFAULT_PROVIDER`` → stored selection → first
+    configured provider → None. Legacy ``TRANSLATE_BASE_URL`` users with no
+    explicit selection resolve to ``custom`` (its envs are TRANSLATE_*).
+    """
+    from services import settings_store
+    env_pick = os.environ.get("LLM_DEFAULT_PROVIDER")
+    if env_pick and env_pick in _BY_ID:
+        return env_pick
+    stored = settings_store.get_text(_ACTIVE_PROVIDER_KEY)
+    if stored and stored in _BY_ID:
+        return stored
+    # Legacy: a lone TRANSLATE_BASE_URL means the old single-endpoint setup.
+    if os.environ.get("TRANSLATE_BASE_URL"):
+        return "custom"
+    # Auto-select only a provider with a real key. Local providers (Ollama/
+    # LM Studio) are *always* "configured" (no key needed) but we must NOT
+    # assume their server is running — they require an explicit selection.
+    for p in _PROVIDERS:
+        if not p.local and is_configured(p):
+            return p.id
+    return None
+
+
+def set_active_provider(pid: str) -> None:
+    from services import settings_store
+    if pid not in _BY_ID:
+        raise ValueError(f"unknown provider {pid!r}")
+    settings_store.set_text(_ACTIVE_PROVIDER_KEY, pid)
+
+
+def active_provider() -> Optional[Provider]:
+    pid = active_provider_id()
+    return _BY_ID.get(pid) if pid else None
+
+
+# ── UI + persistence helpers ──────────────────────────────────────────────
+
+def save_key(pid: str, api_key: str) -> None:
+    """Persist (encrypted) or clear an API key for a provider."""
+    from services import settings_store
+    if pid not in _BY_ID:
+        raise ValueError(f"unknown provider {pid!r}")
+    settings_store.set_secret(SECRET_PREFIX + pid, api_key or "")
+
+
+def save_overrides(pid: str, *, base_url: Optional[str] = None,
+                   model: Optional[str] = None,
+                   account_id: Optional[str] = None) -> None:
+    from services import settings_store
+    if pid not in _BY_ID:
+        raise ValueError(f"unknown provider {pid!r}")
+    p = _BY_ID[pid]
+    if base_url is not None:
+        bu = base_url.strip()
+        # Never freeze an override that equals the built-in default. Critical
+        # for account-templated URLs (Cloudflare): persisting the shown value
+        # would pin the base_url and stop later account-id edits from taking
+        # effect. Clearing (→ empty) falls the resolver back to the default
+        # template so substitution stays live. Also self-heals a stale override
+        # if a provider's default URL changes in a future release.
+        settings_store.set_text(_BASE_URL_KEY + pid, "" if bu == p.default_base_url else bu)
+    if model is not None:
+        settings_store.set_text(_MODEL_KEY + pid, model.strip())
+    if account_id is not None:
+        settings_store.set_text(f"llm.account.{pid}", account_id.strip())
+
+
+def _active_env_pin() -> Optional[str]:
+    """The provider id pinned by ``LLM_DEFAULT_PROVIDER`` (if set + valid)."""
+    pick = os.environ.get("LLM_DEFAULT_PROVIDER")
+    return pick if pick and pick in _BY_ID else None
+
+
+def describe(p: Provider) -> dict:
+    """Client-safe provider descriptor — NEVER includes the key material.
+
+    The ``*_from_env`` booleans mirror ``key_from_env`` so the UI can disable an
+    env-pinned field (and the make-active button) with an explainer instead of
+    letting the user edit a value the resolver will silently override. ``base_url``
+    is the RAW template (``substitute=False``) so an account-scoped default shows
+    ``{account_id}`` rather than a baked-in value; ``account_id`` is returned
+    separately for account-scoped providers so the field can round-trip.
+    """
+    d = {
+        "id": p.id,
+        "display_name": p.display_name,
+        "local": p.local,
+        "needs_account": p.needs_account,
+        "signup_url": p.signup_url,
+        "notes": p.notes,
+        "base_url": resolve_base_url(p, substitute=False),
+        "model": resolve_model(p),
+        "has_key": has_key(p),
+        "key_from_env": bool(_env_first(p.key_envs)),
+        "base_url_from_env": bool(p.base_url_env and os.environ.get(p.base_url_env)),
+        "model_from_env": bool(p.model_env and os.environ.get(p.model_env)),
+        "active_from_env": _active_env_pin() is not None,
+        "configured": is_configured(p),
+    }
+    if p.needs_account:
+        d["account_id"] = resolve_account_id(p)
+        d["account_from_env"] = bool(p.account_env and os.environ.get(p.account_env))
+    return d

backend/services/llm_skills.py

@@ -0,0 +1,304 @@
+"""LLM Skills registry — per-feature enable/route control for every LLM call.
+
+Every LLM-powered capability ("skill") in the backend is registered here, so
+the Settings → LLM Skills panel can (a) toggle it and (b) route it to a
+specific provider (a local Ollama/LM Studio vs a remote key) instead of
+everything riding the one global active provider.
+
+The five consumption points today:
+
+    cinematic_translation — services/translator.py (Cinematic + Autofit
+                            REFLECT/ADAPT rewrite; dub_translate quality gate)
+    slot_fitting          — services/speech_rate.py (trim/expand a line to its
+                            time slot; Autofit strict pass + /tools/rate-fit)
+    glossary_extract      — api/routers/glossary.py auto-extract
+    direction_parse       — services/director.py (natural-language direction →
+                            taxonomy tokens; /tools/direction + dub generate)
+    dictation_refinement  — services/refinement.py (dictation transcript
+                            cleanup on finals)
+
+Design rules:
+
+* **Disabled == unconfigured.** A disabled skill degrades through the exact
+  same path the feature takes today when no LLM is configured (Fast
+  translation fallback, refinement pass-through, heuristic direction parse,
+  no-llm slot fit, 503 on glossary auto-extract). No new degradation modes.
+* **Override > active > none.** A per-skill provider override (persisted in
+  settings_store) wins over the global active provider. No override → the
+  active provider, resolved exactly as before (so existing setups see zero
+  behavior change; all skills default to enabled with no override).
+* **Persistence** is two plaintext settings rows per skill:
+  ``llm_skill.<id>.enabled`` ("1"/"0", absent = enabled) and
+  ``llm_skill.<id>.provider`` (provider id, absent/empty = active provider).
+  Keys stay in the provider registry (encrypted) — nothing secret here.
+* ``OMNIVOICE_LLM_BACKEND=off`` remains the global kill switch: it also
+  silences skills routed through a per-skill override.
+"""
+from __future__ import annotations
+
+import logging
+import os
+from dataclasses import dataclass
+from typing import Any, Callable, Optional
+
+logger = logging.getLogger("omnivoice.llm_skills")
+
+_ENABLED_KEY = "llm_skill.{sid}.enabled"
+_PROVIDER_KEY = "llm_skill.{sid}.provider"
+
+_UNSET = object()
+
+
+@dataclass(frozen=True)
+class LLMSkill:
+    """A registered LLM consumption point. name/description resolve via the
+    frontend i18n layer (localization hard rule — no hardcoded UI text)."""
+
+    id: str
+    name_key: str
+    description_key: str
+
+
+def _skill(sid: str) -> LLMSkill:
+    return LLMSkill(
+        id=sid,
+        name_key=f"settings.llmskills_{sid}_name",
+        description_key=f"settings.llmskills_{sid}_desc",
+    )
+
+
+# Display order in the settings panel: the dub pipeline first (translation →
+# fit → glossary → direction), then dictation.
+_SKILLS: tuple[LLMSkill, ...] = (
+    _skill("cinematic_translation"),
+    _skill("slot_fitting"),
+    _skill("glossary_extract"),
+    _skill("direction_parse"),
+    _skill("dictation_refinement"),
+)
+
+_BY_ID: dict[str, LLMSkill] = {s.id: s for s in _SKILLS}
+
+
+def all_skills() -> tuple[LLMSkill, ...]:
+    return _SKILLS
+
+
+def get_skill(skill_id: str) -> Optional[LLMSkill]:
+    return _BY_ID.get(skill_id)
+
+
+# ── Persistence (settings_store text rows) ─────────────────────────────────
+
+
+def is_enabled(skill_id: str) -> bool:
+    """Skill toggle. Absent row = enabled (all skills default on)."""
+    from services import settings_store
+
+    raw = settings_store.get_text(_ENABLED_KEY.format(sid=skill_id))
+    return raw != "0"
+
+
+def provider_override(skill_id: str) -> Optional[str]:
+    """The per-skill provider id, or None when the skill follows the active
+    provider. A stored id that no longer exists in the registry reads as None
+    (stale override — resolution falls back to the active provider)."""
+    from services import llm_providers, settings_store
+
+    raw = (settings_store.get_text(_PROVIDER_KEY.format(sid=skill_id)) or "").strip()
+    if not raw:
+        return None
+    if llm_providers.get_provider(raw) is None:
+        logger.warning("llm_skills: stale provider override %r on %s — ignoring",
+                       raw, skill_id)
+        return None
+    return raw
+
+
+def configure_skill(skill_id: str, *, enabled: Optional[bool] = None,
+                    provider_override: Any = _UNSET) -> None:
+    """Persist a skill's toggle and/or provider routing.
+
+    ``provider_override``: omit to leave unchanged; ``None``/``""`` clears it
+    (skill follows the active provider); a provider id routes the skill there.
+    Raises KeyError for an unknown skill, ValueError for an unknown provider.
+    """
+    if skill_id not in _BY_ID:
+        raise KeyError(f"unknown LLM skill {skill_id!r}. Known: {sorted(_BY_ID)}")
+    from services import llm_providers, settings_store
+
+    if enabled is not None:
+        settings_store.set_text(_ENABLED_KEY.format(sid=skill_id),
+                                "1" if enabled else "0")
+    if provider_override is not _UNSET:
+        pid = (provider_override or "").strip()
+        if pid and llm_providers.get_provider(pid) is None:
+            raise ValueError(f"unknown provider {pid!r}")
+        settings_store.set_text(_PROVIDER_KEY.format(sid=skill_id), pid)
+
+
+# ── Resolution (override > active > none) ──────────────────────────────────
+
+
+@dataclass(frozen=True)
+class SkillResolution:
+    skill: LLMSkill
+    enabled: bool
+    provider: Optional[Any]      # llm_providers.Provider or None
+    source: str                  # "override" | "active" | "none"
+    ready: bool
+    reason: Optional[str]        # None | "disabled" | "no_provider" | "unconfigured"
+
+
+def resolve_skill(skill_id: str) -> SkillResolution:
+    """Resolve a skill's effective provider + ready status.
+
+    Precedence: per-skill override → global active provider → none. Ready
+    means enabled AND the effective provider is configured end-to-end.
+    Raises KeyError for an unknown skill.
+    """
+    skill = _BY_ID.get(skill_id)
+    if skill is None:
+        raise KeyError(f"unknown LLM skill {skill_id!r}. Known: {sorted(_BY_ID)}")
+    from services import llm_providers
+
+    enabled = is_enabled(skill_id)
+    override = provider_override(skill_id)
+    if override:
+        provider = llm_providers.get_provider(override)
+        source = "override"
+    else:
+        provider = llm_providers.active_provider()
+        source = "active" if provider is not None else "none"
+
+    if not enabled:
+        ready, reason = False, "disabled"
+    elif provider is None:
+        ready, reason = False, "no_provider"
+    elif not llm_providers.is_configured(provider):
+        ready, reason = False, "unconfigured"
+    else:
+        ready, reason = True, None
+    return SkillResolution(skill=skill, enabled=enabled, provider=provider,
+                           source=source, ready=ready, reason=reason)
+
+
+def effective_provider(skill_id: str) -> Optional[Any]:
+    """The provider a skill would call (override or active), or None."""
+    return resolve_skill(skill_id).provider
+
+
+# ── Client / backend construction ───────────────────────────────────────────
+
+
+@dataclass(frozen=True)
+class SkillClient:
+    """A ready-to-call OpenAI-compatible client bound to the skill's provider."""
+
+    client: Any        # openai.OpenAI
+    model: str
+    provider_id: str
+    timeout: float
+
+
+def _default_timeout() -> float:
+    try:
+        return float(os.environ.get("OMNIVOICE_LLM_TIMEOUT", "45"))
+    except ValueError:
+        return 45.0
+
+
+def resolve_skill_client(skill_id: str) -> Optional[SkillClient]:
+    """OpenAI-compat client + model for a skill, or None.
+
+    None when the skill is disabled, no provider resolves, the provider is
+    unconfigured, or the openai package is missing — callers treat None
+    exactly like "no LLM configured" (their existing degradation path).
+    Raises KeyError for an unknown skill (programming error, not user state).
+    """
+    res = resolve_skill(skill_id)
+    if not res.ready:
+        return None
+    try:
+        from openai import OpenAI
+    except ImportError:
+        logger.warning("openai package not installed — LLM skill %s unavailable.",
+                       skill_id)
+        return None
+    from services import llm_providers
+
+    api_key = llm_providers.resolve_api_key(res.provider)
+    if not api_key:
+        return None
+    kw: dict[str, Any] = {"api_key": api_key}
+    base_url = llm_providers.resolve_base_url(res.provider)
+    if base_url:
+        kw["base_url"] = base_url
+    # max_retries=0: a rate-limited provider returning 429 + a long Retry-After
+    # would otherwise let the SDK sleep+retry inside a single call, blowing the
+    # skill's wall-clock budget (the cinematic pass budget, the glossary call
+    # timeout) from inside one request. Fail fast — the per-call timeout and the
+    # pass-level budget are the only bounds we want. Mirrors OpenAICompatBackend.
+    return SkillClient(
+        client=OpenAI(max_retries=0, **kw),
+        model=llm_providers.resolve_model(res.provider),
+        provider_id=res.provider.id,
+        timeout=_default_timeout(),
+    )
+
+
+def skill_backend(skill_id: str, active: Optional[Callable[[], Any]] = None):
+    """LLMBackend for a skill — the drop-in for ``get_active_llm_backend()``.
+
+    * disabled skill → OffBackend (same object the no-LLM path returns today,
+      so every caller's ``id == "off"`` / ``isinstance(…, OffBackend)`` check
+      degrades identically);
+    * no override → the ``active`` callable (callers pass their module-local
+      ``get_active_llm_backend`` so existing monkeypatch seams keep working),
+      defaulting to ``llm_backend.get_active_llm_backend`` — the exact legacy
+      path, env/prefs overrides included;
+    * override → an OpenAICompatBackend bound to that provider, or OffBackend
+      when the provider is unconfigured, openai is missing, or the global
+      ``OMNIVOICE_LLM_BACKEND=off`` kill switch is set.
+    """
+    from services.llm_backend import OffBackend, OpenAICompatBackend
+
+    res = resolve_skill(skill_id)
+    if not res.enabled:
+        return OffBackend()
+    if res.source != "override":
+        if active is not None:
+            return active()
+        from services import llm_backend
+        return llm_backend.get_active_llm_backend()
+    if os.environ.get("OMNIVOICE_LLM_BACKEND") == "off":
+        return OffBackend()
+    if not res.ready:
+        return OffBackend()
+    try:
+        import openai  # noqa: F401
+    except ImportError:
+        return OffBackend()
+    return OpenAICompatBackend(provider=res.provider)
+
+
+# ── API descriptor ──────────────────────────────────────────────────────────
+
+
+def describe(skill_id: str) -> dict:
+    """Client-safe skill descriptor for GET /api/settings/llm-skills."""
+    res = resolve_skill(skill_id)
+    p = res.provider
+    return {
+        "id": res.skill.id,
+        "name_key": res.skill.name_key,
+        "description_key": res.skill.description_key,
+        "enabled": res.enabled,
+        "provider_override": provider_override(skill_id),
+        "provider": p.id if p is not None else None,
+        "provider_display_name": p.display_name if p is not None else None,
+        "provider_local": p.local if p is not None else None,
+        "provider_source": res.source,
+        "ready": res.ready,
+        "reason": res.reason,
+    }

backend/services/model_lifecycle.py

@@ -60,7 +60,7 @@ def list_loaded() -> dict:
         models.append({
             "id": "tts",
             "name": "OmniVoice TTS",
-            "checkpoint": os.environ.get("OMNIVOICE_MODEL", "k2-fsa/OmniVoice"),
+            "checkpoint": mm.resolve_omnivoice_checkpoint(),  # #693: effective checkpoint, not a leaked raw value
             "device": device,
             "vram_mb": round(_tts_vram_mb(), 1),
             "unloadable": True,

backend/services/model_manager.py

@@ -3,7 +3,7 @@ import time
 import asyncio
 import logging
 import threading
-from concurrent.futures import ThreadPoolExecutor
+from concurrent.futures import ThreadPoolExecutor, Executor
 
 # ── Lazy imports ─────────────────────────────────────────────────────
 # torch and OmniVoice are heavy (~2-3s import on Apple Silicon).
@@ -25,7 +25,16 @@ def _lazy_torch():
 def _lazy_omnivoice():
     global _OmniVoice
     if _OmniVoice is None:
-        from omnivoice.models.omnivoice import OmniVoice as _OV
+        try:
+            from omnivoice.models.omnivoice import OmniVoice as _OV
+        except ModuleNotFoundError:
+            # The venv's editable install is missing/broken (#564). main.py wires
+            # the source fallback at startup, but resolve it here too so the
+            # model-load path self-heals and logs the paths it searched.
+            from core.omnivoice_path import ensure_omnivoice_importable
+            _backend_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+            ensure_omnivoice_importable(_backend_dir, logger)
+            from omnivoice.models.omnivoice import OmniVoice as _OV
         _OmniVoice = _OV
     return _OmniVoice
 
@@ -35,17 +44,30 @@ from core.config import IDLE_TIMEOUT_SECONDS, CPU_POOL_WORKERS
 logger = logging.getLogger("omnivoice.model")
 
 # Per-TTS-job VRAM headroom estimate. OmniVoice's forward + autoregressive
-# decode peaks around 1.6 GB on a 24 kHz 8-second utterance; we budget 2.5 GB
-# to leave room for the ASR/diarization pipelines that run concurrently in
-# the same process. Tuned empirically — bumps to 3 GB if anyone reports OOM
-# at 16 GB on a multi-segment dub.
-_GPU_VRAM_PER_JOB_GB = 2.5
+# decode peaks around 1.6 GB, but the interactive clone path co-loads WhisperX
+# large-v3 ASR (~3 GB) to transcribe the reference, so a *concurrent* clone job
+# is realistically ~5 GB. The old 2.5 GB budget over-committed: an 8 GB card
+# (~7 GB free) got 2 workers, and two concurrent clone jobs blew past VRAM into
+# a sticky CUDA "illegal memory access" that aborts the whole backend process —
+# the wave of "Can't reach the local backend" crash reports on 8 GB GPUs
+# (#567/#570/#571/#580/#582/#583/#584). Budgeting 5 GB serializes to 1 worker on
+# ≤10 GB cards (no contention → no crash) while 16/24 GB cards still parallelize.
+# Power users override with OMNIVOICE_GPU_WORKERS.
+_GPU_VRAM_PER_JOB_GB = 5.0
 _GPU_WORKER_CAP = 4
 
-_gpu_pool_singleton: "ThreadPoolExecutor | None" = None
+_gpu_pool_singleton: "_ResilientGpuPool | None" = None
 _cpu_pool = ThreadPoolExecutor(max_workers=CPU_POOL_WORKERS)
 
 
+def _workers_for_free_vram(free_gb: float) -> int:
+    """GPU worker count for a given free-VRAM figure: free // per-job budget,
+    floored at 1 and capped at _GPU_WORKER_CAP. Pure so the sizing policy is
+    unit-tested without a GPU (the #567 crash hinged on this returning >1 on
+    8 GB cards)."""
+    return max(1, min(_GPU_WORKER_CAP, int(free_gb // _GPU_VRAM_PER_JOB_GB)))
+
+
 def _pick_gpu_workers() -> int:
     """Pick a sensible GPU worker count from the runtime environment.
 
@@ -68,7 +90,7 @@ def _pick_gpu_workers() -> int:
         if hasattr(torch, "cuda") and torch.cuda.is_available():
             free_bytes, _total = torch.cuda.mem_get_info()
             free_gb = free_bytes / (1024 ** 3)
-            workers = max(1, min(_GPU_WORKER_CAP, int(free_gb // _GPU_VRAM_PER_JOB_GB)))
+            workers = _workers_for_free_vram(free_gb)
             logger.info(
                 "GPU pool sized to %d worker(s) — %.1f GB free / %.1f GB per job (cap %d)",
                 workers, free_gb, _GPU_VRAM_PER_JOB_GB, _GPU_WORKER_CAP,
@@ -87,14 +109,82 @@ def _build_gpu_pool() -> ThreadPoolExecutor:
     return ThreadPoolExecutor(max_workers=workers, thread_name_prefix="gpu-pool")
 
 
-def _get_gpu_pool() -> ThreadPoolExecutor:
-    """Internal accessor. Same singleton as the module-level `_gpu_pool`
-    attribute, but resolvable from inside this module (Python's module
-    `__getattr__` only fires for unresolved lookups from *outside*).
+class _ResilientGpuPool(Executor):
+    """A stable, self-healing wrapper around the GPU `ThreadPoolExecutor`.
+
+    The crash this fixes (#589 #599): `_reset_gpu_pool()` shuts the pool down on
+    a model-load timeout, but consumers that captured the executor *object* at
+    import time (`from services.model_manager import _gpu_pool` at module level —
+    generation, dub_generate, dub_core, dub_translate, openai_compat) kept
+    submitting to the dead pool and got `RuntimeError: cannot schedule new
+    futures after shutdown` on the next generate/dub/translate.
+
+    Making `_gpu_pool` a single long-lived wrapper whose *inner* pool is swapped
+    means those references never go stale: every `submit()` resolves the live
+    pool, and a submit that races a shutdown rebuilds once and retries. Building
+    the inner pool stays lazy so we still size workers after torch's device
+    probe (the reason for the original `__getattr__` indirection).
+    """
+
+    def __init__(self):
+        self._pool: "ThreadPoolExecutor | None" = None
+        self._lock = threading.Lock()
+
+    def _live_pool(self) -> ThreadPoolExecutor:
+        pool = self._pool
+        if pool is None:
+            with self._lock:
+                if self._pool is None:
+                    self._pool = _build_gpu_pool()
+                pool = self._pool
+        return pool
+
+    def submit(self, fn, /, *args, **kwargs):
+        try:
+            return self._live_pool().submit(fn, *args, **kwargs)
+        except RuntimeError as e:
+            # "cannot schedule new futures after shutdown": the inner pool was
+            # reset (or torn down) under us. Rebuild once and retry so a stale
+            # caller self-heals instead of 500-ing. (Interpreter-shutdown races
+            # re-raise on the retry — we don't loop.)
+            if "shutdown" not in str(e).lower():
+                raise
+            with self._lock:
+                self._pool = _build_gpu_pool()
+                pool = self._pool
+            return pool.submit(fn, *args, **kwargs)
+
+    def reset(self) -> None:
+        """Abandon the current worker pool; the next submit builds a fresh one.
+
+        Python can't kill a thread wedged in a timed-out load, but dropping the
+        poisoned pool means a retry gets a clean worker instead of queueing
+        behind the wedged one. The wrapper identity is preserved, so references
+        held by importers stay valid.
+        """
+        with self._lock:
+            pool, self._pool = self._pool, None
+        if pool is not None:
+            try:
+                pool.shutdown(wait=False, cancel_futures=True)
+            except Exception:
+                pass
+
+    def shutdown(self, wait=True, *, cancel_futures=False):
+        with self._lock:
+            pool, self._pool = self._pool, None
+        if pool is not None:
+            pool.shutdown(wait=wait, cancel_futures=cancel_futures)
+
+
+def _get_gpu_pool() -> "_ResilientGpuPool":
+    """Internal accessor for the GPU pool singleton. Same object as the
+    module-level `_gpu_pool` attribute, but resolvable from inside this module
+    (Python's module `__getattr__` only fires for lookups from *outside*).
     """
     global _gpu_pool_singleton
     if _gpu_pool_singleton is None:
-        _gpu_pool_singleton = _build_gpu_pool()
+        _gpu_pool_singleton = _ResilientGpuPool()
     return _gpu_pool_singleton
 
 
@@ -108,6 +198,91 @@ def __getattr__(name: str):
         return _get_gpu_pool()
     raise AttributeError(f"module 'services.model_manager' has no attribute {name!r}")
 
+
+# ── GPU-job timeout guard (#730 class; residual #850/#802/#755 …) ─────
+# A blocking GPU job that wedges on a Windows+CUDA hang keeps occupying its
+# worker forever — run_in_executor can't cancel the thread. With a 1–2 worker
+# pool that starves *every* other request, so the next user action surfaces as
+# the misleading "Can't reach the local backend" even though the process is
+# alive. ASR/dub/model-load already bound+reset on hang (run_transcribe_guarded,
+# _reset_pool_on_wedge, _load_model_with_timeout); the TTS **generate** paths
+# (generation.py, tts_stream.py) were the last unguarded dispatch — and the
+# residual on-main reports all fail on generate:start (audio). This is the same
+# guard generalised so every GPU dispatch shares one recovery path.
+GPU_JOB_TIMEOUT_S = float(os.environ.get("OMNIVOICE_GENERATE_TIMEOUT_S", "300.0"))
+
+
+class GpuJobTimeoutError(TimeoutError):
+    """A GPU-pool job exceeded its wall-clock bound and was abandoned.
+
+    The backend is alive — the job was too heavy for the available compute
+    (most often a VRAM-starved GPU). Pool capacity is restored automatically by
+    resetting the pool; the message carries the durable fix.
+    """
+
+
+async def run_on_gpu_pool_guarded(fn, *, what: str = "GPU job",
+                                  timeout: float = GPU_JOB_TIMEOUT_S,
+                                  executor=None):
+    """Run blocking ``fn`` on the GPU pool with a hard wall-clock bound.
+
+    On timeout, ``reset()`` the pool (abandon the wedged worker so the next
+    submit gets a fresh one) and raise :class:`GpuJobTimeoutError`. ``fn`` must
+    be a zero-arg callable — wrap args with ``functools.partial`` at the call
+    site. Deliberately mirrors ``asr_backend.run_transcribe_guarded`` so every
+    GPU dispatch shares one bound+recover path (#730 class). Executors without
+    ``reset`` (a plain ThreadPoolExecutor in tests) still get the bound + error.
+    """
+    loop = asyncio.get_running_loop()
+    ex = executor if executor is not None else _get_gpu_pool()
+    fut = loop.run_in_executor(ex, fn)
+    try:
+        return await asyncio.wait_for(fut, timeout=timeout)
+    except asyncio.TimeoutError:
+        _reset = getattr(ex, "reset", None)
+        if callable(_reset):
+            try:
+                _reset()
+                logger.warning(
+                    "%s exceeded %.0fs — abandoned the GPU-pool worker to "
+                    "restore capacity (#730).", what, timeout,
+                )
+            except Exception:
+                logger.exception("GPU pool reset after %s timeout failed", what)
+        raise GpuJobTimeoutError(_timeout_guidance(what, timeout))
+
+
+def _timeout_guidance(what: str, timeout: float) -> str:
+    """Device-aware timeout message (#896): a CPU-only host must never be told
+    to "set the engine to CPU" or blamed on VRAM — on CPU the job is simply
+    compute-bound. GPU hosts keep the VRAM-contention guidance."""
+    family = "cuda"  # conservative default: GPU wording if the probe fails
+    try:
+        from core.device_caps import detect_host_caps
+        family = detect_host_caps().family
+    except Exception:  # noqa: BLE001 — guidance must never mask the timeout
+        pass
+    common = (
+        f"{what} exceeded {timeout:.0f}s and was abandoned — the backend is "
+        "running, but the job was too heavy for the available compute. "
+        "Capacity was restored automatically; "
+    )
+    if family == "cpu":
+        return common + (
+            "this machine renders on CPU, where long generations are "
+            "compute-bound. For a durable fix try shorter text or a lighter "
+            "engine (OmniVoice GGUF and Supertonic-3 are CPU-tuned). If you "
+            "expect very long single generations, raise "
+            "OMNIVOICE_GENERATE_TIMEOUT_S."
+        )
+    return common + (
+        "most often the GPU is VRAM-starved (a resident model and this job "
+        "contend for memory). For a durable fix try shorter text, a lighter "
+        "engine, or set the engine to CPU in Settings → Models. (Raise "
+        "OMNIVOICE_GENERATE_TIMEOUT_S for very long single generations.)"
+    )
+
+
 model = None  # type: ignore
 _model_lock = asyncio.Lock()
 _last_used = time.time()
@@ -218,6 +393,19 @@ def get_best_device():
         compatible, warning = check_device_compatibility()
         if not compatible:
             logger.warning(warning)
+            # #756: the GPU's compute capability isn't in this torch build's arch
+            # list, so CUDA kernels can't launch ("no kernel image is available
+            # for execution") — every generate would 500. Too-old (Pascal sm_61)
+            # and too-new (Blackwell sm_120 on pre-cu128 wheels) both land here.
+            # Fall back to CPU so the app WORKS (slowly) instead of dead-ending;
+            # OMNIVOICE_FORCE_CUDA=1 overrides for users who installed a matching
+            # torch and know the arch_list probe is wrong for their setup.
+            if not _env_flag("OMNIVOICE_FORCE_CUDA"):
+                logger.warning(
+                    "Falling back to CPU: this GPU is unsupported by the installed "
+                    "PyTorch build (set OMNIVOICE_FORCE_CUDA=1 to force CUDA anyway)."
+                )
+                return "cpu"
         return "cuda"
 
     # ── Intel Arc / discrete GPU via IPEX ────────────────────────────
@@ -449,6 +637,168 @@ def should_preload_tts_asr() -> bool:
     return _env_flag("OMNIVOICE_PRELOAD_TTS_ASR")
 
 
+def _is_incomplete_cache_error(exc: BaseException) -> bool:
+    """True when `exc` is the truncated-HF-cache class (#352 / #581).
+
+    transformers raises an OSError whose message contains "does not appear to
+    have a file named …" when the on-disk snapshot has config/tokenizer files
+    but no weight shard — the signature of an interrupted download. We match on
+    that phrase (stable across transformers 4.x/5.x) rather than the error type,
+    since the same OSError type covers unrelated I/O failures."""
+    return "does not appear to have a file named" in str(exc)
+
+
+def _hf_offline() -> bool:
+    """Respect HF's offline switches so repair never makes a network call the
+    user opted out of. `snapshot_download` would itself raise offline, but
+    checking up front lets us skip straight to the actionable message."""
+    return _env_flag("HF_HUB_OFFLINE") or _env_flag("TRANSFORMERS_OFFLINE")
+
+
+# Why the LAST _repair_model_cache run failed ("" when it succeeded / hasn't
+# run). #886: the "could not be auto-repaired" message used to drop the cause
+# entirely, so a mirror outage, offline mode, or a full disk all read the same.
+_last_repair_error: str = ""
+
+
+def _repair_failure_detail() -> str:
+    """One sanitized clause naming why auto-repair failed, or "" (#886).
+
+    Feeds user-facing messages (the generate 500 detail / model status), so it
+    goes through core.failure.sanitize — and because the cause text is now part
+    of the surfaced error, the shared HF-mirror hint (#874) fires on it when
+    the repair failed against an unreachable configured mirror."""
+    if not _last_repair_error:
+        return ""
+    try:
+        from core.failure import sanitize
+        cause = sanitize(_last_repair_error)
+    except Exception:
+        cause = _last_repair_error
+    return f" Auto-repair failed with: {cause}."
+
+
+def _repair_model_cache(checkpoint: str, *, force: bool = False) -> bool:
+    """Re-fetch a checkpoint's missing files in place and report success.
+
+    An interrupted download leaves the cache missing only some files;
+    `snapshot_download` resumes/fills exactly those (already-present, correctly
+    sized blobs are skipped by hash, so a near-complete cache repairs in
+    seconds and a complete one would no-op). Returns False — leaving the caller
+    to surface the actionable delete-and-reinstall message — when repair is
+    impossible (offline) or the re-fetch itself fails (no network, gated repo,
+    full disk). Never raises; repair is best-effort.
+
+    ``force=True`` passes ``force_download`` so the re-fetch replaces files that
+    are *present but corrupt* — a truncated/garbled blob that still has the right
+    size won't be re-fetched by the default resume (#739). It re-downloads the
+    whole snapshot, so it's the last resort the load path only reaches after a
+    plain resume-repair didn't fix the cache."""
+    global _last_repair_error
+    _last_repair_error = ""
+    if _hf_offline():
+        logger.warning(
+            "Model cache for %s is incomplete but HF offline mode is set — "
+            "cannot auto-repair.", checkpoint,
+        )
+        _last_repair_error = (
+            "Hugging Face offline mode is enabled (HF_HUB_OFFLINE/TRANSFORMERS_OFFLINE)"
+        )
+        return False
+    try:
+        from huggingface_hub import snapshot_download
+    except Exception as imp_err:  # pragma: no cover - huggingface_hub is a hard dep
+        logger.warning("Cannot import snapshot_download to repair cache: %s", imp_err)
+        _last_repair_error = f"{type(imp_err).__name__}: {imp_err}"
+        return False
+    dl_kwargs: dict = {"repo_id": checkpoint}
+    endpoint = os.environ.get("HF_ENDPOINT")
+    if endpoint:
+        dl_kwargs["endpoint"] = endpoint
+    if force:
+        # Replace present-but-corrupt blobs that resume would trust by size.
+        dl_kwargs["force_download"] = True
+    if os.name == "nt":
+        # Match the install path (download.py): avoid symlinks on Windows.
+        dl_kwargs["local_dir_use_symlinks"] = False
+
+    def _attempt() -> None:
+        """One snapshot_download, tolerating an hf_hub that rejects the optional
+        symlink knob. Lets real failures (network, gated repo, disk) propagate."""
+        try:
+            snapshot_download(**dl_kwargs)
+        except TypeError:
+            # Older/newer huggingface_hub may not accept local_dir_use_symlinks
+            # on a cache-only call — retry without the optional knob.
+            dl_kwargs.pop("local_dir_use_symlinks", None)
+            snapshot_download(**dl_kwargs)
+
+    # Bounded retries (#739): an incomplete cache *is* an interrupted download, so
+    # a single transient blip mid-repair shouldn't drop the user back to a manual
+    # delete-and-reinstall. snapshot_download resumes between attempts (present,
+    # correctly-sized blobs are skipped by hash), so each retry continues where
+    # the last left off — cheap and idempotent. Counts/backoff are env-tunable
+    # for restricted networks and kept fast (backoff=0) in tests.
+    try:
+        retries = max(1, int(os.environ.get("OMNIVOICE_MODEL_REPAIR_RETRIES", "3")))
+    except ValueError:
+        retries = 3
+    try:
+        backoff = max(0.0, float(os.environ.get("OMNIVOICE_MODEL_REPAIR_BACKOFF_S", "2")))
+    except ValueError:
+        backoff = 2.0
+
+    logger.info(
+        "Auto-repairing incomplete model cache for %s (up to %d attempt(s)) …",
+        checkpoint, retries,
+    )
+    for attempt in range(1, retries + 1):
+        try:
+            _attempt()
+            logger.info("Auto-repair of %s completed; retrying model load.", checkpoint)
+            return True
+        except Exception as e:
+            logger.warning(
+                "Auto-repair of %s attempt %d/%d failed: %s",
+                checkpoint, attempt, retries, e,
+            )
+            _last_repair_error = f"{type(e).__name__}: {e}"
+            if attempt < retries and backoff:
+                time.sleep(backoff * attempt)
+    return False
+
+
+_DEFAULT_OMNIVOICE_CHECKPOINT = "k2-fsa/OmniVoice"
+
+
+def resolve_omnivoice_checkpoint() -> str:
+    """Resolve the OmniVoice TTS checkpoint from ``OMNIVOICE_MODEL``, self-healing
+    a misconfigured value.
+
+    A valid checkpoint is either a HuggingFace repo id (``org/repo`` — contains a
+    ``/``) or an existing local directory. A bare token like ``"omnivoice"`` — a
+    TTS *engine id* that leaked into ``OMNIVOICE_MODEL`` (e.g. a stale pref/env) —
+    is neither, and would crash model load with *"omnivoice is not a local folder
+    and is not a valid model identifier listed on huggingface.co/models"* (#693).
+    Fall back to the default rather than 500 on every launch.
+    """
+    checkpoint = os.environ.get("OMNIVOICE_MODEL", _DEFAULT_OMNIVOICE_CHECKPOINT).strip()
+    if not checkpoint:
+        return _DEFAULT_OMNIVOICE_CHECKPOINT
+    # Honor a HF repo id (org/repo) or an EXPLICIT local path (absolute, or with
+    # a path separator). A bare token like "omnivoice" must NOT be treated as a
+    # local dir even if a cwd-relative folder happens to share its name — that
+    # is exactly the engine-id leak (#693), so self-heal to the default.
+    if "/" in checkpoint or "\\" in checkpoint or os.path.isabs(checkpoint):
+        return checkpoint
+    logger.warning(
+        "OMNIVOICE_MODEL=%r is not a HuggingFace repo id (org/repo) or a local "
+        "path — falling back to %s (#693).",
+        checkpoint, _DEFAULT_OMNIVOICE_CHECKPOINT,
+    )
+    return _DEFAULT_OMNIVOICE_CHECKPOINT
+
+
 def _load_model_sync():
     global model
     from utils.hf_progress import register_listener, unregister_listener
@@ -475,7 +825,7 @@ def _load_model_sync():
         OmniVoice = _lazy_omnivoice()
         device = get_best_device()
 
-        checkpoint = os.environ.get("OMNIVOICE_MODEL", "k2-fsa/OmniVoice")
+        checkpoint = resolve_omnivoice_checkpoint()
         _set_loading("loading_weights", f"Loading TTS weights on {device}…")
         logger.info("Loading OmniVoice model on device: %s", device)
         preload_asr = should_preload_tts_asr()
@@ -483,23 +833,67 @@ def _load_model_sync():
             logger.info("Preloading PyTorch Whisper with TTS model.")
         else:
             logger.info("Skipping PyTorch Whisper preload; ASR will load on demand.")
-        try:
-            _model = OmniVoice.from_pretrained(
+        def _load():
+            return OmniVoice.from_pretrained(
                 checkpoint, device_map=device, dtype=torch.float16, load_asr=preload_asr,
             )
+
+        try:
+            _model = _load()
         except OSError as e:
-            # #352: a truncated HF cache surfaces here as "does not appear to
-            # have a file named pytorch_model.bin or model.safetensors".
-            # Translate to an actionable message instead of the raw
-            # transformers error.
-            if "does not appear to have a file named" in str(e):
+            # #352 / #581: a truncated HF cache surfaces here as "does not
+            # appear to have a file named pytorch_model.bin or
+            # model.safetensors". Instead of dead-ending the user with a
+            # manual delete-and-reinstall instruction, try to self-repair: an
+            # interrupted download leaves the cache missing only some files,
+            # and snapshot_download() resumes/fills exactly those (a complete
+            # cache never reaches this branch, so the fast path is untouched).
+            if not _is_incomplete_cache_error(e):
+                raise
+            _set_loading("loading_weights", "Repairing incomplete model cache…")
+            if not _repair_model_cache(checkpoint):
                 raise RuntimeError(
                     f"The TTS model cache for {checkpoint} is incomplete "
-                    "(weights missing — usually an interrupted download). "
+                    "(weights missing — usually an interrupted download)."
+                    f"{_repair_failure_detail()} "
                     "Open Settings → Models, delete the OmniVoice TTS model, "
                     "and install it again."
                 ) from e
-            raise
+            _set_loading("loading_weights", f"Loading TTS weights on {device}…")
+            try:
+                _model = _load()
+            except OSError as e2:
+                # Resume-repair ran but the cache is still unusable. The usual
+                # cause beyond "repo genuinely lacks weights" is a blob that's
+                # present with the right size but corrupt — snapshot_download's
+                # resume trusts it and never re-fetches it (#739). Force a full
+                # re-download (replaces corrupt blobs) and retry once more before
+                # falling back to the manual delete-and-reinstall message.
+                if _is_incomplete_cache_error(e2):
+                    _set_loading("loading_weights", "Re-downloading model files…")
+                    if _repair_model_cache(checkpoint, force=True):
+                        try:
+                            _model = _load()
+                        except OSError as e3:
+                            raise RuntimeError(
+                                f"The TTS model cache for {checkpoint} is incomplete "
+                                "and could not be auto-repaired. Open Settings → "
+                                "Models, delete the OmniVoice TTS model, and install "
+                                "it again."
+                            ) from e3
+                    else:
+                        raise RuntimeError(
+                            f"The TTS model cache for {checkpoint} is incomplete and "
+                            f"could not be auto-repaired.{_repair_failure_detail()} "
+                            "Open Settings → Models, delete the OmniVoice TTS model, "
+                            "and install it again."
+                        ) from e2
+                else:
+                    raise RuntimeError(
+                        f"The TTS model cache for {checkpoint} is incomplete and "
+                        "could not be auto-repaired. Open Settings → Models, delete "
+                        "the OmniVoice TTS model, and install it again."
+                    ) from e2
 
         try:
             # plan-02 (#65): gate on Triton availability (+ user setting), not
@@ -549,9 +943,19 @@ def _load_model_sync():
         logger.info("OmniVoice model loaded successfully.")
         return _model
     except Exception as exc:
-        err_msg = str(exc)
+        # Surface an ACTIONABLE, sanitized error in /model/status (it's shown in
+        # the first-run System Check). build_failure classifies the cause and
+        # attaches a fix hint — e.g. a corrupted transformers install
+        # ([Errno 2] … modeling_*.py) now says "reinstall transformers" instead
+        # of an unhelpful raw path + "try restarting" — and strips the home dir.
+        try:
+            from core.failure import build_failure
+            _f = build_failure(exc, stage="model-load", include_diagnostic=False)
+            err_msg = _f["reason"] + (f" — {_f['hint']}" if _f.get("hint") else "")
+        except Exception:  # never let failure-formatting mask the real error
+            err_msg = str(exc)
         _set_loading("error", "Model loading failed", error=err_msg)
-        logger.error("Model loading failed: %s", err_msg)
+        logger.error("Model loading failed: %s", str(exc))
         raise
     finally:
         unregister_listener(lid)
@@ -571,19 +975,15 @@ def _model_load_timeout() -> float:
 
 
 def _reset_gpu_pool() -> None:
-    """Drop the GPU pool singleton so the next access builds a fresh one.
+    """Recover from a wedged/timed-out load by abandoning the GPU worker pool.
 
-    Python can't kill the thread stuck in a timed-out load, but abandoning the
-    poisoned single-worker pool means a *retry* gets a clean worker instead of
-    queueing forever behind the wedged one.
+    The resilient wrapper is kept (its identity is shared by every importer);
+    only its inner `ThreadPoolExecutor` is dropped, so the next submit builds a
+    fresh worker. This is what stops stale references from raising "cannot
+    schedule new futures after shutdown" after a reset (#589 #599).
     """
-    global _gpu_pool_singleton
-    pool, _gpu_pool_singleton = _gpu_pool_singleton, None
-    if pool is not None:
-        try:
-            pool.shutdown(wait=False, cancel_futures=True)
-        except Exception:
-            pass
+    if _gpu_pool_singleton is not None:
+        _gpu_pool_singleton.reset()
 
 
 async def _load_model_with_timeout():
@@ -634,8 +1034,11 @@ async def preload_model():
         return  # already loaded
     try:
         # Check if the required model checkpoint exists before attempting
-        # a heavy load that would fail and pollute startup logs.
-        checkpoint = os.environ.get("OMNIVOICE_MODEL", "k2-fsa/OmniVoice")
+        # a heavy load that would fail and pollute startup logs. Use the same
+        # resolver as the load path (#693) so a leaked engine id in
+        # OMNIVOICE_MODEL can't make this model_info() probe fail and silently
+        # disable warm-up (then the first /generate eats the full load).
+        checkpoint = resolve_omnivoice_checkpoint()
         try:
             from huggingface_hub import model_info
             model_info(checkpoint, timeout=5)

backend/services/pronunciation.py

@@ -145,3 +145,179 @@ def save_lexicon(path, lexicon: Optional[dict]) -> dict[str, str]:
         encoding="utf-8",
     )
     return clean
+
+
+# ── DB-backed global / per-language dictionary (Expressive-TTS Spec 01) ───────
+#
+# The JSON ``load_lexicon``/``save_lexicon`` above stay the per-project audiobook
+# override. THIS layer is the user-editable, DB-persisted, per-language default
+# dictionary surfaced in Settings → Pronunciation. Rows scoped ``language="*"``
+# apply to every request; a 2-letter language row applies only when the request
+# language's prefix matches (case-insensitive), so a German entry never fires on
+# an English render. Both layers are pure text substitution — they ride the same
+# ReDoS-safe ``apply_lexicon`` matcher, so every engine honors them.
+
+_ALL_LANG = "*"
+
+
+def _lang_prefix(language: Optional[str]) -> Optional[str]:
+    """Normalize a request language to a lowercase 2-letter prefix.
+
+    ``"Auto"``/``None``/``""`` → ``None`` (means "no language pin": only global
+    ``*`` rows apply, language-tagged rows are skipped, mirroring how the engines
+    treat an unset language). A value like ``"en-US"`` / ``"English"`` →
+    ``"en"`` (first two letters); matching against entries is on this prefix.
+    """
+    if not language:
+        return None
+    s = str(language).strip().lower()
+    if not s or s == "auto":
+        return None
+    return s[:2]
+
+
+def entries_for_language(entries, language: Optional[str]) -> dict[str, str]:
+    """Collapse DB rows into a ``{term: replacement}`` map for ``apply_lexicon``.
+
+    Filters to ``enabled`` rows whose scope is global (``*``) OR whose language
+    prefix matches the request language. Only the **respelling** path produces a
+    plain substitution here (Phase 1); IPA/CMU rows that carry no respelling are
+    skipped at this layer (they're handled — or honestly degraded — by the
+    engine-markup path, never silently mangling text). A language-specific row
+    overrides a global row with the same (case-folded) term, so a per-language
+    pronunciation can refine the global default.
+
+    ``entries`` is any iterable of mappings/rows with ``term``, ``replacement``,
+    ``type``, ``language``, ``enabled`` keys (a ``sqlite3.Row`` works directly).
+    """
+    req_prefix = _lang_prefix(language)
+    # Two passes so language rows win over global rows on the same term: collect
+    # global first, then overlay matching-language rows.
+    glob: dict[str, str] = {}
+    lang: dict[str, str] = {}
+    for e in entries:
+        try:
+            if not int(e["enabled"]):
+                continue
+        except (KeyError, IndexError, TypeError, ValueError):
+            continue
+        term = (e["term"] or "").strip()
+        if not term:
+            continue
+        etype = (e["type"] or "respelling").strip().lower()
+        replacement = e["replacement"] if e["replacement"] is not None else ""
+        # Phase 1: only respelling rows substitute text. IPA/CMU rows without a
+        # respelling fall through (Phase 2 lowers them to engine markup); we do
+        # NOT feed a raw IPA string into the grapheme stream.
+        if etype != "respelling":
+            continue
+        scope = (e["language"] or _ALL_LANG).strip() or _ALL_LANG
+        if scope == _ALL_LANG:
+            glob[term] = str(replacement)
+        else:
+            if req_prefix is not None and scope[:2].lower() == req_prefix:
+                lang[term] = str(replacement)
+    merged = dict(glob)
+    merged.update(lang)  # language rows override global on the same term
+    return merged
+
+
+# ── Inline one-off override:  [[term|replacement]]  /  [[replacement]] ─────────
+#
+# Double brackets are unambiguous against the single-bracket grammar
+# (``[voice:]``/``[pause]``/SSML-lite/``[Name]``): ``_VOICE_RE`` is
+# ``\[voice:([^\]\[]*)\]`` — it forbids inner brackets, so it can't span a
+# ``[[…]]``; the SSML-lite / pause vocabularies are closed literal sets that
+# ``[[…]]`` is not a member of. We resolve ``[[…]]`` BEFORE chunking so the
+# splitter never sees it. ReDoS-safe: ``\[\[[^\]]*\]\]`` is a bounded literal
+# class, no nested quantifier.
+#
+#   [[gif|jiff]]      → replaces the literal "gif" → "jiff" for this occurrence
+#   [[Nuh-VAD-uh]]    → the bracket content itself is spoken (brackets stripped)
+# Bounded inner repetition ({0,256}) keeps this strictly linear: ``[^\]]`` also
+# matches ``[``, so an unbounded run of ``[`` with no closing ``]]`` would let the
+# engine re-scan O(n) content from O(n) start positions (polynomial ReDoS). The
+# bound caps per-position work; an inline override is a short respelling, so 256
+# chars is far more than any real ``[[term|replacement]]`` needs.
+_INLINE_RE = re.compile(r"\[\[([^\]]{0,256})\]\]")
+
+
+def apply_inline_overrides(text: str) -> str:
+    """Resolve ``[[…]]`` one-off pronunciation overrides to plain spoken text.
+
+    ``[[term|replacement]]`` → ``replacement`` (the ``term`` half is a label for
+    the author; only the replacement is spoken). ``[[replacement]]`` (no pipe) →
+    ``replacement`` with the brackets stripped. Empty ``[[]]`` collapses away.
+    Applied once per occurrence; nothing persists. Single ``[…]`` tags are left
+    untouched (the regex requires a double bracket on both sides).
+    """
+    if not text or "[[" not in text:
+        return text or ""
+
+    def _repl(m: re.Match) -> str:
+        inner = m.group(1)
+        if "|" in inner:
+            inner = inner.split("|", 1)[1]
+        return inner
+
+    return _INLINE_RE.sub(_repl, text)
+
+
+def apply_pronunciation(
+    text: str,
+    entries=None,
+    language: Optional[str] = None,
+    *,
+    lexicon: Optional[dict] = None,
+) -> str:
+    """Apply the pronunciation dictionary + inline overrides to ``text``.
+
+    Order (load-bearing):
+      1. DB dictionary rows (``entries``) filtered to ``language`` + an optional
+         per-project ``lexicon`` JSON overlay (project wins on term conflict,
+         matching the audiobook layering). Both go through one ``apply_lexicon``
+         pass (longest-term-first, word-boundary aware, idempotent).
+      2. Inline ``[[…]]`` one-off overrides resolved last, so an inline override
+         always wins over any dictionary entry for that occurrence.
+
+    A falsy ``text`` / empty dictionary / no inline markers is a pass-through, so
+    legacy plain text is byte-identical.
+    """
+    if not text:
+        return text or ""
+    merged = entries_for_language(entries or [], language)
+    if lexicon:
+        # Project-local JSON overlays the DB defaults; project wins on conflict.
+        merged.update(normalize_lexicon(lexicon))
+    out = apply_lexicon(text, merged) if merged else text
+    return apply_inline_overrides(out)
+
+
+# ── DB load/save ──────────────────────────────────────────────────────────────
+
+def load_entries_from_db() -> list[dict]:
+    """Return every pronunciation_entries row as a list of plain dicts.
+
+    Import-light: the DB module is imported lazily so the pure-parser path (and
+    the audiobook JSON path) never pull in sqlite/config.
+    """
+    from core.db import db_conn
+
+    with db_conn() as conn:
+        rows = conn.execute(
+            "SELECT id, term, replacement, type, language, enabled, created_at "
+            "FROM pronunciation_entries ORDER BY created_at ASC, id ASC"
+        ).fetchall()
+    return [dict(r) for r in rows]
+
+
+def load_dict_for_request(language: Optional[str] = None) -> dict[str, str]:
+    """Convenience: DB rows → ``{term: replacement}`` for a request language.
+
+    Returns ``{}`` (a no-op for ``apply_pronunciation``) if the table is absent
+    or the DB can't be opened — pronunciation is never allowed to break synth.
+    """
+    try:
+        return entries_for_language(load_entries_from_db(), language)
+    except Exception:  # noqa: BLE001 — table missing / DB locked → no-op
+        return {}

backend/services/refinement.py

@@ -19,13 +19,69 @@ Two tiers, both applied only to FINAL transcripts (never partials):
 
 from __future__ import annotations
 
+import asyncio
 import json
 import logging
+import os
 import re
+import time
 from dataclasses import dataclass
 
 logger = logging.getLogger("omnivoice.refinement")
 
+# Hard wall-clock budget (seconds) for a single dictation refinement LLM call.
+# The dictation FINAL must never be delayed longer than this by a slow or dead
+# LLM endpoint — refinement is best-effort and falls back to the unrefined
+# (but polished) text on timeout. 4s keeps a healthy local model (Ollama /
+# LM Studio, sub-second on the tiny cleanup prompt) fully usable while turning
+# the old worst case — a placeholder/dead endpoint blocking the send ~51s until
+# the widget's 15s fallback fired — into a bounded ~4s at most. Env-tunable so
+# power users on a slow local LLM can raise it. Guarded by the regression tests
+# in tests/backend/services/test_refinement_llm.py and tests/test_capture_ws.py.
+_DEFAULT_REFINE_TIMEOUT_S = 4.0
+
+
+def _refine_timeout_s() -> float:
+    """The refinement LLM budget in seconds (OMNIVOICE_REFINE_TIMEOUT_S).
+
+    Falls back to :data:`_DEFAULT_REFINE_TIMEOUT_S` on an unset/invalid/non-
+    positive value so a bad env var can never disable the bound."""
+    raw = os.environ.get("OMNIVOICE_REFINE_TIMEOUT_S", "")
+    try:
+        v = float(raw)
+        if v > 0:
+            return v
+    except (TypeError, ValueError):
+        pass
+    return _DEFAULT_REFINE_TIMEOUT_S
+
+
+# Most-recent refinement outcome, so the Settings panel can tell the user when a
+# configured LLM is actually failing/timing out (the honesty layer behind the
+# `llm_ready` flag, which only means "an endpoint is configured"). Best-effort,
+# process-local, cleared on success.
+_last_refine_status: dict | None = None
+
+
+def _note_refine_status(*, ok: bool, reason: str | None = None) -> None:
+    global _last_refine_status
+    _last_refine_status = {"ok": bool(ok), "reason": reason, "at": time.time()}
+
+
+def get_last_refine_status() -> dict | None:
+    """The last refinement outcome as ``{ok, reason, at}`` or None if refinement
+    hasn't run this session. ``ok=False`` with ``reason`` ("timeout" or a short
+    error string) means a configured LLM failed the most recent final."""
+    return dict(_last_refine_status) if _last_refine_status else None
+
+
+def _short_reason(exc: Exception) -> str:
+    """A compact, non-leaky label for a refinement failure (for the UI hint)."""
+    name = type(exc).__name__
+    if "Timeout" in name or "timeout" in str(exc).lower():
+        return "timeout"
+    return name
+
 # A token (or unit) must repeat at least this many times consecutively to be
 # treated as an STT artifact. Rhetorical repetition ("no, no, no, no, no" —
 # five repeats) stays below the threshold and survives.
@@ -248,6 +304,19 @@ REFINEMENT_EXAMPLES: list[tuple[str, str]] = [
 # settings_store key holding the user's refinement config (plain JSON).
 _SETTINGS_KEY = "dictation_refinement"
 
+# LLM Skills registry id — Settings → LLM Skills can disable refinement's LLM
+# use or route it to a specific provider. Disabled == identical pass-through
+# (the same path as "no LLM configured").
+_SKILL_ID = "dictation_refinement"
+
+
+def _skill_llm():
+    """The skill-resolved backend (OffBackend when disabled/unconfigured)."""
+    from services import llm_skills
+    from services.llm_backend import get_active_llm_backend
+
+    return llm_skills.skill_backend(_SKILL_ID, active=get_active_llm_backend)
+
 
 def get_refinement_config() -> dict:
     """Read the persisted config: {auto, smart_cleanup, self_correction,
@@ -274,43 +343,97 @@ def set_refinement_config(cfg: dict) -> dict:
     return merged
 
 
-def refine_transcript(transcript: str, flags: RefinementFlags | None = None) -> str:
+def refine_transcript(
+    transcript: str,
+    flags: RefinementFlags | None = None,
+    *,
+    timeout_s: float | None = None,
+) -> str:
     """Run the transcript through the configured LLM. Raises on failure —
-    callers decide the fallback (maybe_refine swallows into pass-through)."""
-    from services.llm_backend import get_active_llm_backend
+    callers decide the fallback (maybe_refine swallows into pass-through).
 
+    The LLM HTTP call is bounded by ``timeout_s`` (default: the refinement
+    budget) so a dead/slow endpoint can't tie the call up for the client's full
+    45s LLM timeout — the class of stall this whole module guards against."""
     flags = flags or RefinementFlags()
-    backend = get_active_llm_backend()
+    backend = _skill_llm()
     messages = [{"role": "system", "content": build_refinement_prompt(flags)}]
     for user_turn, assistant_turn in REFINEMENT_EXAMPLES:
         messages.append({"role": "user", "content": user_turn})
         messages.append({"role": "assistant", "content": assistant_turn})
     messages.append({"role": "user", "content": transcript})
-    return backend.chat_messages(messages=messages).strip()
+    budget = timeout_s if timeout_s is not None else _refine_timeout_s()
+    return backend.chat_messages(messages=messages, timeout=budget).strip()
 
 
-def maybe_refine(transcript: str) -> str | None:
+def maybe_refine(transcript: str, *, timeout_s: float | None = None) -> str | None:
     """Best-effort refinement for the dictation final path.
 
     Returns the refined text, or None when refinement is off, no LLM
     backend is configured, the result is empty, or anything fails — the
-    raw transcript always stands. Never raises.
+    raw transcript always stands. Never raises. Records the outcome via
+    :func:`get_last_refine_status` so the UI can flag a failing LLM.
+
+    Blocking (network I/O); the WS/REST callers run it off-thread. Prefer
+    :func:`maybe_refine_async` on the live-dictation path — it adds the hard
+    wall-clock bound so a slow endpoint can never delay the ``final`` send.
     """
     if not transcript or not transcript.strip():
         return None
+    cfg = get_refinement_config()
+    if not cfg.get("auto", True):
+        return None
+    backend = _skill_llm()
+    if backend.id == "off":
+        # No LLM configured — or the dictation_refinement skill is disabled /
+        # routed to an unconfigured provider — is not a failure. Leave the last
+        # status untouched (same pass-through as today).
+        return None
     try:
-        cfg = get_refinement_config()
-        if not cfg.get("auto", True):
-            return None
-        from services.llm_backend import get_active_llm_backend
-
-        backend = get_active_llm_backend()
-        if backend.id == "off":
-            return None
-        refined = refine_transcript(transcript, RefinementFlags.from_dict(cfg))
+        refined = refine_transcript(
+            transcript, RefinementFlags.from_dict(cfg), timeout_s=timeout_s
+        )
         if not refined:
             return None
+        _note_refine_status(ok=True)
         return refined
     except Exception as e:  # noqa: BLE001 — pass-through is the contract
         logger.warning("Dictation refinement skipped: %s", e)
+        _note_refine_status(ok=False, reason=_short_reason(e))
+        return None
+
+
+async def maybe_refine_async(
+    transcript: str, *, timeout_s: float | None = None
+) -> str | None:
+    """Async, hard-time-bounded refinement for the live-dictation final path.
+
+    Runs :func:`maybe_refine` off-thread under a hard ``OMNIVOICE_REFINE_TIMEOUT_S``
+    (~4s) budget so a slow or dead LLM endpoint can NEVER block the caller — and
+    therefore the dictation ``final`` send — longer than the budget. On timeout
+    (or any failure) it returns None and the raw, already-polished transcript
+    stands. Never raises.
+
+    ``asyncio.wait_for`` can't cancel the worker thread, but the LLM call it runs
+    is itself bounded to the same budget (see :func:`refine_transcript`), so an
+    orphaned thread unwinds shortly after rather than lingering the full 45s.
+    """
+    if not transcript or not transcript.strip():
+        return None
+    budget = timeout_s if timeout_s is not None else _refine_timeout_s()
+    try:
+        return await asyncio.wait_for(
+            asyncio.to_thread(maybe_refine, transcript, timeout_s=budget),
+            timeout=budget,
+        )
+    except asyncio.TimeoutError:
+        logger.warning(
+            "Dictation refinement exceeded its %.1fs budget — sending the "
+            "unrefined final (set OMNIVOICE_REFINE_TIMEOUT_S to adjust).", budget,
+        )
+        _note_refine_status(ok=False, reason="timeout")
+        return None
+    except Exception as e:  # noqa: BLE001 — best-effort; the raw final stands
+        logger.warning("Dictation refinement failed: %s", e)
+        _note_refine_status(ok=False, reason=_short_reason(e))
         return None

backend/services/segmentation.py

@@ -542,3 +542,146 @@ def assign_speakers_heuristic(segments: List[dict]) -> List[dict]:
         s["speaker_id"] = f"Speaker {current}"
         last_end = s["end"]
     return segments
+
+
+# ── Speaker-aware re-split (#486) ────────────────────────────────────────────
+#
+# Segmentation runs BEFORE diarization and groups words by sentence/duration
+# only, so one segment can span two speakers' turns. assign_speakers_* then only
+# *relabels* each segment with its majority speaker — the boundary is lost and a
+# two-speaker exchange reads as one line. This pass re-splits such a segment at
+# the word-level speaker boundary, after diarization.
+#
+# Hard invariant (the single-speaker no-regression guarantee): a segment whose
+# words all map to ONE speaker is returned byte-for-byte unchanged — same dict,
+# id, text, start, end — so single-speaker dubs and their timing never move.
+
+def _word_speaker(w: "Word", turns: Sequence[tuple]) -> Optional[str]:
+    """Majority-overlap speaker label for a word; midpoint membership as a
+    fallback; ``None`` when the word has no diarization coverage at all."""
+    acc: dict = {}
+    for ts, te, label in turns:
+        left = max(w.start, ts)
+        right = min(w.end, te)
+        if right > left:
+            acc[label] = acc.get(label, 0.0) + (right - left)
+    if acc:
+        return max(acc.items(), key=lambda kv: kv[1])[0]
+    mid = (w.start + w.end) / 2.0
+    for ts, te, label in turns:
+        if ts <= mid <= te:
+            return label
+    return None
+
+
+def _fill_and_smooth(labels: List[Optional[str]]) -> List[Optional[str]]:
+    """Forward/back-fill gaps (words with no coverage inherit a neighbor) and
+    smooth single-word flips, so one mis-attributed word inside a speaker's run
+    (diarization noise) doesn't trigger a spurious split."""
+    out = list(labels)
+    n = len(out)
+    last = None
+    for i in range(n):
+        if out[i] is None:
+            out[i] = last
+        else:
+            last = out[i]
+    nxt = None
+    for i in range(n - 1, -1, -1):
+        if out[i] is None:
+            out[i] = nxt
+        else:
+            nxt = out[i]
+    for i in range(1, n - 1):
+        if out[i] != out[i - 1] and out[i - 1] == out[i + 1]:
+            out[i] = out[i - 1]
+    return out
+
+
+def _resplit_core(
+    segments: List[dict], words: Sequence["Word"], turns: Sequence[tuple],
+) -> List[dict]:
+    """Split each segment that spans >1 speaker at the word-level boundary.
+
+    ``turns`` is a normalised list of ``(start, end, speaker_label)``. Single-
+    speaker segments are passed through untouched. Pieces keep the segment's
+    outer start/end (preserving any onset-snap) and use word times for interior
+    boundaries, so the pieces exactly cover the original span.
+    """
+    if not turns or not words:
+        return segments
+    ordered = sorted(words, key=lambda w: (w.start, w.end))
+    out: List[dict] = []
+    for seg in segments:
+        s0, s1 = seg["start"], seg["end"]
+        seg_words = [w for w in ordered if min(w.end, s1) - max(w.start, s0) > 1e-6]
+        if len(seg_words) < 2:
+            out.append(seg)
+            continue
+        labels = _fill_and_smooth([_word_speaker(w, turns) for w in seg_words])
+        if len({l for l in labels if l is not None}) <= 1:
+            out.append(seg)  # single speaker (or unknown) → byte-for-byte unchanged
+            continue
+        runs: List[tuple] = []
+        for w, label in zip(seg_words, labels):
+            if runs and runs[-1][0] == label:
+                runs[-1][1].append(w)
+            else:
+                runs.append((label, [w]))
+        n_runs = len(runs)
+        piece_no = 0
+        for k, (label, ws) in enumerate(runs):
+            text = _clean(" ".join(w.text for w in ws))
+            if not text:
+                continue
+            piece = dict(seg)
+            piece["text"] = text
+            piece["start"] = s0 if k == 0 else ws[0].start
+            piece["end"] = s1 if k == n_runs - 1 else ws[-1].end
+            if label:
+                piece["speaker_id"] = label
+            if piece_no > 0:
+                piece["id"] = f"{seg.get('id', 'seg')}-{piece_no}"
+                if "text_original" in piece:
+                    piece["text_original"] = text
+            elif "text_original" in piece:
+                piece["text_original"] = text
+            out.append(piece)
+            piece_no += 1
+    return out
+
+
+def _diar_speaker_label(raw) -> str:
+    """``SPEAKER_00`` → ``Speaker 1`` (mirrors assign_speakers_from_diarization)."""
+    try:
+        return f"Speaker {int(str(raw).split('_')[-1]) + 1}"
+    except (ValueError, AttributeError):
+        return str(raw)
+
+
+def resplit_segments_by_diarization(
+    segments: List[dict], words: Sequence["Word"], diarization,
+) -> List[dict]:
+    """Speaker-aware re-split using a pyannote diarization result (#486)."""
+    turns = [
+        (turn.start, turn.end, _diar_speaker_label(spk))
+        for turn, _, spk in diarization.itertracks(yield_label=True)
+    ]
+    return _resplit_core(segments, words, turns)
+
+
+def resplit_segments_by_turns(
+    segments: List[dict], words: Sequence["Word"], turns: Sequence[dict],
+) -> List[dict]:
+    """Speaker-aware re-split using inline ASR speaker turns (FunASR cam++).
+
+    ``speaker`` is used verbatim (FunASR already labels ``"Speaker N"``), matching
+    :func:`assign_speakers_from_turns`."""
+    norm = [
+        (t["start"], t["end"], t["speaker"])
+        for t in (turns or [])
+        if t.get("speaker") is not None
+        and t.get("start") is not None
+        and t.get("end") is not None
+    ]
+    return _resplit_core(segments, words, norm)

backend/services/settings_store.py

@@ -108,6 +108,107 @@ def clear_hf_token() -> None:
         conn.execute("DELETE FROM settings WHERE key = ?", (_TOKEN_KEY,))
 
 
+# ── Generic encrypted secrets (LLM provider API keys, future tokens) ───────
+# The HF token got the first bespoke encrypted row; the LLM-providers feature
+# needs the *same* at-rest protection for a dozen provider keys. Rather than
+# copy the Fernet dance per provider, expose generic secret helpers. Rows are
+# namespaced with the ``secret.`` prefix so a misrouted ``get_text`` on a
+# secret key returns opaque ciphertext (defence in depth), and so plaintext
+# ``settings`` rows can never collide with a secret. Same InvalidToken →
+# None degrade as the HF path (install moved across machines → fall back to
+# env), same per-install key.
+_SECRET_PREFIX = "secret."
+
+
+def _secret_key_name(name: str) -> str:
+    if not name or not isinstance(name, str):
+        raise ValueError(f"secret name must be a non-empty string, got {name!r}")
+    if name == _TOKEN_KEY or name.startswith(_SECRET_PREFIX):
+        raise ValueError(f"invalid secret name {name!r}")
+    return f"{_SECRET_PREFIX}{name}"
+
+
+def get_secret(name: str) -> Optional[str]:
+    """Return a decrypted secret (e.g. an LLM provider API key), or None.
+
+    Mirrors :func:`get_hf_token`: on decrypt failure (install migrated across
+    machines) or any SQLite error, log and return None so callers fall back to
+    env / provider defaults instead of crashing.
+    """
+    from core.db import db_conn
+
+    key = _secret_key_name(name)
+    try:
+        with db_conn() as conn:
+            row = conn.execute(
+                "SELECT value FROM settings WHERE key = ?", (key,)
+            ).fetchone()
+        if row is None or not row[0]:
+            return None
+        try:
+            from cryptography.fernet import InvalidToken
+        except ImportError:  # pragma: no cover — dep should always be present
+            logger.error("cryptography unavailable; cannot decrypt secret %s", name)
+            return None
+        try:
+            return _fernet().decrypt(row[0].encode("ascii")).decode("utf-8")
+        except InvalidToken:
+            logger.warning(
+                "Stored secret %r failed to decrypt (install moved across "
+                "machines or salt tampered) — falling back to env/default.", name,
+            )
+            return None
+    except Exception:
+        logger.exception("settings_store.get_secret(%s): SQLite read failed", name)
+        return None
+
+
+def set_secret(name: str, value: str) -> None:
+    """Persist an encrypted secret. Empty value clears the row."""
+    if not value:
+        clear_secret(name)
+        return
+    from core.db import db_conn
+
+    key = _secret_key_name(name)
+    blob = _fernet().encrypt(value.encode("utf-8")).decode("ascii")
+    with db_conn() as conn:
+        conn.execute(
+            "INSERT OR REPLACE INTO settings(key, value, updated_at) "
+            "VALUES (?, ?, ?)",
+            (key, blob, time.time()),
+        )
+
+
+def clear_secret(name: str) -> None:
+    """Remove a secret row (salt row preserved, like clear_hf_token)."""
+    from core.db import db_conn
+
+    key = _secret_key_name(name)
+    with db_conn() as conn:
+        conn.execute("DELETE FROM settings WHERE key = ?", (key,))
+
+
+def list_secret_names() -> list[str]:
+    """Return the bare names of all stored secrets (no values, no ciphertext).
+
+    Lets the LLM-providers settings API report *which* providers have a key
+    configured without ever decrypting or returning the key material.
+    """
+    from core.db import db_conn
+
+    try:
+        with db_conn() as conn:
+            rows = conn.execute(
+                "SELECT key FROM settings WHERE key LIKE ?",
+                (f"{_SECRET_PREFIX}%",),
+            ).fetchall()
+        return [r[0][len(_SECRET_PREFIX):] for r in rows if r and r[0]]
+    except Exception:
+        logger.exception("settings_store.list_secret_names: SQLite read failed")
+        return []
+
+
 # ── Non-secret text settings ──────────────────────────────────────────────
 # Plan 01-02 Task 4 (INST-12): the Performance panel needs to persist a
 # boolean toggle (`perf.torch_compile_disabled`). It is NOT a secret — no
@@ -128,7 +229,8 @@ def get_text(key: str, default: Optional[str] = None) -> Optional[str]:
     looking like opaque bytes — callers MUST use `get_hf_token()` for
     secrets and only ever pass non-secret keys to `get_text()`.
     """
-    if key == _TOKEN_KEY:  # defence in depth — never let a misrouted call leak ciphertext
+    if key == _TOKEN_KEY or key.startswith(_SECRET_PREFIX):
+        # defence in depth — never let a misrouted call leak ciphertext
         return default
     from core.db import db_conn
 
@@ -150,10 +252,10 @@ def set_text(key: str, value: str) -> None:
 
     Use for non-secret config only. For tokens, use `set_hf_token()`.
     """
-    if key == _TOKEN_KEY:
+    if key == _TOKEN_KEY or key.startswith(_SECRET_PREFIX):
         raise ValueError(
-            "set_text refuses to write to the encrypted hf_token row; "
-            "use set_hf_token() for secrets"
+            "set_text refuses to write to an encrypted secret row; "
+            "use set_hf_token()/set_secret() for secrets"
         )
     from core.db import db_conn
 

backend/services/sherpa_dictation.py

@@ -0,0 +1,334 @@
+"""
+sherpa-onnx live-dictation ASR backend.
+
+Adds the k2-fsa/sherpa-onnx ONNX runtime as a *dictation* engine alongside the
+existing Whisper/NeMo family — without touching any of them. The whole point of
+this engine is **live, faster-than-real-time dictation on CPU**:
+
+  • STREAMING models (OnlineRecognizer) emit partial text frame-by-frame as the
+    user speaks, finalising on sherpa's built-in endpoint (silence) detection.
+  • OFFLINE models (OfflineRecognizer) re-transcribe a growing buffer on a short
+    cadence so the user still sees live partials, finalising on EOF/silence.
+
+CPU provider only (strict cross-platform-default parity rule): identical
+behaviour on macOS arm64+x86_64, Windows x64, Linux. No CUDA dependency.
+
+Model weights are the small int8 ONNX checkpoints published under
+``csukuangfj/`` on HuggingFace; they download on first use through the same HF
+cache the rest of the app uses (``snapshot_download``). Exact asset filenames
+were verified against the live HF repo trees (see ``_MODELS`` below) — the
+streaming zipformer repos use the plain ``encoder-epoch-99-avg-1.int8.onnx``
+naming, NOT a ``-chunk-16-left-64`` variant.
+"""
+from __future__ import annotations
+
+import logging
+import os
+from dataclasses import dataclass, field
+
+logger = logging.getLogger("omnivoice.asr.sherpa")
+
+# CPU only — strict cross-platform default-parity rule. Overridable for
+# power users on a verified GPU build, but the default never diverges.
+_PROVIDER = os.environ.get("OMNIVOICE_SHERPA_ASR_PROVIDER", "cpu")
+_NUM_THREADS = int(os.environ.get("OMNIVOICE_SHERPA_ASR_THREADS", "2"))
+
+
+def _endpoint_rules() -> tuple[float, float]:
+    """Trailing-silence endpoint rules (seconds) for streaming recognizers.
+
+    Wispr-Flow-speed defaults (dictation v2): rule2 commits ~0.6s after speech
+    stops, rule1 flushes after 1.0s of trailing non-speech — down from the
+    upstream 2.4/1.2, which made every committed sentence feel laggy. Read at
+    call time so the env overrides apply without a restart.
+    """
+    def _f(env: str, default: float) -> float:
+        try:
+            return float(os.environ.get(env, "") or default)
+        except (TypeError, ValueError):
+            return default
+    return (_f("OMNIVOICE_DICTATION_ENDPOINT_R1", 1.0),
+            _f("OMNIVOICE_DICTATION_ENDPOINT_R2", 0.6))
+
+
+@dataclass(frozen=True)
+class SherpaModelSpec:
+    """One downloadable sherpa-onnx dictation model.
+
+    ``files`` maps a logical role (encoder/decoder/joiner/tokens) to the EXACT
+    asset filename in the HF repo. ``kind`` selects the recognizer factory:
+    ``offline-transducer`` | ``offline-whisper`` | ``online-transducer`` |
+    ``online-paraformer``. ``tag`` is the frontend-facing "offline"/"streaming".
+    """
+    id: str
+    repo_id: str
+    label: str
+    tag: str            # "offline" | "streaming"
+    kind: str           # recognizer factory selector
+    size_gb: float
+    languages: str
+    files: dict[str, str]
+    recommended: bool = False
+    model_type: str = ""           # offline transducer only (nemo_transducer)
+    extra: dict = field(default_factory=dict)
+
+    @property
+    def streaming(self) -> bool:
+        return self.tag == "streaming"
+
+
+# ── The 7 models (HF repo ids under csukuangfj/, filenames VERIFIED against the
+#    live HF /api/models/<repo>/tree/main on 2026-06-25; int8 variants pinned).
+_MODELS: dict[str, SherpaModelSpec] = {
+    "sherpa-parakeet-tdt-v3": SherpaModelSpec(
+        id="sherpa-parakeet-tdt-v3",
+        repo_id="csukuangfj/sherpa-onnx-nemo-parakeet-tdt-0.6b-v3-int8",
+        label="Parakeet TDT v3",
+        tag="offline",
+        kind="offline-transducer",
+        size_gb=0.18,
+        languages="25 European languages",
+        recommended=True,
+        model_type="nemo_transducer",
+        files={
+            "encoder": "encoder.int8.onnx",
+            "decoder": "decoder.int8.onnx",
+            "joiner": "joiner.int8.onnx",
+            "tokens": "tokens.txt",
+        },
+    ),
+    "sherpa-parakeet-tdt-v2": SherpaModelSpec(
+        id="sherpa-parakeet-tdt-v2",
+        repo_id="csukuangfj/sherpa-onnx-nemo-parakeet-tdt-0.6b-v2-int8",
+        label="Parakeet TDT v2",
+        tag="offline",
+        kind="offline-transducer",
+        size_gb=0.17,
+        languages="English",
+        model_type="nemo_transducer",
+        files={
+            "encoder": "encoder.int8.onnx",
+            "decoder": "decoder.int8.onnx",
+            "joiner": "joiner.int8.onnx",
+            "tokens": "tokens.txt",
+        },
+    ),
+    "sherpa-zipformer-bilingual-zh-en": SherpaModelSpec(
+        id="sherpa-zipformer-bilingual-zh-en",
+        repo_id="csukuangfj/sherpa-onnx-streaming-zipformer-bilingual-zh-en-2023-02-20",
+        label="Zipformer Bilingual",
+        tag="streaming",
+        kind="online-transducer",
+        size_gb=0.13,
+        languages="Chinese + English",
+        files={
+            "encoder": "encoder-epoch-99-avg-1.int8.onnx",
+            "decoder": "decoder-epoch-99-avg-1.int8.onnx",
+            "joiner": "joiner-epoch-99-avg-1.int8.onnx",
+            "tokens": "tokens.txt",
+        },
+    ),
+    "sherpa-paraformer-bilingual-zh-en": SherpaModelSpec(
+        id="sherpa-paraformer-bilingual-zh-en",
+        repo_id="csukuangfj/sherpa-onnx-streaming-paraformer-bilingual-zh-en",
+        label="Paraformer Bilingual",
+        tag="streaming",
+        kind="online-paraformer",
+        size_gb=0.115,
+        languages="Chinese + English",
+        files={
+            "encoder": "encoder.int8.onnx",
+            "decoder": "decoder.int8.onnx",
+            "tokens": "tokens.txt",
+        },
+    ),
+    "sherpa-zipformer-en-20m": SherpaModelSpec(
+        id="sherpa-zipformer-en-20m",
+        repo_id="csukuangfj/sherpa-onnx-streaming-zipformer-en-20M-2023-02-17",
+        label="Zipformer Streaming EN",
+        tag="streaming",
+        kind="online-transducer",
+        size_gb=0.128,
+        languages="English",
+        files={
+            "encoder": "encoder-epoch-99-avg-1.int8.onnx",
+            "decoder": "decoder-epoch-99-avg-1.int8.onnx",
+            "joiner": "joiner-epoch-99-avg-1.int8.onnx",
+            "tokens": "tokens.txt",
+        },
+    ),
+    "sherpa-zipformer-zh-14m": SherpaModelSpec(
+        id="sherpa-zipformer-zh-14m",
+        repo_id="csukuangfj/sherpa-onnx-streaming-zipformer-zh-14M-2023-02-23",
+        label="Zipformer Streaming ZH",
+        tag="streaming",
+        kind="online-transducer",
+        size_gb=0.074,
+        languages="Chinese",
+        files={
+            "encoder": "encoder-epoch-99-avg-1.int8.onnx",
+            "decoder": "decoder-epoch-99-avg-1.int8.onnx",
+            "joiner": "joiner-epoch-99-avg-1.int8.onnx",
+            "tokens": "tokens.txt",
+        },
+    ),
+    "sherpa-whisper-tiny": SherpaModelSpec(
+        id="sherpa-whisper-tiny",
+        repo_id="csukuangfj/sherpa-onnx-whisper-tiny",
+        label="Whisper Tiny",
+        tag="offline",
+        kind="offline-whisper",
+        size_gb=0.116,
+        languages="90+ languages (auto-detect)",
+        files={
+            "encoder": "tiny-encoder.int8.onnx",
+            "decoder": "tiny-decoder.int8.onnx",
+            "tokens": "tiny-tokens.txt",
+        },
+    ),
+}
+
+DEFAULT_MODEL_ID = "sherpa-parakeet-tdt-v3"
+
+# repo_id → model id, so the model-store list (keyed by repo_id) can be
+# enriched with the dictation metadata, and so capture can map either key.
+_REPO_TO_ID: dict[str, str] = {m.repo_id: mid for mid, m in _MODELS.items()}
+
+
+def list_specs() -> list[SherpaModelSpec]:
+    return list(_MODELS.values())
+
+
+def get_spec(model_id: str) -> SherpaModelSpec | None:
+    """Look up a spec by its dictation id OR its HF repo_id."""
+    if model_id in _MODELS:
+        return _MODELS[model_id]
+    if model_id in _REPO_TO_ID:
+        return _MODELS[_REPO_TO_ID[model_id]]
+    return None
+
+
+def is_sherpa_model(model_id: str | None) -> bool:
+    return bool(model_id) and get_spec(model_id) is not None
+
+
+def sherpa_available() -> tuple[bool, str]:
+    try:
+        import sherpa_onnx  # noqa: F401
+        return True, "ready"
+    except ImportError as e:
+        return False, f"sherpa-onnx not installed: {e}. Install with: uv add sherpa-onnx"
+
+
+def _resolve_model_dir(spec: SherpaModelSpec, *, download: bool = True) -> str:
+    """Return the local directory containing this model's ONNX assets.
+
+    Tries the HF cache offline first (``local_files_only=True``); on a miss,
+    downloads on first use (like every other engine) unless ``download=False``.
+    Restricts the fetch to the exact int8 assets we pin via ``allow_patterns``
+    so we never pull the bundled fp32 weights or test wavs.
+    """
+    from huggingface_hub import snapshot_download
+
+    wanted = list(spec.files.values())
+    try:
+        return snapshot_download(
+            repo_id=spec.repo_id,
+            local_files_only=True,
+            allow_patterns=wanted,
+        )
+    except Exception:
+        if not download:
+            raise
+    logger.info("sherpa dictation: downloading %s on first use", spec.repo_id)
+    return snapshot_download(repo_id=spec.repo_id, allow_patterns=wanted)
+
+
+def is_installed(spec: SherpaModelSpec) -> bool:
+    """True if every pinned asset is already present in the HF cache."""
+    try:
+        d = _resolve_model_dir(spec, download=False)
+    except Exception:
+        return False
+    return all(os.path.isfile(os.path.join(d, f)) for f in spec.files.values())
+
+
+# ── Recognizers ──────────────────────────────────────────────────────────────
+
+
+def build_offline_recognizer(spec: SherpaModelSpec, *, download: bool = True):
+    """Construct an ``OfflineRecognizer`` for an offline transducer/whisper model."""
+    import sherpa_onnx
+
+    d = _resolve_model_dir(spec, download=download)
+
+    def p(role: str) -> str:
+        return os.path.join(d, spec.files[role])
+
+    if spec.kind == "offline-transducer":
+        return sherpa_onnx.OfflineRecognizer.from_transducer(
+            encoder=p("encoder"),
+            decoder=p("decoder"),
+            joiner=p("joiner"),
+            tokens=p("tokens"),
+            num_threads=_NUM_THREADS,
+            provider=_PROVIDER,
+            decoding_method="greedy_search",
+            model_type=spec.model_type or "nemo_transducer",
+        )
+    if spec.kind == "offline-whisper":
+        return sherpa_onnx.OfflineRecognizer.from_whisper(
+            encoder=p("encoder"),
+            decoder=p("decoder"),
+            tokens=p("tokens"),
+            num_threads=_NUM_THREADS,
+            provider=_PROVIDER,
+            language="",          # auto-detect
+            task="transcribe",
+        )
+    raise ValueError(f"{spec.id} is not an offline model (kind={spec.kind})")
+
+
+def build_online_recognizer(spec: SherpaModelSpec, *, download: bool = True):
+    """Construct an ``OnlineRecognizer`` (true streaming) with endpoint detection.
+
+    Endpoint (silence) detection drives the live "final" boundary: sherpa
+    commits a sentence after trailing silence so we can flush a ``final`` and
+    reset the stream for the next utterance — all within one WS session.
+    """
+    import sherpa_onnx
+
+    d = _resolve_model_dir(spec, download=download)
+    rule1, rule2 = _endpoint_rules()
+
+    def p(role: str) -> str:
+        return os.path.join(d, spec.files[role])
+
+    if spec.kind == "online-transducer":
+        return sherpa_onnx.OnlineRecognizer.from_transducer(
+            tokens=p("tokens"),
+            encoder=p("encoder"),
+            decoder=p("decoder"),
+            joiner=p("joiner"),
+            num_threads=_NUM_THREADS,
+            provider=_PROVIDER,
+            decoding_method="greedy_search",
+            enable_endpoint_detection=True,
+            rule1_min_trailing_silence=rule1,
+            rule2_min_trailing_silence=rule2,
+            rule3_min_utterance_length=20,
+        )
+    if spec.kind == "online-paraformer":
+        return sherpa_onnx.OnlineRecognizer.from_paraformer(
+            tokens=p("tokens"),
+            encoder=p("encoder"),
+            decoder=p("decoder"),
+            num_threads=_NUM_THREADS,
+            provider=_PROVIDER,
+            decoding_method="greedy_search",
+            enable_endpoint_detection=True,
+            rule1_min_trailing_silence=rule1,
+            rule2_min_trailing_silence=rule2,
+            rule3_min_utterance_length=20,
+        )
+    raise ValueError(f"{spec.id} is not a streaming model (kind={spec.kind})")

backend/services/speech_rate.py

@@ -21,6 +21,10 @@ from services.llm_backend import get_active_llm_backend, OffBackend
 
 logger = logging.getLogger("omnivoice.speech_rate")
 
+# LLM Skills registry id — Settings → LLM Skills can disable the slot-fit
+# LLM pass or route it to a specific provider. Disabled == the no-llm path.
+_SKILL_ID = "slot_fitting"
+
 # Per-language read-speed estimates (chars/sec at natural pace, counting
 # Python `len()` codepoints — not phonemes or graphemes). These are
 # rough; real speakers vary wildly. Numbers below come from a mix of
@@ -97,16 +101,28 @@ def adjust_for_slot(
     slot_seconds: float,
     target_lang: str,
     source_text: Optional[str] = None,
+    strict: bool = False,
 ) -> dict:
     """Return `{text, rate_ratio, attempts, error?}`.
 
     Falls back to the input text if the LLM is off or the loop gives up.
+
+    ``strict`` (Autofit mode) caps the accepted upper bound at 1.0 instead of
+    ``TOL_HIGH`` — i.e. the line must fit *within* the slot, never overrun it —
+    so the target-language reading time can't exceed the segment and push the
+    video timing out. A too-short line is still accepted down to ``TOL_LOW`` (we
+    don't pad just to fill silence). Best-effort: after ``MAX_ATTEMPTS`` it
+    returns the closest candidate seen, so a stubborn line degrades gracefully.
     """
+    tol_high = 1.0 if strict else TOL_HIGH
     initial_ratio = rate_ratio(text, slot_seconds, target_lang)
-    if TOL_LOW <= initial_ratio <= TOL_HIGH:
+    if TOL_LOW <= initial_ratio <= tol_high:
         return {"text": text, "rate_ratio": initial_ratio, "attempts": 0}
 
-    llm = get_active_llm_backend()
+    from services import llm_skills
+    # `active=` forwards this module's (monkeypatch-able) name so the
+    # no-override path is byte-identical to the pre-skills behavior.
+    llm = llm_skills.skill_backend(_SKILL_ID, active=lambda: get_active_llm_backend())
     if isinstance(llm, OffBackend):
         return {
             "text": text,
@@ -119,7 +135,7 @@ def adjust_for_slot(
     best = (current, initial_ratio)
     for attempt in range(1, MAX_ATTEMPTS + 1):
         r = rate_ratio(current, slot_seconds, target_lang)
-        if TOL_LOW <= r <= TOL_HIGH:
+        if TOL_LOW <= r <= tol_high:
             return {"text": current, "rate_ratio": r, "attempts": attempt - 1}
 
         system = _TRIM_PROMPT if r > 1.0 else _EXPAND_PROMPT
@@ -162,3 +178,78 @@ def adjust_many(pairs: Iterable[tuple[str, float, str, Optional[str]]]) -> list[
         adjust_for_slot(t, slot_seconds=s, target_lang=tl, source_text=src)
         for (t, s, tl, src) in pairs
     ]
+
+
+async def adjust_for_slot_many(
+    items: Iterable[tuple],
+    *,
+    executor=None,
+    concurrency: Optional[int] = None,
+    deadline: Optional[float] = None,
+    loop=None,
+) -> dict:
+    """Fan `adjust_for_slot` out across many segments concurrently, bounded by a
+    shared wall-clock ``deadline``.
+
+    ``items``: iterable of ``(key, text, slot_seconds, target_lang,
+    source_text_or_None, strict)``. Returns ``{key: adjust_for_slot_result}``.
+
+    Why this exists: the Autofit fit pass used to run one `adjust_for_slot` per
+    segment *sequentially* and *outside* any budget, so a 50-segment dub against
+    a slow/rate-limited LLM spun ~50×(per-call timeout) unbounded. Here every
+    segment runs on the executor under a bounded ``asyncio.Semaphore``, and any
+    segment still running when the shared ``deadline`` passes degrades to a
+    no-fit result (input text kept, predicted ``rate_ratio``, ``error`` =
+    ``"fit-budget"``) instead of hanging the translate. ``deadline`` is an
+    absolute ``loop.time()``; ``None`` disables the bound (run to completion).
+    """
+    import asyncio
+    import os
+
+    loop = loop or asyncio.get_running_loop()
+    items = list(items)
+    if not items:
+        return {}
+    sem = asyncio.Semaphore(concurrency or int(os.environ.get("OMNIVOICE_LLM_CONCURRENCY", "6")))
+
+    async def _one(key, text, slot, tgt, src, strict):
+        async with sem:
+            res = await loop.run_in_executor(
+                executor,
+                lambda: adjust_for_slot(
+                    text, slot_seconds=slot, target_lang=tgt,
+                    source_text=src, strict=strict,
+                ),
+            )
+        return key, res
+
+    def _degraded(text, slot, tgt) -> dict:
+        return {
+            "text": text,
+            "rate_ratio": rate_ratio(text, slot, tgt),
+            "attempts": 0,
+            "error": "fit-budget",
+        }
+
+    tasks = [asyncio.ensure_future(_one(*it)) for it in items]
+
+    if deadline is None:
+        pairs_out = await asyncio.gather(*tasks)
+        return dict(pairs_out)
+
+    timeout = max(0.0, deadline - loop.time())
+    done, _pending = await asyncio.wait(tasks, timeout=timeout)
+    out: dict = {}
+    for task, it in zip(tasks, items):
+        key, text, slot, tgt = it[0], it[1], it[2], it[3]
+        if task in done and not task.cancelled():
+            try:
+                k, res = task.result()
+                out[k] = res
+                continue
+            except Exception as e:  # noqa: BLE001 — one slow seg must not sink the pass
+                logger.warning("fit segment %s failed: %s", key, e)
+        else:
+            task.cancel()  # stop awaiting; the executor thread is abandoned (#730 pattern)
+        out[key] = _degraded(text, slot, tgt)
+    return out

backend/services/storage_report.py

@@ -0,0 +1,471 @@
+"""Storage usage report for Settings → Storage.
+
+Computes, for everything the app owns on disk:
+
+  * per-volume totals (total / used / free, grouped by ``st_dev`` so two
+    roots on the same disk are reported once),
+  * per-category directory sizes — the HF model cache (with the largest
+    model dirs), the app data dir (broken into voices / outputs / dub_jobs /
+    batch / preview / database / logs / other subtotals), the per-engine
+    venvs under ``backend/engines/*/.venv`` (+ the app venv), and any
+    ``omnivoice*`` entries in the OS temp dir,
+  * server-side ``warnings`` (low disk, volume pressure, unreadable paths)
+    so every client renders the same guidance.
+
+Directory walks are **bounded**: each top-level category gets a deadline
+(default 10 s) and returns a partial total (``complete: false`` + an
+``unreadable`` warning with ``reason: "timeout"``) when it expires. Results
+are cached in-process for 5 minutes; ``refresh`` bypasses the cache. The API
+layer runs the whole build in a worker thread so the event loop never blocks.
+"""
+from __future__ import annotations
+
+import glob
+import os
+import shutil
+import sys
+import tempfile
+import threading
+import time
+from pathlib import Path
+
+CACHE_TTL_SECONDS = 300.0
+CATEGORY_TIMEOUT_SECONDS = 10.0
+TOP_MODEL_COUNT = 10
+VOLUME_PRESSURE_PERCENT = 90.0
+DEFAULT_MIN_FREE_GB = 10  # callers pass setup.wizard.MIN_FREE_GB — this is the standalone fallback
+
+# DATA_DIR children we know by name (core.config constants + routers that
+# write there). Anything else lands in the "other" subtotal so the numbers
+# always add up to the real on-disk footprint.
+_DATA_CHILD_DIRS = ("voices", "outputs", "dub_jobs", "batch", "preview")
+_DB_PREFIX = "omnivoice.db"          # omnivoice.db + -wal / -shm / -journal
+_LOG_FILES = ("crash_log.txt", "error_journal.jsonl")
+_LOG_PREFIX = "omnivoice.log"        # rolling log + rotations
+
+_GB = 1024 ** 3
+
+
+def default_engines_dir() -> str:
+    """``backend/engines`` — where per-engine venvs live (`<id>/.venv`)."""
+    return str(Path(__file__).resolve().parents[1] / "engines")
+
+
+def default_app_venv() -> str | None:
+    """The venv this backend runs from, when it is one (None for system python)."""
+    if sys.prefix != getattr(sys, "base_prefix", sys.prefix):
+        return sys.prefix
+    return None
+
+
+def _existing_ancestor(path: str) -> str:
+    """Deepest existing ancestor of ``path`` (for disk_usage on missing dirs)."""
+    p = os.path.abspath(path)
+    while p and not os.path.exists(p):
+        parent = os.path.dirname(p)
+        if parent == p:
+            break
+        p = parent
+    return p
+
+
+def _mount_point(path: str) -> str:
+    """Mount point of the volume holding ``path`` (best-effort, cheap)."""
+    p = _existing_ancestor(path)
+    try:
+        while p and not os.path.ismount(p):
+            parent = os.path.dirname(p)
+            if parent == p:
+                break
+            p = parent
+    except OSError:
+        pass
+    return p or os.path.abspath(os.sep)
+
+
+def _dir_size(path: str, deadline: float) -> tuple[int, bool, str | None]:
+    """du-style size of ``path``: ``(bytes, complete, first_unreadable_path)``.
+
+    Never follows symlinks (lstat + walk default), never raises. Stops early
+    and reports ``complete=False`` once ``deadline`` (time.monotonic) passes.
+    """
+    err_path: str | None = None
+
+    def _onerror(e: OSError) -> None:
+        nonlocal err_path
+        if err_path is None:
+            err_path = getattr(e, "filename", None) or path
+
+    try:
+        if not os.path.exists(path):
+            return 0, True, None
+        if not os.path.isdir(path):
+            return os.lstat(path).st_size, True, None
+    except OSError:
+        return 0, True, path
+
+    total = 0
+    complete = True
+    for root, _dirs, files in os.walk(path, onerror=_onerror):
+        if time.monotonic() > deadline:
+            complete = False
+            break
+        for name in files:
+            fp = os.path.join(root, name)
+            try:
+                total += os.lstat(fp).st_size
+            except OSError:
+                if err_path is None:
+                    err_path = fp
+    return total, complete, err_path
+
+
+def _sum_files(paths: list[str]) -> int:
+    total = 0
+    for p in paths:
+        try:
+            total += os.lstat(p).st_size
+        except OSError:
+            pass
+    return total
+
+
+def _hf_model_dirs(cache_dir: str) -> list[str]:
+    """`models--org--name` dirs in the cache root and its `hub/` child.
+
+    HF_HUB_CACHE points straight at the hub dir; HF_HOME needs `/hub`
+    appended — scanning both covers either env resolution.
+    """
+    out: list[str] = []
+    for base in (cache_dir, os.path.join(cache_dir, "hub")):
+        try:
+            with os.scandir(base) as it:
+                out.extend(
+                    e.path for e in it
+                    if e.name.startswith("models--") and e.is_dir(follow_symlinks=False)
+                )
+        except OSError:
+            continue
+    return out
+
+
+def _model_display_name(dir_name: str) -> str:
+    return dir_name.removeprefix("models--").replace("--", "/")
+
+
+def build_report(
+    *,
+    data_dir: str,
+    hf_cache_dir: str,
+    engines_dir: str | None = None,
+    app_venv: str | None = None,
+    temp_root: str | None = None,
+    min_free_gb: float = DEFAULT_MIN_FREE_GB,
+    category_timeout: float = CATEGORY_TIMEOUT_SECONDS,
+) -> dict:
+    """Build the full storage report (synchronous; call from a worker thread)."""
+    engines_dir = engines_dir if engines_dir is not None else default_engines_dir()
+    temp_root = temp_root if temp_root is not None else tempfile.gettempdir()
+    warnings: list[dict] = []
+    categories: list[dict] = []
+
+    def _warn_unreadable(category_id: str, path: str, reason: str) -> None:
+        warnings.append({
+            "kind": "unreadable",
+            "severity": "warning",
+            "category_id": category_id,
+            "path": path,
+            "reason": reason,
+        })
+
+    def _finish(category_id: str, cat: dict, complete: bool, err_path: str | None) -> None:
+        cat["complete"] = complete
+        if not complete:
+            _warn_unreadable(category_id, cat["path"], "timeout")
+        if err_path is not None:
+            _warn_unreadable(category_id, err_path, "permission")
+
+    # ── 1. HF model cache (+ top model dirs) ───────────────────────────────
+    deadline = time.monotonic() + category_timeout
+    hf_total = 0
+    hf_complete = True
+    hf_err: str | None = None
+    models: list[dict] = []
+    model_dirs = set(_hf_model_dirs(hf_cache_dir))
+    seen: set[str] = set()
+    for mdir in sorted(model_dirs):
+        size, ok, err = _dir_size(mdir, deadline)
+        hf_total += size
+        hf_complete = hf_complete and ok
+        hf_err = hf_err or err
+        models.append({"name": _model_display_name(os.path.basename(mdir)), "bytes": size})
+        seen.add(os.path.realpath(mdir))
+    # Non-model remainder of the cache (datasets, xet chunks, token file, …):
+    # walk the top-level entries that aren't model dirs so the category total
+    # reflects the whole cache, not just models.
+    try:
+        with os.scandir(hf_cache_dir) as it:
+            entries = list(it)
+    except OSError:
+        entries = []
+        if os.path.exists(hf_cache_dir):
+            hf_err = hf_err or hf_cache_dir
+    for e in entries:
+        if os.path.realpath(e.path) in seen:
+            continue
+        if e.name == "hub":
+            # hub/ holds the model dirs (already counted) + misc; count the rest.
+            try:
+                with os.scandir(e.path) as hub_it:
+                    for h in hub_it:
+                        if os.path.realpath(h.path) in seen:
+                            continue
+                        size, ok, err = _dir_size(h.path, deadline)
+                        hf_total += size
+                        hf_complete = hf_complete and ok
+                        hf_err = hf_err or err
+            except OSError:
+                hf_err = hf_err or e.path
+            continue
+        size, ok, err = _dir_size(e.path, deadline)
+        hf_total += size
+        hf_complete = hf_complete and ok
+        hf_err = hf_err or err
+    models.sort(key=lambda m: m["bytes"], reverse=True)
+    hf_cat = {
+        "id": "hf_cache",
+        "path": hf_cache_dir,
+        "exists": os.path.isdir(hf_cache_dir),
+        "bytes": hf_total,
+        "items": models[:TOP_MODEL_COUNT],
+    }
+    _finish("hf_cache", hf_cat, hf_complete, hf_err)
+    categories.append(hf_cat)
+
+    # ── 2. App data dir, broken into subtotals ─────────────────────────────
+    deadline = time.monotonic() + category_timeout
+    data_complete = True
+    data_err: str | None = None
+    children: list[dict] = []
+    claimed: set[str] = set()
+
+    for name in _DATA_CHILD_DIRS:
+        p = os.path.join(data_dir, name)
+        size, ok, err = _dir_size(p, deadline)
+        data_complete = data_complete and ok
+        data_err = data_err or err
+        claimed.add(name)
+        children.append({"id": name, "path": p, "bytes": size, "complete": ok})
+
+    db_files = sorted(glob.glob(os.path.join(glob.escape(data_dir), _DB_PREFIX + "*")))
+    claimed.update(os.path.basename(p) for p in db_files)
+    children.append({
+        "id": "database",
+        "path": os.path.join(data_dir, _DB_PREFIX),
+        "bytes": _sum_files(db_files),
+        "complete": True,
+    })
+
+    log_files = sorted(glob.glob(os.path.join(glob.escape(data_dir), _LOG_PREFIX + "*")))
+    log_files += [os.path.join(data_dir, n) for n in _LOG_FILES]
+    claimed.update(os.path.basename(p) for p in log_files)
+    children.append({
+        "id": "logs",
+        "path": data_dir,
+        "bytes": _sum_files(log_files),
+        "complete": True,
+    })
+
+    other_bytes = 0
+    try:
+        with os.scandir(data_dir) as it:
+            for e in it:
+                if e.name in claimed:
+                    continue
+                if e.is_dir(follow_symlinks=False):
+                    size, ok, err = _dir_size(e.path, deadline)
+                    other_bytes += size
+                    data_complete = data_complete and ok
+                    data_err = data_err or err
+                else:
+                    try:
+                        other_bytes += e.stat(follow_symlinks=False).st_size
+                    except OSError:
+                        data_err = data_err or e.path
+    except OSError:
+        if os.path.exists(data_dir):
+            data_err = data_err or data_dir
+    children.append({"id": "other", "path": data_dir, "bytes": other_bytes, "complete": True})
+
+    data_cat = {
+        "id": "data",
+        "path": data_dir,
+        "exists": os.path.isdir(data_dir),
+        "bytes": sum(c["bytes"] for c in children),
+        "children": children,
+    }
+    _finish("data", data_cat, data_complete, data_err)
+    categories.append(data_cat)
+
+    # ── 3. Engine venvs (+ the app venv) ───────────────────────────────────
+    deadline = time.monotonic() + category_timeout
+    venv_total = 0
+    venv_complete = True
+    venv_err: str | None = None
+    venv_items: list[dict] = []
+    try:
+        with os.scandir(engines_dir) as it:
+            engine_dirs = sorted(e.path for e in it if e.is_dir(follow_symlinks=False))
+    except OSError:
+        engine_dirs = []
+    for edir in engine_dirs:
+        venv_dir = os.path.join(edir, ".venv")
+        if not os.path.isdir(venv_dir):
+            continue
+        size, ok, err = _dir_size(venv_dir, deadline)
+        venv_total += size
+        venv_complete = venv_complete and ok
+        venv_err = venv_err or err
+        venv_items.append({"name": os.path.basename(edir), "bytes": size})
+    if app_venv:
+        size, ok, err = _dir_size(app_venv, deadline)
+        venv_total += size
+        venv_complete = venv_complete and ok
+        venv_err = venv_err or err
+        venv_items.append({"name": "app", "bytes": size})
+    venv_items.sort(key=lambda m: m["bytes"], reverse=True)
+    venv_cat = {
+        "id": "engine_venvs",
+        "path": engines_dir,
+        "exists": os.path.isdir(engines_dir),
+        "bytes": venv_total,
+        "items": venv_items,
+    }
+    _finish("engine_venvs", venv_cat, venv_complete, venv_err)
+    categories.append(venv_cat)
+
+    # ── 4. Temp/working files the app owns (omnivoice* in the OS temp dir) ─
+    deadline = time.monotonic() + category_timeout
+    tmp_total = 0
+    tmp_complete = True
+    tmp_err: str | None = None
+    for p in sorted(glob.glob(os.path.join(glob.escape(temp_root), "omnivoice*"))):
+        size, ok, err = _dir_size(p, deadline)
+        tmp_total += size
+        tmp_complete = tmp_complete and ok
+        tmp_err = tmp_err or err
+    tmp_cat = {
+        "id": "temp",
+        "path": temp_root,
+        "exists": os.path.isdir(temp_root),
+        "bytes": tmp_total,
+        "items": [],
+    }
+    _finish("temp", tmp_cat, tmp_complete, tmp_err)
+    categories.append(tmp_cat)
+
+    # ── Volumes: group category roots by device, disk_usage once each ──────
+    roots = {"hf_cache": hf_cache_dir, "data": data_dir, "engine_venvs": engines_dir, "temp": temp_root}
+    by_dev: dict[object, dict] = {}
+    for cid, root in roots.items():
+        anchor = _existing_ancestor(root)
+        try:
+            dev: object = os.stat(anchor).st_dev
+        except OSError:
+            dev = anchor
+        if dev not in by_dev:
+            try:
+                usage = shutil.disk_usage(anchor)
+            except OSError:
+                continue
+            by_dev[dev] = {
+                "path": _mount_point(anchor),
+                "total_bytes": usage.total,
+                "used_bytes": usage.used,
+                "free_bytes": usage.free,
+                "used_percent": round(usage.used / usage.total * 100.0, 1) if usage.total else 0.0,
+                "roots": [],
+            }
+        by_dev[dev]["roots"].append(cid)
+    volumes = list(by_dev.values())
+
+    # ── Server-side warnings ────────────────────────────────────────────────
+    for v in volumes:
+        free_gb = v["free_bytes"] / _GB
+        base = {
+            "path": v["path"],
+            "free_gb": round(free_gb, 1),
+            "min_free_gb": min_free_gb,
+            "roots": v["roots"],
+        }
+        if free_gb < min_free_gb:
+            warnings.append({"kind": "low_disk", "severity": "critical", **base})
+        elif free_gb < 2 * min_free_gb:
+            warnings.append({"kind": "low_disk", "severity": "low", **base})
+        if v["used_percent"] > VOLUME_PRESSURE_PERCENT and ({"hf_cache", "data"} & set(v["roots"])):
+            warnings.append({
+                "kind": "volume_pressure",
+                "severity": "warning",
+                "path": v["path"],
+                "used_percent": v["used_percent"],
+                "roots": v["roots"],
+            })
+
+    # Order: critical first, then the rest in computed order (stable sort).
+    warnings.sort(key=lambda w: 0 if w["severity"] == "critical" else 1)
+
+    return {
+        "generated_at": time.time(),
+        "min_free_gb": min_free_gb,
+        "volumes": volumes,
+        "categories": categories,
+        "warnings": warnings,
+    }
+
+
+# ── In-process cache (5-minute TTL, refresh bypasses) ──────────────────────
+_cache_lock = threading.Lock()
+_cache: dict = {"key": None, "ts": 0.0, "report": None}
+
+
+def get_report(
+    *,
+    data_dir: str,
+    hf_cache_dir: str,
+    engines_dir: str | None = None,
+    app_venv: str | None = None,
+    temp_root: str | None = None,
+    min_free_gb: float = DEFAULT_MIN_FREE_GB,
+    category_timeout: float = CATEGORY_TIMEOUT_SECONDS,
+    refresh: bool = False,
+    ttl: float = CACHE_TTL_SECONDS,
+) -> dict:
+    """Cached ``build_report``. ``refresh=True`` forces a rescan."""
+    key = (data_dir, hf_cache_dir, engines_dir, app_venv, temp_root, min_free_gb)
+    if not refresh:
+        with _cache_lock:
+            fresh = (
+                _cache["report"] is not None
+                and _cache["key"] == key
+                and (time.monotonic() - _cache["ts"]) < ttl
+            )
+            if fresh:
+                return {**_cache["report"], "cached": True}
+    report = build_report(
+        data_dir=data_dir,
+        hf_cache_dir=hf_cache_dir,
+        engines_dir=engines_dir,
+        app_venv=app_venv,
+        temp_root=temp_root,
+        min_free_gb=min_free_gb,
+        category_timeout=category_timeout,
+    )
+    with _cache_lock:
+        _cache.update(key=key, ts=time.monotonic(), report=report)
+    return {**report, "cached": False}
+
+
+def clear_cache() -> None:
+    """Testing hook — drop the in-process cache."""
+    with _cache_lock:
+        _cache.update(key=None, ts=0.0, report=None)

backend/services/subprocess_asr.py

@@ -132,6 +132,10 @@ class IsolatedFasterWhisperBackend(SubprocessASRBackend):
 
     id = "faster-whisper-isolated"
     display_name = "Faster-Whisper (crash-isolated subprocess)"
+    # Same engine as FasterWhisperBackend, so the same device support — the
+    # sidecar picks cuda/cpu itself via `_device()`. Without this the registry
+    # default ("cpu",) would dishonestly report cpu_only routing on CUDA hosts.
+    gpu_compat = ("cuda", "cpu")
 
     @classmethod
     def is_available(cls) -> tuple[bool, str]:

backend/services/text_polish.py

@@ -0,0 +1,79 @@
+"""
+Deterministic polish for dictation finals (dictation v2).
+
+Every ``final`` that leaves ``/ws/transcribe`` passes through
+:func:`polish_text` so pasted dictation reads like typed text:
+
+  * leading capital -- Latin scripts only (CJK/Cyrillic/etc. untouched),
+  * terminal punctuation -- a period is appended unless the text already
+    ends with sentence-terminal punctuation (incl. the CJK fullwidth forms),
+  * doubled spaces collapsed, leading/trailing whitespace stripped.
+
+Purely rule-based -- no model, no locale detection, no network -- so it is
+byte-for-byte reproducible and idempotent (``polish(polish(x)) == polish(x)``).
+
+CJK codepoints below are ``\\u``-escaped on purpose: this is functional
+punctuation handling (allowed), and the escapes keep this file outside the
+literal-CJK scan in ``tests/test_no_hardcoded_cjk.py`` without growing its
+allowlist.
+"""
+from __future__ import annotations
+
+import re
+
+# Sentence-terminal punctuation that already "closes" a final -- Latin plus
+# the CJK fullwidth forms (U+3002 ideographic full stop, U+FF01 !, U+FF1F ?)
+# and ellipsis. A trailing closing quote/bracket after one of these still
+# counts as terminated ("He said \"hi.\"").
+_TERMINAL = ".!?\u2026\u3002\uff01\uff1f"
+_CLOSERS = "\"'\u201d\u2019\u00bb\u203a)]}\u300d\u300f\uff09\u3011"
+
+# A dangling clause separator at the very end (ASR often stops mid-breath on
+# a comma) is swapped for a stop instead of stacking ",." punctuation.
+# Latin , ; : plus the CJK forms U+3001 U+FF0C U+FF1B U+FF1A.
+_DANGLING = ",;:\u3001\uff0c\uff1b\uff1a"
+
+# CJK codepoints (kana, unified ideographs, compatibility + halfwidth forms)
+# -- used to pick the fullwidth stop U+3002 over "." for CJK sentences.
+_CJK = re.compile(
+    "[\u3040-\u30ff\u3400-\u4dbf\u4e00-\u9fff\uf900-\ufaff\uff66-\uff9f]"
+)
+
+_MULTISPACE = re.compile(r"[ \t]{2,}")
+
+
+def _is_latin_lower(ch: str) -> bool:
+    """Lowercase letter in a Latin block (ASCII, Latin-1, Latin Extended-A/B).
+
+    Capitalization is meaningless (CJK) or presumptuous (Cyrillic, Greek --
+    the model's casing is trusted) outside Latin scripts.
+    """
+    return ch.islower() and ord(ch) <= 0x024F
+
+
+def polish_text(text: str) -> str:
+    """Normalise one dictation final. Empty/whitespace-only input -> ``""``."""
+    if not text:
+        return ""
+    out = _MULTISPACE.sub(" ", text).strip()
+    if not out:
+        return ""
+
+    # Leading capital (Latin scripts only).
+    if _is_latin_lower(out[0]):
+        out = out[0].upper() + out[1:]
+
+    # Already terminated -- possibly behind a closing quote/bracket?
+    body = out.rstrip(_CLOSERS)
+    if body and body[-1] in _TERMINAL:
+        return out
+
+    # Swap a dangling comma/colon for the stop instead of stacking ",.".
+    if out[-1] in _DANGLING:
+        out = out[:-1].rstrip()
+        if not out:
+            return ""
+
+    # Script-matched stop: fullwidth U+3002 when the sentence ends in CJK.
+    out += "\u3002" if _CJK.search(out[-1]) else "."
+    return out

backend/services/translation_engines.py

@@ -120,6 +120,23 @@ def _probe(entry: dict) -> tuple[bool, str]:
         return False, f"import {mod!r} failed: {e}"
 
 
+def install_command(engine: "str | dict | None") -> str | None:
+    """The exact shell command that makes this engine importable, or None.
+
+    Single source of truth for the install string. BOTH the proactive Install
+    affordance in the Engine selector (via list_engines' ``install_command``
+    field) AND the translate-time 400 error (dub_translate.py) read from here,
+    so the command a user is told to run can never drift between the two
+    surfaces. Returns None when the engine needs no separate install — either
+    it's unknown or its dependency is a core dep already pinned in
+    ``pyproject.toml`` (e.g. NLLB → transformers), in which case a
+    ``uv pip install`` line would be misleading.
+    """
+    entry = engine if isinstance(engine, dict) else REGISTRY.get(engine) if engine else None
+    pkg = entry.get("pip_package") if entry else None
+    return f"uv pip install {pkg}" if pkg else None
+
+
 def list_engines() -> list[dict]:
     """Return a UI-ready list with per-engine availability stamped in."""
     out = []
@@ -129,6 +146,7 @@ def list_engines() -> list[dict]:
             **e,
             "installed": installed,
             "availability_reason": reason,
+            "install_command": install_command(e),
         })
     return out
 
@@ -177,6 +195,16 @@ async def run_pip(args: list[str], timeout: float = 600.0) -> tuple[int, str]:
     """
     base = _installer_cmd()
     using_uv = base[:1] == ["uv"]
+    # Pin `uv pip` to the interpreter the backend ACTUALLY runs under. The desktop
+    # spawns `<venv>/bin/python -m uvicorn` WITHOUT exporting VIRTUAL_ENV, so bare
+    # `uv pip install` finds no venv and 500s with "No virtual environment found"
+    # (#529/#527) — and the `--system` branch below never fires, because the
+    # running interpreter genuinely IS in a venv (uv just can't auto-discover it).
+    # `--python sys.executable` targets the same interpreter _probe()/is_installed()
+    # import from, and takes precedence when both flags are present, so the Docker
+    # `--system` path is unaffected.
+    if using_uv and args and args[0] in ("install", "uninstall") and "--python" not in args:
+        args = [args[0], "--python", sys.executable, *args[1:]]
     if using_uv and not _in_virtualenv() and args and args[0] in ("install", "uninstall") and "--system" not in args:
         args = [args[0], "--system", *args[1:]]
     cmd = base + args

backend/services/translator.py

@@ -93,28 +93,37 @@ def _looks_like_target_script(text: str, code: str, threshold: float = 0.5) -> b
     return (inside / len(letters)) >= threshold
 
 
+# The LLM Skills registry entry this pipeline resolves through — lets the
+# user disable Cinematic/Autofit's LLM use or route it to a specific provider
+# (Settings → LLM Skills) independently of the other LLM features.
+_SKILL_ID = "cinematic_translation"
+
+
 def _llm_client():
-    """Lazy-build the OpenAI-compatible client. Returns None if no key + no local base_url."""
-    try:
-        from openai import OpenAI
-    except ImportError:
-        logger.warning("openai package not installed — cinematic mode unavailable.")
-        return None
-    base_url = os.environ.get("TRANSLATE_BASE_URL")
-    api_key = (
-        os.environ.get("TRANSLATE_API_KEY")
-        or os.environ.get("OPENAI_API_KEY")
-        or ("local" if base_url else None)  # local providers often accept any key
-    )
-    if not api_key:
-        return None
-    kw = {"api_key": api_key}
-    if base_url:
-        kw["base_url"] = base_url
-    return OpenAI(**kw)
+    """Lazy-build the OpenAI-compatible client for the Cinematic skill.
+
+    Resolves through the LLM Skills registry: per-skill provider override →
+    global active provider (Settings → LLM Providers). The registry's
+    ``custom`` provider still maps ``TRANSLATE_BASE_URL``/``TRANSLATE_API_KEY``,
+    so legacy env setups keep working. Returns None if the skill is disabled
+    or no provider is configured — the callers' Fast-fallback path.
+
+    The registry builds the client with ``max_retries=0`` (see
+    ``llm_skills.resolve_skill_client``) so a 429 + long Retry-After can't make
+    one call sleep+retry past the cinematic wall-clock budget from inside a
+    single request. The pass-level budget (``cinematic_refine_many``) and the
+    per-call timeout stay the only bounds.
+    """
+    from services import llm_skills
+    handle = llm_skills.resolve_skill_client(_SKILL_ID)
+    return handle.client if handle is not None else None
 
 
 def _llm_model() -> str:
+    from services import llm_providers, llm_skills
+    p = llm_skills.effective_provider(_SKILL_ID)
+    if p is not None:
+        return llm_providers.resolve_model(p)
     return os.environ.get("TRANSLATE_MODEL", "gpt-4o-mini")
 
 
@@ -125,6 +134,16 @@ def _llm_timeout() -> float:
         return 45.0
 
 
+def _cinematic_budget() -> float:
+    """Overall wall-clock cap for a whole cinematic/autofit refine pass (seconds).
+    Unfinished segments degrade to their literal (Fast) translation once hit, so
+    a slow provider can't hang the translate. Default 180s; <=0 disables."""
+    try:
+        return float(os.environ.get("OMNIVOICE_CINEMATIC_BUDGET_S", "180"))
+    except ValueError:
+        return 180.0
+
+
 def _glossary_text(glossary: Iterable[dict] | None) -> str:
     """Format the project glossary as a preamble for the LLM prompts.
 
@@ -320,4 +339,35 @@ async def cinematic_refine_many(
             )
         return {"id": seg_id, **res}
 
-    return await asyncio.gather(*(_one(sid, src, lit) for sid, src, lit in pairs))
+    # Overall wall-clock budget for the whole pass. Per-call timeout + bounded
+    # concurrency already cap it, but a slow/rate-limited provider on a large dub
+    # can still stall the "Translating…" spinner for minutes. Bound it: segments
+    # that finish in time keep their cinematic refine; any still-running segment
+    # degrades to its literal (Fast) translation so the translate ALWAYS returns
+    # within the budget instead of hanging. 0/negative disables the bound.
+    budget = _cinematic_budget()
+    tasks = [asyncio.ensure_future(_one(sid, src, lit)) for sid, src, lit in pairs]
+    if budget <= 0:
+        return await asyncio.gather(*tasks)
+
+    done, pending = await asyncio.wait(tasks, timeout=budget)
+    if pending:
+        logger.warning(
+            "Cinematic pass hit its %.0fs budget with %d/%d segment(s) unfinished "
+            "— falling back to the literal translation for those (slow LLM "
+            "provider?). Raise OMNIVOICE_CINEMATIC_BUDGET_S or pick a faster "
+            "provider.", budget, len(pending), len(tasks),
+        )
+    out: list[dict] = []
+    for task, (sid, _src, lit) in zip(tasks, pairs):
+        if task in done and not task.cancelled():
+            try:
+                out.append(task.result())
+                continue
+            except Exception as e:  # noqa: BLE001 — never let one seg sink the pass
+                logger.warning("cinematic segment %s failed: %s", sid, e)
+        else:
+            task.cancel()  # stop awaiting; the executor thread is abandoned (#730 pattern)
+        out.append({"id": sid, "text": lit, "literal": lit, "critique": "",
+                    "error": "cinematic-budget"})
+    return out

backend/services/tts_backend.py

@@ -55,6 +55,59 @@ def _mask_hf_tokens(value):
     return _HF_TOKEN_MASK_RE.sub(_HF_TOKEN_MASK, value)
 
 
+# ── HF Hub closed-client recovery (#880) ────────────────────────────────────
+#
+# huggingface_hub ≥1.x shares ONE global httpx client across every download.
+# If anything closes it mid-lifecycle, every later hub call — e.g. an engine's
+# first-use model download inside the generate path — dies with httpx's
+# "Cannot send a request, as the client has been closed". The client is
+# recoverable: ``close_session()`` drops it and the next hub call builds a
+# fresh one, so the correct handling is a single targeted retry, not a
+# user-facing failure.
+
+
+def _is_closed_client_error(e) -> bool:
+    """True iff ``e`` (or anything in its __cause__/__context__ chain) is
+    httpx's closed-client lifecycle error. Cycle-safe."""
+    seen, stack = set(), [e]
+    while stack:
+        exc = stack.pop()
+        if exc is None or id(exc) in seen:
+            continue
+        seen.add(id(exc))
+        low = str(exc).lower()
+        if "client has been closed" in low or "cannot send a request" in low:
+            return True
+        stack.append(exc.__cause__)
+        stack.append(exc.__context__)
+    return False
+
+
+def _retry_once_with_fresh_hf_client(loader, what: str):
+    """Run ``loader()`` — a model constructor that may download from the HF
+    Hub on first use. On the specific closed-client failure above, reset the
+    hub's shared client and retry exactly ONCE. Any other failure (and a
+    repeat closed-client failure) propagates untouched, where the generation
+    error classifier labels it as a network problem (#880)."""
+    try:
+        return loader()
+    except Exception as e:
+        if not _is_closed_client_error(e):
+            raise
+        logger.warning(
+            "%s: HF Hub httpx client was closed mid-download (%s); "
+            "retrying once with a fresh client.", what, e,
+        )
+        try:
+            from huggingface_hub.utils import close_session
+            close_session()
+        except Exception:  # pragma: no cover — hub too old / API renamed
+            logger.warning(
+                "%s: couldn't reset the HF Hub client; retrying anyway.", what,
+            )
+        return loader()
+
+
 # ── Protocol ────────────────────────────────────────────────────────────────
 
 
@@ -587,7 +640,13 @@ class KittenTTSBackend(TTSBackend):
             "OMNIVOICE_KITTENTTS_MODEL", "KittenML/kitten-tts-mini-0.8"
         )
         logger.info("Loading KittenTTS from %s", checkpoint)
-        self._model = KittenTTS(checkpoint)
+        # #880: the first-use load downloads ~80 MB from the HF Hub inside the
+        # generate path; if the hub's shared httpx client was closed
+        # mid-lifecycle, retry once with a fresh client instead of failing
+        # the whole generation.
+        self._model = _retry_once_with_fresh_hf_client(
+            lambda: KittenTTS(checkpoint), what="KittenTTS"
+        )
 
     def generate(self, text: str, **kw) -> torch.Tensor:
         import numpy as np
@@ -1061,13 +1120,34 @@ class SherpaOnnxBackend(TTSBackend):
     def is_available(cls) -> tuple[bool, str]:
         try:
             import sherpa_onnx  # noqa: F401
-            return True, "ready"
         except ImportError as e:
             return False, (
                 f"sherpa-onnx not installed: {e}. "
                 "Install with: pip install sherpa-onnx. "
                 "Download models from https://github.com/k2-fsa/sherpa-onnx/releases"
             )
+        # #919: sherpa-onnx ships no bundled default model — it can only
+        # synthesize once OMNIVOICE_SHERPA_MODEL points at a downloaded model
+        # directory. Gate on it here (like the other path-configured opt-in
+        # engines: Confucius4/dots/MOSS) so the picker marks it unavailable-
+        # with-a-reason instead of letting a user select it, generate, and hit
+        # a config error that used to be mislabeled as out-of-memory.
+        model_dir = os.environ.get("OMNIVOICE_SHERPA_MODEL", "").strip()
+        if not model_dir:
+            return False, (
+                "OMNIVOICE_SHERPA_MODEL not set. Point it to a sherpa-onnx TTS "
+                "model directory (containing model.onnx + tokens.txt), then "
+                "restart OmniVoice. Download models from "
+                "https://github.com/k2-fsa/sherpa-onnx/releases"
+            )
+        if not os.path.isfile(os.path.join(model_dir, "model.onnx")):
+            return False, (
+                f"No model.onnx in OMNIVOICE_SHERPA_MODEL ({model_dir}). Point "
+                "it at a sherpa-onnx TTS model directory containing model.onnx "
+                "+ tokens.txt. Download models from "
+                "https://github.com/k2-fsa/sherpa-onnx/releases"
+            )
+        return True, "ready"
 
     @property
     def sample_rate(self) -> int:
@@ -1151,6 +1231,19 @@ _LAZY_REGISTRY: dict[str, tuple[str, str]] = {
     # this module for TTSBackend). The class is resolved on first
     # attribute access via the LazyRegistry below.
     "supertonic3": ("engines.supertonic3", "Supertonic3Backend"),
+    # Issue #498: MOSS-TTS-v1.5 (8B) and dots.tts (2B) — both opt-in,
+    # subprocess-isolated with their own venv because each pins a
+    # transformers version that conflicts with the parent's >=5.3
+    # (MOSS == 5.0.0, dots.tts == 4.57.0). Same dedicated-venv pattern as
+    # IndexTTS2. Lazy for the same import-cycle reason as the entries above.
+    "moss-tts-v15": ("engines.moss_tts_v15", "MossTTSV15Backend"),
+    "dots-tts": ("engines.dots_tts", "DotsTTSBackend"),
+    # Issue #590: Confucius4-TTS (netease-youdao) — LLM-based, 14-language
+    # cross-lingual zero-shot cloning, Apache-2.0. Opt-in + subprocess-isolated
+    # (own Python 3.10 venv) like the entries above. Validated end-to-end
+    # 2026-07-02 (CPU, Apple Silicon; 22.05 kHz output). Gated behind
+    # OMNIVOICE_CONFUCIUS4_TTS_DIR so it's inert until enabled.
+    "confucius4-tts": ("engines.confucius4", "Confucius4Backend"),
 }
 
 
@@ -1244,6 +1337,26 @@ _INSTALL_HINTS: dict[str, str] = {
     "sherpa-onnx":   "pip install sherpa-onnx  (universal ONNX runtime, WASM-ready)",
     "omnivoice-gguf":"Bundled — runs the C++ omnivoice-tts binary in bin/. Quants download lazily from Serveurperso/OmniVoice-GGUF on first generate.",
     "supertonic3":   "uv sync --extra supertonic  (CPU-only ONNX, 31 langs, ~400 MB model on first use; OpenRAIL-M model license)",
+    "moss-tts-v15":  "git clone OpenMOSS/MOSS-TTS + set OMNIVOICE_MOSS_TTS_V15_DIR  (own venv, transformers==5.0; 8B, ~16 GB weights; CUDA/CPU, no MPS; Apache-2.0)",
+    "dots-tts":      "git clone rednote-hilab/dots.tts + set OMNIVOICE_DOTS_TTS_DIR  (own venv, transformers==4.57; 2B, ~9 GB weights; CUDA/CPU, Linux/macOS only — no Windows; Apache-2.0)",
+    "confucius4-tts":"git clone netease-youdao/Confucius4-TTS + set OMNIVOICE_CONFUCIUS4_TTS_DIR  (own Python 3.10 venv; 14-lang cross-lingual zero-shot clone; ~5 GB weights auto-download; CUDA/CPU, no MPS; Apache-2.0)",
+}
+
+
+# Copy-paste-ready setup line for opt-in engines gated behind a filesystem-path
+# env var (issue #498 / #590). The install_hint tells users a var exists; this
+# is the *exact* `export VAR=...` line to run, so they don't have to reconstruct
+# it from the docs. Surfaced verbatim in the Compat Matrix's "Why unavailable?"
+# disclosure with a Copy button. Single-sourced here so it can't drift from the
+# var each engine's is_available() actually reads. bash/zsh form (the dominant
+# clone-and-run workflow for these engines; dots.tts is *nix-only anyway).
+_SETUP_SNIPPETS: dict[str, str] = {
+    "indextts2":      "export OMNIVOICE_INDEXTTS_DIR=/path/to/index-tts",
+    "moss-tts-v15":   "export OMNIVOICE_MOSS_TTS_V15_DIR=/path/to/MOSS-TTS",
+    "dots-tts":       "export OMNIVOICE_DOTS_TTS_DIR=/path/to/dots.tts",
+    "confucius4-tts": "export OMNIVOICE_CONFUCIUS4_TTS_DIR=/path/to/Confucius4-TTS",
+    # #919: sherpa-onnx gates on a downloaded model dir (model.onnx + tokens.txt).
+    "sherpa-onnx":    "export OMNIVOICE_SHERPA_MODEL=/path/to/sherpa-onnx-model",
 }
 
 
@@ -1258,6 +1371,7 @@ def list_backends() -> list[dict]:
           "available":      bool,
           "reason":         Optional[str],          # message when not available
           "install_hint":   Optional[str],
+          "setup_snippet":  Optional[str],          # exact `export VAR=...` for path-gated opt-in engines
           "last_error":     Optional[str],          # cached most-recent failure
           "isolation_mode": "in-process" | "subprocess",
           "gpu_compat":     list[str],              # subset of {cuda, rocm, mps, xpu, cpu}
@@ -1321,6 +1435,8 @@ def list_backends() -> list[dict]:
             "available": ok,
             "reason": None if ok else _mask_hf_tokens(msg),
             "install_hint": _INSTALL_HINTS.get(bid),
+            # Exact `export VAR=...` line for path-gated opt-in engines, or None.
+            "setup_snippet": _SETUP_SNIPPETS.get(bid),
             "last_error": _LAST_ERRORS.get(bid),
             "isolation_mode": isolation,
             "gpu_compat": list(gpu_compat),

backend/tests/test_asr_oom_fallback.py

@@ -25,7 +25,17 @@ sys.modules["core.config"] = _config
 
 whisperx = pytest.importorskip("whisperx")
 
-from services.asr_backend import WhisperXBackend  # noqa: E402
+from services.asr_backend import (  # noqa: E402
+    WhisperXBackend,
+    _is_compute_type_error,
+)
+
+# The exact ValueError CTranslate2 raises at model construction on a GPU
+# without efficient fp16 (older Maxwell/Pascal, GTX 16xx) or a cuDNN mismatch.
+_FP16_ERR = (
+    "Requested float16 compute type, but the target device or backend do not "
+    "support efficient float16 computation"
+)
 
 
 def test_cuda_oom_falls_back_to_cpu(monkeypatch):
@@ -52,8 +62,13 @@ def test_cuda_oom_falls_back_to_cpu(monkeypatch):
 
 
 def test_non_oom_runtime_error_still_raises(monkeypatch):
+    msg = "some other failure"
+    # A generic non-OOM, non-compute-type RuntimeError must still propagate —
+    # the new compute_type fallback must NOT swallow it.
+    assert _is_compute_type_error(msg) is False
+
     def fake_load_model(name, device, compute_type, **kw):
-        raise RuntimeError("some other failure")  # not an OOM → must propagate
+        raise RuntimeError(msg)  # not an OOM, not compute-type → must propagate
 
     monkeypatch.setattr(whisperx, "load_model", fake_load_model)
 
@@ -62,3 +77,63 @@ def test_non_oom_runtime_error_still_raises(monkeypatch):
     be._allow_vad_pickle_globals = lambda: None
     with pytest.raises(RuntimeError, match="some other failure"):
         be._ensure_asr()
+
+
+def test_float16_unsupported_falls_back_to_int8(monkeypatch):
+    """#551: a GPU without efficient fp16 raises a ValueError at load for both
+    float16 AND int8_float16; the backend must degrade to int8 on the SAME
+    device (cuda) without raising — not fall to CPU and not crash."""
+    calls = []
+
+    def fake_load_model(name, device, compute_type, **kw):
+        calls.append((device, compute_type))
+        if device == "cuda" and compute_type in ("float16", "int8_float16"):
+            raise ValueError(_FP16_ERR)
+        return object()  # cuda int8 succeeds
+
+    monkeypatch.setattr(whisperx, "load_model", fake_load_model)
+
+    be = WhisperXBackend()
+    be._device, be._compute_type = "cuda", "float16"
+    be._allow_vad_pickle_globals = lambda: None
+
+    be._ensure_asr()
+
+    assert be._asr is not None                       # recovered, no raise
+    assert be._device == "cuda" and be._compute_type == "int8"  # same device, int8
+    assert calls == [("cuda", "float16"), ("cuda", "int8_float16"), ("cuda", "int8")]
+
+
+def test_faster_whisper_float16_unsupported_falls_back_to_int8(monkeypatch):
+    """Mirror for FasterWhisperBackend: float16 + int8_float16 raise the fp16
+    ValueError, int8 succeeds → loads on (cuda, int8) without raising."""
+    import services.asr_backend as asr_backend
+    from services.asr_backend import FasterWhisperBackend
+
+    calls = []
+
+    class FakeWhisperModel:
+        def __init__(self, name, device, compute_type, **kw):
+            calls.append((device, compute_type))
+            if device == "cuda" and compute_type in ("float16", "int8_float16"):
+                raise ValueError(_FP16_ERR)
+            # cuda int8 succeeds
+
+    fake_fw = types.ModuleType("faster_whisper")
+    fake_fw.WhisperModel = FakeWhisperModel
+    monkeypatch.setitem(sys.modules, "faster_whisper", fake_fw)
+
+    # Force the CUDA starting point regardless of the CI host's hardware by
+    # making torch.cuda.is_available() return True inside _ensure_model.
+    fake_torch = types.ModuleType("torch")
+    fake_torch.cuda = types.SimpleNamespace(
+        is_available=lambda: True, empty_cache=lambda: None
+    )
+    monkeypatch.setitem(sys.modules, "torch", fake_torch)
+
+    be = FasterWhisperBackend()
+    be._ensure_model()
+
+    assert be._model is not None                     # recovered, no raise
+    assert be._device == "cuda" and be._compute_type == "int8"
+    assert calls == [("cuda", "float16"), ("cuda", "int8_float16"), ("cuda", "int8")]

backend/tests/test_asr_speechbrain_lazy_guard.py

@@ -0,0 +1,84 @@
+"""speechbrain LazyModule cross-platform guard (#630/#611/#647).
+
+speechbrain 1.x suppresses optional-integration imports (k2_fsa, numba, …) that
+are triggered merely by introspection from the stdlib `inspect` module. Its
+guard checked `filename.endswith("/inspect.py")` — a hardcoded POSIX separator —
+so on Windows (backslash paths) the guard MISSED and a stray access to the
+`speechbrain.k2_integration` redirect actually imported the (absent) k2 package,
+raising `ImportError: Lazy import of LazyModule(...k2_fsa...) failed` that aborted
+WhisperX transcription with zero segments.
+
+`_harden_speechbrain_lazy_imports()` re-implements `ensure_module` with an
+`os.path.basename` check so the guard fires on every platform. These tests fake
+the importer frame (both Windows- and POSIX-style `inspect.py` paths, plus a
+real-caller path) so they pin the behaviour regardless of the host OS.
+"""
+import os
+import sys
+
+import pytest
+
+sys.path.insert(0, os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+importutils = pytest.importorskip(
+    "speechbrain.utils.importutils",
+    reason="speechbrain not installed in this environment",
+)
+from services.asr_backend import _harden_speechbrain_lazy_imports  # noqa: E402
+
+
+class _FakeFrameInfo:
+    def __init__(self, filename):
+        self.filename = filename
+
+
+def _bogus_lazy_module():
+    # A LazyModule whose target can never import — so we can observe whether the
+    # inspect.py guard fired (AttributeError) or the import was attempted (ImportError).
+    return importutils.LazyModule(
+        "omnivoice_nonexistent_zzz",
+        "omnivoice_nonexistent_zzz_target",
+        None,
+    )
+
+
+@pytest.mark.parametrize(
+    "inspect_path",
+    [
+        r"C:\Python311\Lib\inspect.py",   # Windows — the case the old guard missed
+        "/usr/lib/python3.11/inspect.py",  # POSIX — already worked, must keep working
+    ],
+)
+def test_guard_fires_for_inspect_frame_on_any_separator(monkeypatch, inspect_path):
+    _harden_speechbrain_lazy_imports()
+    lm = _bogus_lazy_module()
+    monkeypatch.setattr(
+        importutils.inspect, "getframeinfo",
+        lambda *_a, **_k: _FakeFrameInfo(inspect_path),
+    )
+    # Guard must treat an inspect.py-triggered access as "attribute absent"
+    # (AttributeError) rather than attempting the doomed import (ImportError).
+    with pytest.raises(AttributeError):
+        lm.ensure_module(0)
+
+
+def test_real_caller_still_surfaces_import_error(monkeypatch):
+    """A genuine access from real user code (not inspect.py) with the target
+    missing must still raise ImportError — we only suppress inspect-triggered
+    spurious imports, never legitimate failures."""
+    _harden_speechbrain_lazy_imports()
+    lm = _bogus_lazy_module()
+    monkeypatch.setattr(
+        importutils.inspect, "getframeinfo",
+        lambda *_a, **_k: _FakeFrameInfo(r"C:\Users\me\app\real_caller.py"),
+    )
+    with pytest.raises(ImportError):
+        lm.ensure_module(0)
+
+
+def test_patch_is_idempotent():
+    _harden_speechbrain_lazy_imports()
+    first = importutils.LazyModule.ensure_module
+    _harden_speechbrain_lazy_imports()
+    assert importutils.LazyModule.ensure_module is first
+    assert getattr(importutils.LazyModule, "_omnivoice_xplat_guard", False) is True

backend/tests/test_asr_transcribe_timeout.py

@@ -0,0 +1,238 @@
+"""Whole-file ASR transcribe must be wall-clock bounded (TamKieu / Vietnam report).
+
+The chunked dub pipeline already bounds each chunk, but the whole-file paths
+(dub QC re-transcribe, dictation, OpenAI-compat) ran unbounded — a slow/stuck
+transcribe (e.g. large-v3 on a VRAM-starved GPU) hung the request *and* held a
+GPU-pool worker, surfacing in the UI as the misleading "can't reach the local
+backend". `run_transcribe_guarded` bounds them and raises `ASRTimeoutError` with
+actionable guidance. These tests pin the timeout path, the pass-through path, and
+that the error message tells the user what to do.
+"""
+import asyncio
+import os
+import sys
+import time
+
+import pytest
+
+sys.path.insert(0, os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+from services import asr_backend  # noqa: E402
+from services.asr_backend import (  # noqa: E402
+    ASRTimeoutError,
+    ASR_TRANSCRIBE_TIMEOUT_S,
+    reset_pool_after_wedge,
+    run_transcribe_guarded,
+)
+from concurrent.futures import ThreadPoolExecutor  # noqa: E402
+
+
+@pytest.fixture(autouse=True)
+def _fresh_timeout_streak(monkeypatch):
+    """The consecutive-timeout streak (#730 residual B) is process-global
+    session state; zero it per test so ordering can't leak recommendations,
+    and pin the active engine so a dev box's prefs can't flip the hint."""
+    monkeypatch.setattr(asr_backend, "_timeout_streak", 0)
+    monkeypatch.setattr(asr_backend, "active_backend_id", lambda: "whisperx")
+
+
+def test_default_timeout_is_env_overridable(monkeypatch):
+    # The constant is read at import; just assert it's a sane positive default.
+    assert ASR_TRANSCRIBE_TIMEOUT_S > 0
+
+
+def test_slow_transcribe_raises_actionable_timeout():
+    pool = ThreadPoolExecutor(max_workers=1)
+
+    def _hang():
+        time.sleep(5)  # would block far past our tiny timeout
+        return "never"
+
+    async def _go():
+        with pytest.raises(ASRTimeoutError) as ei:
+            await run_transcribe_guarded(pool, _hang, what="QC", timeout=0.2)
+        msg = str(ei.value)
+        # Message must reassure (backend alive) + give concrete remedies.
+        assert "backend is running" in msg
+        assert "Settings → Models" in msg
+        assert "CPU" in msg
+
+    asyncio.run(_go())
+    pool.shutdown(wait=False)
+
+
+def test_fast_transcribe_passes_through():
+    pool = ThreadPoolExecutor(max_workers=1)
+
+    def _quick():
+        return {"segments": [{"text": "hi"}]}, "whisperx"
+
+    async def _go():
+        out = await run_transcribe_guarded(pool, _quick, what="Dictation", timeout=5.0)
+        assert out == ({"segments": [{"text": "hi"}]}, "whisperx")
+
+    asyncio.run(_go())
+    pool.shutdown(wait=True)
+
+
+def test_timeout_error_is_a_timeouterror_subclass():
+    # Routers that catch broad TimeoutError (openai_compat) must also catch ours.
+    assert issubclass(ASRTimeoutError, TimeoutError)
+
+
+def test_timeout_resets_a_resilient_pool_to_restore_capacity():
+    # #730: a wedged transcribe holds its GPU-pool worker forever; with a 1-2
+    # worker pool that starves TTS generate and surfaces as "can't reach
+    # backend". On timeout, run_transcribe_guarded must reset() a pool that
+    # supports it (the real _ResilientGpuPool) so the next submit gets a fresh
+    # worker — capacity restored without an app restart.
+    class _FakePool(ThreadPoolExecutor):
+        def __init__(self):
+            super().__init__(max_workers=1)
+            self.reset_calls = 0
+
+        def reset(self):
+            self.reset_calls += 1
+
+    pool = _FakePool()
+
+    def _hang():
+        time.sleep(5)
+        return "never"
+
+    async def _go():
+        with pytest.raises(ASRTimeoutError):
+            await run_transcribe_guarded(pool, _hang, what="Dub", timeout=0.2)
+
+    asyncio.run(_go())
+    assert pool.reset_calls == 1
+    pool.shutdown(wait=False)
+
+
+def test_timeout_without_reset_capable_pool_does_not_crash():
+    # A plain ThreadPoolExecutor (no reset) must still bound + raise cleanly —
+    # the reset() is best-effort, never required.
+    pool = ThreadPoolExecutor(max_workers=1)
+
+    def _hang():
+        time.sleep(5)
+        return "never"
+
+    async def _go():
+        with pytest.raises(ASRTimeoutError):
+            await run_transcribe_guarded(pool, _hang, what="QC", timeout=0.2)
+
+    asyncio.run(_go())
+    pool.shutdown(wait=False)
+
+
+# ── Residual B on #730: consecutive timeouts recommend the isolated engine ──
+
+
+def _hang_forever():
+    time.sleep(5)
+    return "never"
+
+
+async def _timeout_once(pool, timeout=0.1) -> str:
+    with pytest.raises(ASRTimeoutError) as ei:
+        await run_transcribe_guarded(pool, _hang_forever, what="Dub", timeout=timeout)
+    return str(ei.value)
+
+
+def test_second_consecutive_timeout_recommends_isolated_engine():
+    """When guarded timeouts hit twice in a row in one session, pool resets
+    clearly aren't recovering the hang — the error the user sees must name the
+    crash-isolated escape-hatch engine (and make clear we never auto-switch)."""
+    pool = ThreadPoolExecutor(max_workers=2)
+
+    async def _go():
+        first = await _timeout_once(pool)
+        assert "faster-whisper-isolated" not in first  # one timeout ≠ a pattern
+        second = await _timeout_once(pool)
+        assert "faster-whisper-isolated" in second
+        assert "Settings → Engines" in second
+        assert "never switches engines automatically" in second
+
+    asyncio.run(_go())
+    pool.shutdown(wait=False)
+
+
+def test_successful_transcribe_resets_the_timeout_streak():
+    """'Consecutive' must mean consecutive: a transcribe that completes between
+    two timeouts proves the pool recovered, so the recommendation must not fire."""
+    pool = ThreadPoolExecutor(max_workers=3)
+
+    async def _go():
+        await _timeout_once(pool)
+        out = await run_transcribe_guarded(pool, lambda: "ok", what="Dub", timeout=5.0)
+        assert out == "ok"
+        second = await _timeout_once(pool)
+        assert "faster-whisper-isolated" not in second
+
+    asyncio.run(_go())
+    pool.shutdown(wait=False)
+
+
+def test_no_recommendation_when_already_on_isolated_engine(monkeypatch):
+    """Recommending the isolated engine to a user already running it is noise —
+    the base message's smaller-model/CPU guidance is all that's left."""
+    monkeypatch.setattr(
+        asr_backend, "active_backend_id", lambda: "faster-whisper-isolated"
+    )
+    pool = ThreadPoolExecutor(max_workers=2)
+
+    async def _go():
+        await _timeout_once(pool)
+        second = await _timeout_once(pool)
+        assert "faster-whisper-isolated) in Settings" not in second
+        assert "never switches engines automatically" not in second
+
+    asyncio.run(_go())
+    pool.shutdown(wait=False)
+
+
+def test_timeout_env_name_is_parameterized():
+    """The chunked dub path passes its own knob; the message must name IT, not
+    the whole-file env var (actionable errors point at the right dial)."""
+    pool = ThreadPoolExecutor(max_workers=1)
+
+    async def _go():
+        with pytest.raises(ASRTimeoutError) as ei:
+            await run_transcribe_guarded(
+                pool, _hang_forever, what="Dub chunk 1/3", timeout=0.1,
+                timeout_env="OMNIVOICE_TRANSCRIBE_CHUNK_TIMEOUT_S",
+            )
+        msg = str(ei.value)
+        assert "OMNIVOICE_TRANSCRIBE_CHUNK_TIMEOUT_S" in msg
+        assert "OMNIVOICE_ASR_TRANSCRIBE_TIMEOUT_S" not in msg
+
+    asyncio.run(_go())
+    pool.shutdown(wait=False)
+
+
+def test_reset_pool_after_wedge_is_shared_and_best_effort():
+    """One reset mechanism for every transcribe path (#730 residual A): it
+    resets a reset-capable pool, no-ops a plain executor, and never raises."""
+
+    class _Pool:
+        resets = 0
+
+        def reset(self):
+            self.resets += 1
+
+    p = _Pool()
+    assert reset_pool_after_wedge(p, what="Dub chunk 1/2") is True
+    assert p.resets == 1
+
+    plain = ThreadPoolExecutor(max_workers=1)
+    try:
+        assert reset_pool_after_wedge(plain) is False
+    finally:
+        plain.shutdown(wait=False)
+
+    class _Broken:
+        def reset(self):
+            raise RuntimeError("reset blew up")
+
+    assert reset_pool_after_wedge(_Broken()) is False  # must not raise

docs/css-to-tailwind-migration.md

@@ -0,0 +1,352 @@
+# Migration — Per-Component `.css` → Tailwind v4 Utilities
+
+**Status:** Plan (not yet executed) · **Drafted:** 2026-06-30 · **Type:** Incremental styling migration, no intended visual change
+**Owner stance:** leans toward a full migration but values not breaking the UI · **This plan's recommendation:** *bounded* migration (utilities for layout/spacing/typography everywhere; keep CSS for the hard stuff). See §8.
+
+## Why
+
+`frontend/src` carries **74 `.css` files / 16,615 lines** of global, BEM-ish CSS
+(`dub-col`, `models-row__role`, `readiness-checklist__title`, …). Tailwind v4 is
+**already wired** — `src/index.css` imports `tailwindcss/theme.css` +
+`tailwindcss/utilities.css`, has an `@theme` block, and `vite.config.js` runs
+`@tailwindcss/vite`. So the runtime cost of utilities is already paid; we are just
+not using them. Editing a layout today means hunting a class across a 989-line
+file and a JSX `className`. Utilities put the layout where it's read — in the JSX —
+and shrink the per-component CSS to only what utilities can't express.
+
+This is **not** a redesign. Every step must render pixel-identical. The honest
+blocker is that **there are zero visual-regression tests** — the prior page
+refactors (see `docs/maintenance-pages-modularization.md`) verified "no change"
+by diffing `className` strings, and *that trick is useless here because the whole
+point is that class names change*. Closing that gap is the first real task (§4),
+not an afterthought.
+
+## Current state (measured 2026-06-30)
+
+| Metric | Value |
+|--------|------:|
+| `.css` files | 74 |
+| Total CSS lines | 16,615 |
+| `var(--…)` token references across CSS | ~3,200 |
+| Files using `display:flex` | 64 |
+| Files using `display:grid` / `grid-template` | 27 |
+| Files using `transition:` | 46 |
+| Files using `box-shadow` | 43 |
+| Files using `@media` | 25 |
+| Files using `linear/radial-gradient` | 22 |
+| Files using `@keyframes` (73 blocks total) | 30 |
+| Files using `animation:` | 34 |
+| Files using `backdrop-filter`/glass blur | 11 |
+| Files using `::before`/`::after` | 11 |
+| Files using `:has()` | 3 |
+| Files using `!important` | 14 |
+
+Biggest files (conversion ROI ranked by layout density, not raw size):
+`index.css` 2532 · `FirstRunSetup.css` 1020 · `DubTab.css` 989 ·
+`VoiceGallery.css` 541 · `StoriesEditor.css` 525 · `LogsFooter.css` 507 ·
+`Settings.css` 469 · `CloneDesignTab.css` 458 · `settings/primitives/primitives.css` 368.
+
+The token system (do **not** redesign it):
+
+- `src/ui/tokens.css` (157 lines, ~82 custom props): the declared "single source of
+  truth" — colors, a 4px spacing scale (`--space-0..9`), radius, fonts, type scale,
+  weights, shadows, motion, z-index, focus ring, glass blur. Imported via `src/ui/index.js`.
+- `src/ui/themes.css` (188 lines): per-theme overrides of the semantic color tokens,
+  keyed on `[data-theme="midnight|nord|solarized|…"]` on `<html>`. Default (no attribute)
+  = Gruvbox Dark.
+- `src/index.css` `@theme { … }`: maps a subset of tokens into Tailwind's theme
+  namespace (`--color-*`, `--radius-*`, `--font-*`) so utilities like `bg-bg`,
+  `text-fg`, `rounded-lg`, `font-mono` exist. **It hardcodes hex literals that
+  duplicate `tokens.css`** — the known drift bug (see §2).
+
+Load order today: `index.css` (`@theme` → `theme` layer, lowest priority) is
+imported in `App.jsx`; `tokens.css` + `themes.css` are **unlayered** `:root` /
+`[data-theme]` rules imported via `ui/index.js`. Because unlayered CSS outranks
+`@layer theme`, **`tokens.css` already wins for the default values and theming
+already works** — the `@theme` hex literals are effectively a *losing duplicate*
+that exists only so Tailwind knows the utility names. That is precisely why they
+drift silently: nothing at runtime reads them, so a stale value never shows up.
+
+## Strategy (the shape of the whole thing)
+
+1. **Incremental, component-by-component — never big-bang.** One component (or one
+   small cluster) per PR. Each PR is independently shippable and CI-green. A
+   half-migrated component is fine; a half-migrated *codebase* is the steady state
+   for months and that's acceptable.
+2. **Utilities-first for the mechanical 80%:** flexbox, grid, gap, padding/margin,
+   width/height, `text-*`/`font-*`, `rounded-*`, `border`, simple `bg-*`/`text-*`
+   color, `hidden`, `truncate`, basic `hover:`/`focus:` color states. These map 1:1
+   to utilities and are where the line-count win lives.
+3. **Keep `.css` for the hard 20%:** glassmorphism (layered gradients +
+   `backdrop-filter`), `::before`/`::after`, `@keyframes`, `:has()` and other complex
+   combinators, `[data-theme]`-specific rules, and anything with `!important`
+   fighting specificity. Utilities don't express these cleanly and forcing them
+   (arbitrary-value soup, `[&::before]:…`) trades readable CSS for unreadable JSX.
+4. **One source of truth via the token bridge (§2):** utilities reference the same
+   CSS vars the remaining `.css` reads, so a value lives in exactly one place and
+   `data-theme` switching keeps working for both.
+5. **No file is "done" until it's deleted or demonstrably minimal.** Success is
+   measured in CSS LOC removed and `.css` files deleted, not files "touched."
+
+## 2. Token-bridge prerequisite (P0 — gates everything)
+
+The migration is only safe if a utility and the leftover CSS in the same component
+resolve a token to the *same* value, including after a theme switch. Today the
+`@theme` literals duplicate `tokens.css`; once components start mixing `bg-bg`
+(utility) with `background: var(--color-bg)` (CSS), any drift becomes a visible,
+theme-dependent bug. Fix the source-of-truth **before** converting anything.
+
+**Recommended fix — Solution A (lowest churn, no rename):** Make `@theme` the
+single declared home for the **already-overlapping** groups only — colors, radius,
+fonts — and **delete those default declarations from `tokens.css`** (leave a
+one-line pointer comment). Everything else in `tokens.css` (spacing, type scale,
+weights, shadows, motion, z-index, focus ring, glass blur) stays put.
+
+Why this is correct and safe:
+
+- Tailwind needs the keys present in `@theme` to generate the utility names
+  (`--color-fg` → `text-fg`/`bg-fg`; `--radius-lg` → `rounded-lg`; `--font-mono` →
+  `font-mono`). Keeping the keys there is non-negotiable.
+- `@theme` emits `:root { --color-fg: … }` into the low-priority `theme` layer.
+  `themes.css` `[data-theme]` rules are unlayered and still outrank it, so
+  **theme switching is unchanged** — verify with a quick manual cycle through all
+  themes after the edit.
+- Removing the duplicate `:root` color/radius/font lines from `tokens.css` leaves
+  exactly one literal per value. All ~3,200 existing `var(--…)` references keep
+  resolving (the var still exists on `:root`, now sourced from `@theme`).
+
+**Guard against recurrence (required, per the "fix the class" rule):** add
+`frontend/src/__tests__/theme-token-parity.test.js` (vitest, no browser) that
+parses `index.css` `@theme` + `tokens.css` + `themes.css` and asserts:
+(a) no token key is declared with a literal in **both** `@theme` and `tokens.css`
+(catches re-introduced duplication), and (b) every `@theme` color key is overridden
+by every `[data-theme]` block in `themes.css` (catches a theme that forgot a color).
+This test is the thing that makes the de-dup *stay* de-duped.
+
+**Rejected alternative — Solution B (purist):** rename source tokens to a private
+namespace (`--ov-color-fg`) and bridge with `@theme inline { --color-fg:
+var(--ov-color-fg) }`. This honors "`tokens.css` is the source" literally and is
+the textbook Tailwind pattern, **but** it forces renaming all ~3,200 `var(--color-*)`
+references across 74 files in one shot — a massive, high-risk diff that violates
+"low-risk, incremental." Not worth it. (`@theme inline` referencing the *same* name
+is circular and is not an option.)
+
+**Optionally, later:** add `--spacing` to `@theme` so `p-*`/`gap-*`/`m-*` map onto
+the existing 4px scale (`--space-1 = 2px` … `--space-9 = 44px`). Tailwind's default
+spacing is a 0.25rem multiplier; OmniVoice's scale is custom, so without this,
+`gap-3` ≠ `var(--space-3)`. Two choices, decide in P0:
+  - **Map to the scale:** set `--spacing: 2px` won't reproduce the non-linear steps;
+    instead define explicit `--spacing-1..9` in `@theme` mirroring `--space-1..9`,
+    and use `gap-2`/`p-5` etc. Cleanest for readers, but utility numbers won't match
+    Tailwind defaults — document it.
+  - **Use arbitrary values bridged to the var:** `gap-[var(--space-3)]`,
+    `p-[var(--space-5)]`. Zero ambiguity, slightly noisier JSX, guarantees identical
+    pixels. **Recommended for P1–P2** (safest for "no visual change"); revisit named
+    spacing once confidence is high.
+
+## 3. What converts cleanly vs. what stays CSS
+
+**Converts cleanly → utilities** (concrete, from real files):
+
+- `ReadinessChecklist.css` `.readiness-checklist { display:flex; flex-direction:column;
+  gap:var(--space-3); padding:var(--space-5); border:1px solid var(--color-border);
+  border-radius:var(--radius-lg); font-size:var(--text-sm); }`
+  → `className="flex flex-col gap-[var(--space-3)] p-[var(--space-5)] border
+  border-border rounded-lg text-sm"` (or mapped `text-sm` if the type scale is
+  bridged). The `backdrop-filter` line on the same selector **stays in CSS** (see below).
+- `.readiness-checklist__title { font-weight:var(--weight-semibold);
+  color:var(--color-fg); display:flex; align-items:center; gap:var(--space-3); }`
+  → `font-semibold text-fg flex items-center gap-[var(--space-3)]`.
+- Generic layout rows/cols (`dub-col`, `models-row`) — flex/grid/gap/padding → utilities.
+
+**Stays in `.css`** (criteria + real examples):
+
+- **Glassmorphism / layered backgrounds.** `Panel.css` `.ui-panel--glass` stacks two
+  `radial-gradient`s + a `linear-gradient` + `backdrop-filter: var(--glass-blur-md)`.
+  Leave entirely in CSS. (11 files use glass blur.)
+- **Pseudo-elements.** `Panel.css` `.ui-panel--glass::before` (top hairline gradient);
+  `DubTab.css` `.dub-stepper__step::before` (connector line). 11 files. Stay.
+- **Keyframes + animations.** 73 `@keyframes` blocks across 30 files
+  (`@keyframes mesh/spin/pulse/shimmer` in `index.css`; `dub-pulse`,
+  `dub-stepper-spin`, `dub-skel-shimmer` in `DubTab.css`). Keep the `@keyframes` and
+  the `animation:` shorthand in CSS; a `className="animate-…"` only helps if you
+  register the animation in `@theme`, which isn't worth it for one-off effects.
+- **`:has()` and complex combinators** (3 files), **`[data-theme]`-specific rules**
+  (all of `themes.css` + scattered overrides), **`!important` blocks** (14 files,
+  e.g. `DubTab.css` `.dub-footer-panel::before { display:none !important; }`).
+- **Media queries** (25 files): convertible to `sm:`/`md:`/`lg:` **only** if the
+  breakpoints match Tailwind's; OmniVoice's are custom, so leave responsive blocks in
+  CSS unless a component's breakpoints are first added to `@theme`. Low priority.
+
+Rule of thumb for a reviewer: *if a declaration reads a single token and sets one
+box/text/flex property, it's a utility; if it composes multiple values, targets a
+pseudo-element/state combinator, or animates, it stays.*
+
+## 4. Risk mitigation — the no-visual-test gap (the gating risk)
+
+This is the make-or-break item. Be honest: **without a visual baseline, "no change"
+is unverifiable**, and `className`-diffing (what the page refactors relied on) cannot
+work when class names are the thing changing. Two layers, do both:
+
+**(a) Establish a screenshot baseline before touching components (part of P0).**
+Add Playwright component/page screenshots for the surfaces being migrated. The repo
+already references Playwright tooling in its docs stack; wire a minimal
+`tests/visual/` that boots the Vite app (or Storybook-less direct route renders) and
+captures per-component PNGs at a fixed viewport for **the default theme + one dark +
+one light theme** (catches token-bridge regressions specifically). Commit baselines.
+Each migration PR runs `playwright test --update-snapshots=none` and **fails on any
+pixel diff above a tiny threshold**. This converts "did it change?" from a human
+guess into a CI gate. Capture baselines *first*, on `main`, so they reflect
+pre-migration truth.
+
+- Scope realistically: snapshotting all 74 surfaces up front is its own project.
+  Snapshot **per phase, just-in-time** — before P1 leaf work, baseline the leaf
+  components; before P3, baseline the big pages. Baselines for a component land in
+  the same PR that prepares to migrate it (separate from the conversion PR so the
+  baseline diff is reviewable on its own).
+
+**(b) A per-component manual checklist** (belt-and-suspenders, and the fallback for
+surfaces that are hard to screenshot deterministically — anything with animation,
+canvas/waveform, or live backend data):
+  1. Default theme: side-by-side before/after at the same viewport.
+  2. Cycle every `[data-theme]` — confirm colors still swap (token-bridge check).
+  3. Hover/focus/active/disabled states on interactive elements.
+  4. The component's `@keyframes`/animation still runs.
+  5. `prefers-reduced-motion` path unaffected (e.g. `#root` launch animation).
+  6. No console warnings; `bun run build` + `bun run lint` clean.
+
+If neither (a) nor (b) is in place for a surface, **do not migrate it** — defer it to
+the "leave as CSS" bucket rather than fly blind.
+
+## 5. Phasing
+
+Each phase = one or more independently shippable, CI-green PRs. Ordered
+leaf-inward so blast radius grows only as confidence does.
+
+### P0 — Token bridge + tooling + visual baseline (no component conversions)
+- De-dup `@theme` ↔ `tokens.css` (§2 Solution A) + the parity test.
+- Decide + document the spacing approach (arbitrary-value bridge recommended).
+- Add `prettier-plugin-tailwindcss` (or confirm oxlint/oxfmt class-sort) and wire
+  class sorting (§6).
+- Update `CONTRIBUTING.md` (§6 — currently says *"Vanilla CSS … no Tailwind"*, which
+  now contradicts reality and **must** change in this same PR per the docs-sync rule).
+- Stand up `tests/visual/` Playwright harness (no per-component baselines yet — just
+  the runner + theme matrix).
+- **Effort:** ~1–2 days. **Success:** parity test green; theme switch verified across
+  all themes; CI gains a class-sort check; zero pixels changed (this PR ships no
+  component edits).
+
+### P1 — Leaf / presentational components (lowest risk)
+Targets: small `ui/` primitives and stateless components where CSS is mostly
+flex/grid/spacing/type — e.g. `Badge`, `UpdateStatusChip`, `NetworkToggle`,
+`ReadinessChecklist`, `ReadinessChecklist`, `DemoPresetGrid`, `KeyboardCheatsheet`,
+`MultiLangPicker`. Skip glass-heavy ones for now.
+- Per component: baseline screenshot PR → conversion PR. Convert layout/spacing/type
+  to utilities; keep any glass/`::before`/animation lines in a now-tiny `.css`; delete
+  the `.css` entirely if nothing remains and remove its import.
+- **Effort:** ~3–5 days across ~10–15 components. **Success:** ~10 `.css` files deleted
+  or reduced >70%; visual diffs clean; a repeatable per-component recipe proven.
+
+### P2 — Panels & mid-size components
+Targets: `settings/*Panel.css`, `Sidebar`, `NotificationPanel`, `CastingView`,
+`ExportModal`, `EngineCompatibilityMatrix`, `donate/Postcard`, etc. More state,
+some glass — convert the layout skeleton, leave glass/pseudo/animation.
+- **Effort:** ~1–1.5 weeks. **Success:** settings panels are thin utility JSX + a
+  shared `primitives.css` for the glass/control look; CSS LOC down materially.
+
+### P3 — Big pages
+Targets in ROI order: `DubTab` (989), `VoiceGallery` (541), `StoriesEditor` (525),
+`LogsFooter` (507), `Settings` (469), `CloneDesignTab` (458), `FirstRunSetup` (1020).
+These pair naturally with the already-planned page modularization
+(`docs/maintenance-pages-modularization.md`) — **sequence the modularization first**,
+then migrate the smaller extracted components (P3 becomes "P1 again" on the pieces).
+Convert layout/spacing; the pipeline steppers, overlays, gradients, and keyframes
+stay as CSS.
+- **Effort:** ~2–3 weeks. **Success:** each page's `.css` drops to the
+  glass/animation/pseudo residue; biggest single LOC reductions land here.
+
+### P4 — Retire `index.css` globals last
+`index.css` (2532 lines) is foundation: `@theme`, `@keyframes`, `::selection`, root
+rendering, base resets, and shared global classes. Convert only the **global utility
+classes** that components reuse into real utilities or component-scoped CSS; **keep**
+the `@theme`, keyframes, resets, and `::selection`. Do this last because everything
+depends on it.
+- **Effort:** ~1 week. **Success:** `index.css` shrinks to foundation only; no
+  orphaned global classes.
+
+## 6. Tooling
+
+- **Class sorting / formatting.** The repo lints with **oxlint** (`bun run lint`,
+  gate) and an advisory ESLint for hooks. For Tailwind class ordering, add
+  **`prettier-plugin-tailwindcss`** (canonical, understands `@theme`) wired to run on
+  `*.jsx`, *or* adopt oxfmt's Tailwind class-sorting if the team prefers a single
+  formatter. Either way the goal is deterministic class order so diffs stay readable
+  and merge-clean.
+- **Regression prevention.** Add an oxlint/convention guard so new components don't
+  reintroduce sprawling CSS: a soft rule (warn-only first, per "keep main green") that
+  flags new `.css` files over a small line budget for components that should be
+  utility-first, and the §2 parity test as a hard gate on token drift.
+- **CONTRIBUTING update (required).** `CONTRIBUTING.md` currently states *"CSS:
+  Vanilla CSS in component-level files — no Tailwind."* That is now false. Replace it
+  with the utilities-first standard: *layout/spacing/typography/simple color via
+  Tailwind utilities; component `.css` only for glass, pseudo-elements, keyframes,
+  `:has()`, `[data-theme]` rules, and `!important` overrides; tokens live in
+  `tokens.css`/`@theme`, never hardcoded.* Per the docs-sync hard rule this lands in
+  the **same PR** as P0.
+- **No new build infra** — `@tailwindcss/vite` already does everything; no PostCSS
+  config, no Tailwind config file (v4 is CSS-first via `@theme`).
+
+## 7. Non-goals / when to stop
+
+- **No 100% conversion target.** ~20% of the CSS (the 11 glass files, 30 keyframe
+  files, 11 pseudo-element files, 3 `:has()` files, 14 `!important` files, custom-
+  breakpoint media queries) is **genuinely better as CSS** and should stay. Forcing it
+  into arbitrary-value utilities makes JSX unreadable for zero benefit.
+- **No token-system redesign.** `tokens.css`/`themes.css` and the `data-theme` model
+  stay as-is (only the §2 de-dup).
+- **No visual redesign.** Pixel-identical is the contract; restyling is a separate task.
+- **No `.jsx` → `.tsx`**, no engine/backend/Tauri/Python surface, no version bump,
+  no dependency change beyond the dev-only formatter plugin + Playwright (frontend-only).
+- **Stop conditions for an individual file:** if after pulling out layout/spacing the
+  remaining CSS is all glass/animation/pseudo, it's *done* — don't chase the last 10%.
+- **Hands off** `BootstrapSplash.css`, `WaveformPlayer.css`/`SegmentTrack.css`
+  (canvas-adjacent), and other animation/`::before`-dominated files unless a clear
+  layout win exists.
+
+## 8. Effort + recommendation
+
+**Total rough effort:** ~5–7 focused weeks for P0–P4 at the *bounded* scope below,
+spread across many small PRs (it parallelizes and pauses cleanly — it never has to be
+one big push).
+
+**Recommendation — bounded migration, not 100%.** The owner leans full-migration and
+prizes not breaking things; those two goals partly conflict, and the honest call is:
+
+- **Do** convert layout/spacing/typography/simple color **everywhere** — that's the
+  real maintainability win, it's where ~80% of the 16.6k lines live, and it's the
+  low-risk part.
+- **Keep ~15–25% as CSS** (glass, keyframes, pseudo-elements, `:has()`,
+  `[data-theme]`, `!important`, custom-breakpoint media). Converting these buys
+  unreadable JSX and *raises* visual-regression risk on exactly the components where
+  diffs are hardest to verify.
+- **Gate on the visual baseline (§4).** This is the single most important decision: if
+  the Playwright screenshot harness doesn't ship in P0, do **not** start P1 — without
+  it the "won't break the UI" requirement is unmet by construction. The token-bridge
+  de-dup (§2) is the other hard prerequisite; both are cheap and both are P0.
+
+A realistic end state: ~60 `.css` files deleted or reduced >70%, perhaps ~10–12k of
+the 16.6k CSS lines removed, the rest a deliberate, documented residue of effects
+utilities can't express. That delivers nearly all the maintainability benefit of a
+"full" migration at a fraction of the regression risk.
+
+## Constraints honored
+
+- **Keep main green** — every phase is an independently CI-green PR; lint/format and
+  parity-test guards are warn-first where they'd otherwise churn.
+- **Docs-sync** — the `CONTRIBUTING.md` rewrite lands in the same PR as P0.
+- **No versioning/Docker/Tauri/Python impact** — frontend-only; dev-dependency-only
+  tooling additions; no `package.json` *version* bump (a devDependency add still
+  requires regenerating root `bun.lock` and confirming `bun install --frozen-lockfile`
+  per the Docker-green rule).
+- **Local-first / cross-platform parity** — pure styling; no behavior, no platform
+  divergence.

docs/downloading-models.md

@@ -14,6 +14,15 @@ download UI couldn't show real bytes/speed. Until a proper Xet progress hook
 lands, the app forces the **classic LFS path**, which streams through the
 standard progress reporter and gives accurate downloaded/remaining/speed.
 
+To keep that path **fast** despite Xet being off, the app runs a built-in
+**multi-connection (segmented) downloader on by default** — it fetches each file
+over parallel byte-ranges (IDM/uGet style), so the legacy-LFS path is no longer
+single-stream. It reports real live speed/ETA and **falls back to the normal
+download on any error**, so it can never compromise a correct install. Adding a
+free Hugging Face token (first-run setup, or Settings → Credentials) makes this
+faster still — authenticated downloads get higher rate limits and fewer stalls.
+To force the old single-stream path, set `OMNIVOICE_SEGMENTED_DOWNLOAD=0`.
+
 State is reported at **Settings → About** / `GET /system/info`:
 
 - `fast_download.xet_installed` — `hf_xet` present (true)
@@ -54,12 +63,13 @@ When a download starts you'll see, in order:
 
 ## Advanced / opt-in tuning
 
-All of these default **off** and apply to every platform identically. Set them
-as environment variables (or via **Settings → API keys / environment**).
+These apply to every platform identically. Set them as environment variables (or
+via **Settings → API keys / environment**). The segmented accelerator is **on by
+default** (set its var to `0` to disable); the rest default **off**.
 
 | Setting | Env var | Effect |
 |---|---|---|
-| Segmented accelerator | `OMNIVOICE_SEGMENTED_DOWNLOAD=1` | Multi-connection downloader (parallel byte-ranges) for the legacy-LFS path — restores parallel speed **and** shows live byte speed/ETA. Falls back to the normal download on any error; files land in the standard cache. Best paired with Xet disabled (the default). |
+| Segmented accelerator | `OMNIVOICE_SEGMENTED_DOWNLOAD=0` | **On by default** (see above). Set to `0` to force the old single-stream legacy-LFS download instead of the parallel byte-range one. |
 | Max parallel files | `OMNIVOICE_DOWNLOAD_MAX_WORKERS` (default 8) | Files fetched at once. Xet already parallelises *within* a file, so raising this rarely helps and uses more memory. |
 | High-performance mode | `HF_XET_HIGH_PERFORMANCE=1` | Maximum throughput. Needs lots of RAM and bandwidth — can **hurt** low-RAM machines. Leave off unless you have headroom. |
 | Spinning-disk (HDD) | `HF_XET_RECONSTRUCT_WRITE_SEQUENTIALLY=1` | Sequential writes; avoids parallel-write thrash on HDDs. Leave off on SSD/NVMe. |

docs/dubbing/translation-engines.md

@@ -0,0 +1,156 @@
+# Translation engines (Dub tab)
+
+OmniVoice dubs in two steps: **transcribe → translate → speak**. The *translate*
+step is pluggable — pick the engine in the Dub tab's **Engine** dropdown. Two
+engines are **built in** and always available offline; the rest need a small
+optional Python package.
+
+| Engine | Category | Needs a package? | Key needed? |
+|--------|----------|------------------|-------------|
+| **Argos** (Local, Fast) | offline | `argostranslate` (bundled) | no |
+| **NLLB-200** (Local, Heavy) | offline | none (uses core `transformers`) | no |
+| Google Translate (Free) | online | `deep_translator` | no |
+| DeepL | online | `deep_translator` | yes (`DEEPL_API_KEY`) |
+| Microsoft Translator | online | `deep_translator` | yes (`MICROSOFT_API_KEY`) |
+| MyMemory | online | `deep_translator` | no |
+| LLM (OpenAI-compatible) | llm | `openai` | usually yes |
+
+If you pick an engine whose package isn't importable yet, the Engine label shows
+a **highlighted Install affordance**, and — if you try to translate anyway — the
+backend returns a single, actionable error telling you exactly what to install
+(the install command is single-sourced, so the button and the error never
+disagree).
+
+## Installing optional translation engines (from-source vs packaged build)
+
+How you add an engine depends on **how you installed OmniVoice**.
+
+### From-source / dev install (one-click)
+
+If you cloned the repo and run OmniVoice from source (`uv sync` + the dev
+launcher) or via Docker, the app can install engines for you:
+
+1. In the Dub tab, open the translation settings and pick the engine you want
+   (e.g. **Google Translate**) from the **Engine** dropdown.
+2. A highlighted **Install** button appears next to the *Engine* label. Click it.
+3. OmniVoice runs the install into the **same** Python environment the backend
+   is using (`uv pip install <package> --python <backend-interpreter>`), then
+   re-probes. When it reports *"restart the backend to load it"*, restart so the
+   freshly-installed module is importable.
+
+You can also install by hand into the backend venv:
+
+```
+uv pip install deep_translator   # Google / DeepL / Microsoft / MyMemory
+uv pip install argostranslate    # Argos (already bundled; rarely needed)
+uv pip install openai            # LLM (OpenAI-compatible) provider
+```
+
+Then restart the backend.
+
+### Packaged / installer build (read-only — use the popover)
+
+The signed desktop installers (`.dmg`, `.msi`, AppImage, `.deb`) ship a
+**read-only, code-signed Python environment**. Installing extra packages into it
+would break the signature, so **in-app install is intentionally disabled** on
+these builds. Selecting an uninstalled engine there shows a highlighted button
+that opens a small popover with everything you need:
+
+- **The exact command** to run (with a copy-to-clipboard button) if you *do*
+  have a from-source checkout somewhere and want the online engines there.
+- **Switch to Argos (bundled, offline)** — one click. Argos and NLLB are always
+  importable in every build, so this is the guaranteed escape hatch: you can
+  keep dubbing immediately, fully offline, no install required.
+- A link back to this page.
+
+**Recommendation for packaged builds:** just use **Argos** (fast, offline) or
+**NLLB-200** (heavier, higher quality, offline). They need nothing installed and
+never leave your machine. Reach for the online engines only from a from-source
+install where you can add their package.
+
+## Translation quality: Fast, Autofit, Cinematic
+
+The **Quality** control in the Dub tab (and Settings → Translation) picks how the
+translation is produced:
+
+- **Fast** — a direct one-shot translation from the selected engine (Argos, NLLB,
+  Google, …). No LLM, no timing awareness.
+- **Cinematic** — an LLM refines the literal translation (reflect → adapt) for
+  natural, in-context phrasing.
+- **Autofit** — Cinematic **plus** a strict fit-to-time pass: the LLM rewrites
+  each line so its target-language reading time fits **within** the segment's
+  slot (never overruns it). This keeps the video timing intact and avoids the
+  stressed audio time-stretch you get when a translation is too long for its
+  slot. Fit is per-language pronunciation-speed aware.
+
+Cinematic and Autofit **require an LLM** (below). If none is configured, they
+fall back to Fast with a notice.
+
+## LLM Providers (for Cinematic / Autofit)
+
+**Settings → System → LLM Providers** is the one place to set up the LLM. Pick a
+provider, paste its API key, choose a model, **Test** it, and "use for
+translation." Supported: OpenAI, OpenRouter, Groq, Cerebras, Google AI (Gemini),
+Mistral, Cohere, NVIDIA, GitHub Models, Cloudflare, Hugging Face, SambaNova,
+SiliconFlow, **local Ollama / LM Studio** (offline, no key), and a **Custom**
+OpenAI-compatible endpoint.
+
+Keys entered here are stored **encrypted** on your machine and never returned to
+the UI. For a fully offline setup, pick **Ollama** (`ollama pull llama3.1`) or
+**LM Studio** — nothing leaves the machine. Power users can still override any
+provider via environment variables (e.g. `GROQ_API_KEY`, or the legacy
+`TRANSLATE_BASE_URL` / `TRANSLATE_API_KEY` / `TRANSLATE_MODEL`, which map to the
+**Custom** provider).
+
+### Pinning the active provider with `LLM_DEFAULT_PROVIDER`
+
+By default the LLM used for Cinematic/Autofit is the one you mark "use for
+translation" in **Settings → LLM Providers**. To force a specific provider
+regardless of that stored selection — handy for headless/CI/Docker runs or a
+shared machine — set the `LLM_DEFAULT_PROVIDER` environment variable to a
+provider id before launching the backend:
+
+```
+LLM_DEFAULT_PROVIDER=groq        # or openai, openrouter, cerebras, ollama, custom, …
+```
+
+Resolution order for the active provider is: `LLM_DEFAULT_PROVIDER` (env) →
+your saved selection → the first provider that has a key → none. The id must be
+one OmniVoice knows (the ids shown in **Settings → LLM Providers**); an unknown
+value is ignored and resolution falls through to your saved selection. While
+this env var is set it wins over the in-app picker, so if the UI selection
+appears to have "no effect," check whether `LLM_DEFAULT_PROVIDER` is exported.
+
+## LLM Skills (per-feature routing)
+
+**Settings → System → LLM Skills** lists every LLM-powered feature — Cinematic &
+Autofit translation, speech-rate slot fitting, glossary auto-extract, direction
+parsing, and dictation cleanup — and lets you toggle each one or route it to a
+specific provider instead of the global active one. That way sensitive work
+(e.g. dictation cleanup) can stay on a local Ollama/LM Studio model while
+heavier jobs use a remote provider. A disabled skill degrades exactly like
+having no LLM configured: Cinematic/Autofit falls back to Fast, dictation
+cleanup passes the raw transcript through, direction parsing uses the keyword
+heuristic. Everything defaults to enabled + "use active provider", so existing
+setups behave unchanged.
+
+## API keys (online MT engines)
+
+The non-LLM online engines need a key, set as an environment variable before
+launching the backend (or in **Settings → Credentials**):
+
+- **DeepL:** `DEEPL_API_KEY` (optionally `DEEPL_BASE_URL` for a self-hosted /
+  pro endpoint).
+- **Microsoft Translator:** `MICROSOFT_API_KEY` (optionally `MICROSOFT_BASE_URL`).
+
+## Troubleshooting
+
+- **"The 'google' translation engine needs the optional deep_translator Python
+  package…"** — the package isn't installed. On a from-source install, click the
+  Install button (or run the command above) and restart. On a packaged build,
+  switch to Argos/NLLB via the popover.
+- **Install button does nothing / says "disabled in packaged builds"** — you're
+  on a signed installer build (expected). Use Argos/NLLB, or add the package in a
+  from-source checkout.
+- **Installed it but still "needs install"** — restart the backend so Python
+  picks up the newly-installed module.

docs/engines/confucius4-tts.md

@@ -0,0 +1,90 @@
+# Confucius4-TTS (opt-in engine)
+
+> **Status: validated end-to-end (2026-07-02).** The integration (engine
+> registration, dedicated-venv bootstrap, sidecar wire protocol, opt-in gating)
+> is done, the sidecar's pure logic is unit-tested
+> (`tests/test_confucius4_sidecar.py`), and a live synthesis run on Apple
+> Silicon (CPU) produced audible cloned speech — confirming the model API and
+> the true output sample rate of **22 050 Hz**. CUDA is the recommended
+> hardware; CPU works but is slow (~17× realtime — roughly 100 s for 6 s of
+> audio). MPS also runs but is *slower* than CPU (~64× realtime), so the
+> sidecar deliberately never selects it. The engine is gated behind
+> `OMNIVOICE_CONFUCIUS4_TTS_DIR`, so it's completely inert until you opt in —
+> it can't affect the default install on any platform.
+
+[Confucius4-TTS](https://github.com/netease-youdao/Confucius4-TTS) (netease-youdao)
+is an LLM-based multilingual / cross-lingual zero-shot voice-cloning TTS.
+
+- **14 languages**: Chinese, English, Japanese, Korean, German, French, Spanish,
+  Indonesian, Italian, Thai, Portuguese, Russian, Malay, Vietnamese.
+- **Unconstrained cloning** — no reference transcript required.
+- **Cross-lingual voice transfer** — keep one voice across languages.
+- **License:** Apache-2.0. **Hardware:** NVIDIA GPU (CUDA 12.6) recommended;
+  CPU validated on Apple Silicon but ~17× realtime. Output: 22 050 Hz mono.
+
+Like IndexTTS-2 / MOSS-TTS-v1.5 / dots.tts, it runs in its **own subprocess venv**
+so its dependency stack never touches the default OmniVoice interpreter.
+
+## Install
+
+```bash
+git clone https://github.com/netease-youdao/Confucius4-TTS.git
+cd Confucius4-TTS
+uv venv --python 3.10
+uv pip install -r requirements.txt
+```
+
+> Upstream ships **no `pyproject.toml`/`setup.py`**, so there is nothing to
+> `pip install -e` — don't try; it fails. The OmniVoice sidecar puts the clone
+> on `sys.path` itself (the same thing upstream's `example.py` does).
+
+**Model weights — all fetched automatically from HuggingFace on first
+synthesis (~5 GB total, cached in `$HF_HUB_CACHE`):**
+
+- `netease-youdao/Confucius4-TTS` — `t2s_model.safetensors` + `s2a_model.pt`
+  (the tokenizer + `wav2vec2bert_stats.pt` already ship in the clone's
+  `checkpoints/`).
+- `facebook/w2v-bert-2.0` — semantic feature extractor (~2.3 GB).
+- `funasr/campplus` — speaker-style encoder (small).
+- `nvidia/bigvgan_v2_22khz_80band_256x` — vocoder (BigVGAN and CAMPPlus
+  *code* is vendored in the clone's `external/`; no Amphion install needed).
+
+Set your `HF_TOKEN` (Settings → Credentials) if you hit rate limits.
+
+Then point OmniVoice at the clone and restart:
+
+- **macOS/Linux:** `export OMNIVOICE_CONFUCIUS4_TTS_DIR=/path/to/Confucius4-TTS`
+- **Windows (PowerShell):** `[Environment]::SetEnvironmentVariable("OMNIVOICE_CONFUCIUS4_TTS_DIR","C:\path\to\Confucius4-TTS","User")`
+
+Select **Confucius4-TTS** in Settings → Engines. The first synthesize triggers
+the weight downloads above, then generates.
+
+### Optional overrides
+
+- `OMNIVOICE_CONFUCIUS4_CONFIG` — path to `inference_config.yaml` if it isn't at
+  `<clone>/config/inference_config.yaml`.
+
+## Validation record (2026-07-02, Apple Silicon M-series, CPU)
+
+The sidecar (`backend/engines/confucius4/main.py`) uses:
+
+```python
+from confuciustts.cli.inference import ConfuciusTTS
+model = ConfuciusTTS(config_path=..., device="cuda")  # or "cpu"
+audio = model.generate(text=..., lang="en", prompt_wav="ref.wav")  # → tensor
+sr = model.sample_rate  # 22050
+```
+
+- ✅ **Live end-to-end run**: English zero-shot clone from a 9.5 s reference —
+  6.06 s of audible speech (peak 0.85) in 102 s on CPU. `model.sample_rate`
+  returned **22 050**, matching `target_sample_rate` in
+  `config/inference_config.yaml`; `CONFUCIUS_SAMPLE_RATE` /
+  `_DEFAULT_SAMPLE_RATE` are pinned to it (regression-tested).
+- ✅ **Not pip-installable upstream** — discovered live; the bootstrap now skips
+  the editable install unless upstream ships packaging, and both the import
+  probe and the sidecar resolve `confuciustts` via the clone on `sys.path`.
+- ✅ **MPS probed and rejected**: runs, but ~4× slower than CPU (Metal op
+  fallbacks) — the sidecar selects CUDA when available, else CPU, never MPS.
+- ✅ **Sidecar logic unit-tested** (`tests/test_confucius4_sidecar.py`):
+  language normalization, tensor→PCM (mono/stereo/clip), config-path
+  resolution, clone sys.path injection, wire framing, synthesize dispatch.

docs/engines/disk-usage.md

@@ -1,10 +1,11 @@
 # Engine venvs & disk usage
 
 Most engines run in-process in OmniVoice's main environment. A few
-(**IndexTTS2**, and any engine whose dependencies conflict with the parent's
-`torch`/`transformers` pins) run in a **dedicated sidecar venv** so their pins
-can't break the rest of the app. Those sidecars are where disk adds up — this
-page explains why, and how the on-disk cost is kept down.
+(**IndexTTS2**, **MOSS-TTS-v1.5**, **dots.tts**, and any engine whose
+dependencies conflict with the parent's `torch`/`transformers` pins) run in a
+**dedicated sidecar venv** so their pins can't break the rest of the app. Those
+sidecars are where disk adds up — this page explains why, and how the on-disk
+cost is kept down.
 
 ## Why a sidecar needs its own venv
 
@@ -48,6 +49,13 @@ the parent whenever the engine allows it.** When it doesn't (IndexTTS2's
 `transformers<5` forces an older torch line), the second copy is the
 unavoidable price of isolation — not a bug.
 
+The opt-in #498 engines illustrate both sides: **dots.tts** pins
+`torch==2.8.0` — the **same** build the parent constrains to — so it shares
+almost all of torch with the main venv and only its `transformers==4.57` +
+model deps are new. **MOSS-TTS-v1.5** pins `torch==2.9.1+cu128`, a **different**
+build, so it pays a full extra multi-GB torch copy on CUDA hosts (the price of
+running an 8B model whose stack pins `transformers==5.0`).
+
 > On Linux, the `nvidia-*` CUDA packages are separate wheels, so even across
 > *different* torch versions any `nvidia-*` whose pinned version happens to
 > match is still shared. On Windows the CUDA DLLs live inside the one torch

docs/engines/dots-tts.md

@@ -0,0 +1,117 @@
+# OmniVoice Studio — dots.tts Engine
+
+dots.tts (rednote-hilab) is a **2B** fully-continuous autoregressive TTS,
+widely cited as one of the strongest open zero-shot voice-cloning models. It
+covers **24 languages**, emits **48 kHz** audio, and is released under
+**Apache-2.0** (code + checkpoints).
+
+It runs in its own subprocess **and its own Python venv** with
+`transformers==4.57.0`, isolated from the OmniVoice parent process which
+pins `transformers>=5.3` — the same isolation primitive used by
+[IndexTTS-2](indextts.md) and [MOSS-TTS-v1.5](moss-tts-v15.md).
+
+> **Opt-in, and never a default.** dots.tts is selected explicitly in
+> **Settings → Engines** (or `OMNIVOICE_TTS_BACKEND=dots-tts`). It is not
+> part of the default install.
+
+## Platform support
+
+- **Linux / macOS only.** dots.tts's upstream package declares Linux and
+  macOS classifiers and has **no Windows install path**. On Windows the
+  engine reports itself unavailable in **Settings → Engines** with a clear
+  reason — run OmniVoice under WSL2 or use a Linux/macOS host.
+- **No MPS.** Upstream device selection is CUDA-or-CPU with no Metal branch,
+  so on Apple Silicon the official package runs on **CPU** (slow but
+  correct). A faster Apple-Silicon path exists only via community MLX ports,
+  which OmniVoice does not auto-wire.
+- **VRAM:** ~9 GB checkpoint; a 12–16 GB CUDA GPU is the realistic target.
+
+## Install
+
+dots.tts is **not** bundled (large checkpoint + conflicting `transformers`).
+
+1. Clone the dots.tts repo on disk:
+
+   ```bash
+   git clone https://github.com/rednote-hilab/dots.tts.git
+   ```
+
+2. Install the editable package into a fresh venv with the upstream
+   constraints. Use `uv pip install -e . -c constraints/recommended.txt` —
+   **never** `uv sync --all-extras`, which would overwrite OmniVoice's lock
+   file with `transformers==4.57` and break the parent process:
+
+   ```bash
+   cd dots.tts
+   uv venv .venv
+   uv pip install -e . -c constraints/recommended.txt
+   ```
+
+3. The ~9 GB checkpoint downloads from HuggingFace on first synthesize. The
+   parent forwards `HF_HOME` / `HF_HUB_CACHE` to the sidecar so the cache is
+   shared with the rest of OmniVoice's downloads.
+
+4. Set `OMNIVOICE_DOTS_TTS_DIR` to the repo root (the directory that
+   contains `pyproject.toml` and `constraints/`):
+
+   ```bash
+   # macOS / Linux
+   echo 'export OMNIVOICE_DOTS_TTS_DIR=$HOME/code/dots.tts' >> ~/.zshrc
+   source ~/.zshrc
+   ```
+
+5. Restart OmniVoice. dots.tts appears in **Settings → Engines** with
+   `available: true` and `isolation_mode: subprocess`.
+
+## Venv resolution order
+
+OmniVoice probes for a usable dots.tts Python interpreter in this priority
+order (see `backend/engines/dots_tts/bootstrap.py`):
+
+1. **`${OMNIVOICE_DOTS_TTS_DIR}/.venv/`** — your existing clone's venv.
+2. **`backend/engines/dots_tts/.venv/`** — OmniVoice's own venv, created on
+   demand by step 3.
+3. **Lazy bootstrap** — `uv venv` then `uv pip install -e <clone> -c
+   <clone>/constraints/recommended.txt`. Requires `OMNIVOICE_DOTS_TTS_DIR`.
+
+## Voice cloning
+
+For best fidelity ("continuation cloning"), pass **both** a reference clip
+(`ref_audio`) and its exact transcript (`ref_text`). A reference clip alone
+does x-vector-only cloning. Keep the reference ~10 s. Upstream requires the
+reference audio whenever a transcript is given, so OmniVoice drops a stray
+`ref_text` that arrives without `ref_audio`.
+
+## Optional env knobs
+
+| Variable | Default | Purpose |
+|----------|---------|---------|
+| `OMNIVOICE_DOTS_TTS_DIR` | — | Path to the dots.tts clone (required). |
+| `OMNIVOICE_DOTS_TTS_MODEL` | `rednote-hilab/dots.tts-soar` | Checkpoint override (`-base`, `-soar`, `-mf`). |
+| `OMNIVOICE_DOTS_TTS_PRECISION` | `bfloat16` (CUDA) / `float32` (CPU) | Inference precision. |
+| `OMNIVOICE_DOTS_TTS_OPTIMIZE` | `0` | `1` enables `torch.compile` (slower first call, faster after). |
+
+> Using the `dots.tts-mf` (MeanFlow-distilled) checkpoint? It's tuned for
+> **4** flow-matching steps — pass `num_step=4`.
+
+## Common errors
+
+### `dots.tts is not supported on Windows ...`
+
+Upstream is Linux/macOS only. Use WSL2 or a Linux/macOS host.
+
+### `dots.tts venv not found. Set OMNIVOICE_DOTS_TTS_DIR ...`
+
+You haven't pointed OmniVoice at a dots.tts clone yet. Follow **Install**.
+
+## License
+
+Apache-2.0 (code and checkpoints). See the upstream
+[README](https://github.com/rednote-hilab/dots.tts/blob/main/README.md).
+
+---
+
+dots.tts runs in a dedicated sidecar venv (it pins `transformers==4.57`,
+which conflicts with the parent's `transformers>=5.3`). For why that adds
+disk and how uv keeps the cost down, see
+[Engine venvs & disk usage](disk-usage.md).

docs/engines/moss-tts-v15.md

@@ -0,0 +1,131 @@
+# OmniVoice Studio — MOSS-TTS-v1.5 Engine
+
+MOSS-TTS-v1.5 (OpenMOSS) is an **8B** flagship zero-shot TTS — a Qwen3-8B
+language backbone plus a 1.6B audio codec. It covers **31 languages**, does
+zero-shot voice cloning, token-level duration control and inline
+`[pause Ns]` markers. Released under **Apache-2.0** (code + weights).
+
+It runs in its own subprocess **and its own Python venv** with
+`transformers==5.0.0`, isolated from the OmniVoice parent process which
+pins `transformers>=5.3`. This is the same isolation primitive used by
+[IndexTTS-2](indextts.md): the two `transformers` pins cannot share one
+interpreter, so MOSS runs behind
+`backend/services/subprocess_backend.py::SubprocessBackend`.
+
+> **Opt-in, and never a default.** MOSS-TTS-v1.5 is selected explicitly in
+> **Settings → Engines** (or `OMNIVOICE_TTS_BACKEND=moss-tts-v15`). It is
+> not part of the default install and does not change OmniVoice's
+> out-of-the-box behaviour on any platform.
+
+## Hardware
+
+- **VRAM/RAM:** an 8B model. The upstream llama.cpp pipeline fits the 8B on
+  8 GB GPUs when quantized; the bf16 Transformers path used here is ~16 GB
+  of weights, so a 16 GB+ GPU is the realistic CUDA target. It also runs on
+  **CPU** (fp32) — correct but slow.
+- **Device:** CUDA when present, else CPU. **There is no MPS path** —
+  upstream documents only CUDA/CPU and the custom modelling code is
+  untested on Apple Silicon, so OmniVoice never routes MOSS to MPS. On a
+  Mac it runs on CPU.
+
+## Install
+
+MOSS-TTS-v1.5 is **not** bundled (the model is large and the package pins a
+conflicting `transformers`). OmniVoice ships a sidecar runner that loads it
+into an isolated venv on demand.
+
+1. Clone the MOSS-TTS repo on disk:
+
+   ```bash
+   git clone https://github.com/OpenMOSS/MOSS-TTS.git
+   ```
+
+2. Install the editable package into a fresh venv. Use
+   `uv pip install -e ".[torch-runtime]"` — **never** `uv sync --all-extras`,
+   which would overwrite OmniVoice's lock file with `transformers==5.0` and
+   break the parent process. The `torch-runtime` extra is CUDA (`+cu128`):
+
+   ```bash
+   cd MOSS-TTS
+   uv venv .venv
+   uv pip install -e ".[torch-runtime]"
+   ```
+
+   On a **non-CUDA / CPU host** (e.g. Apple Silicon), install plain
+   `torch`/`torchaudio`/`transformers==5.0.0` into the venv instead of the
+   `+cu128` extra (the auto-bootstrap below only targets CUDA hosts).
+
+3. The ~16 GB weights download from HuggingFace on first synthesize. The
+   parent forwards `HF_HOME` / `HF_HUB_CACHE` to the sidecar so the cache is
+   shared with the rest of OmniVoice's downloads.
+
+4. Set `OMNIVOICE_MOSS_TTS_V15_DIR` to the repo root (the directory that
+   contains `pyproject.toml`):
+
+   ```bash
+   # macOS / Linux
+   echo 'export OMNIVOICE_MOSS_TTS_V15_DIR=$HOME/code/MOSS-TTS' >> ~/.zshrc
+   source ~/.zshrc
+   ```
+
+   ```powershell
+   # Windows PowerShell
+   [Environment]::SetEnvironmentVariable("OMNIVOICE_MOSS_TTS_V15_DIR","$env:USERPROFILE\code\MOSS-TTS","User")
+   ```
+
+5. Restart OmniVoice. MOSS-TTS-v1.5 appears in **Settings → Engines** with
+   `available: true` and `isolation_mode: subprocess`.
+
+## Venv resolution order
+
+OmniVoice probes for a usable MOSS Python interpreter in this priority
+order (see `backend/engines/moss_tts_v15/bootstrap.py`):
+
+1. **`${OMNIVOICE_MOSS_TTS_V15_DIR}/.venv/`** — your existing clone's venv.
+   Highest priority, so a power user who already set MOSS up gets zero
+   re-install.
+2. **`backend/engines/moss_tts_v15/.venv/`** — OmniVoice's own venv,
+   created on demand by step 3.
+3. **Lazy bootstrap** — if neither venv exists, OmniVoice runs `uv venv`
+   then `uv pip install --python <python> -e "${DIR}[torch-runtime]"`.
+   Requires `OMNIVOICE_MOSS_TTS_V15_DIR`; raises a clear error otherwise.
+   On a non-CUDA host the `+cu128` extra cannot resolve — set the venv up
+   manually per step 2.
+
+## Voice cloning
+
+Pass a reference clip as `ref_audio`. MOSS's zero-shot clone mode needs only
+the audio (no transcript). Without a reference, MOSS synthesizes in its own
+default voice. `duration` (seconds) maps to MOSS's `tokens` argument at
+~12.5 tokens/second.
+
+## Optional env knobs
+
+| Variable | Default | Purpose |
+|----------|---------|---------|
+| `OMNIVOICE_MOSS_TTS_V15_DIR` | — | Path to the MOSS-TTS clone (required). |
+| `OMNIVOICE_MOSS_TTS_V15_MODEL` | `OpenMOSS-Team/MOSS-TTS-v1.5` | HF repo id override (mirror / air-gapped). |
+| `OMNIVOICE_MOSS_TTS_V15_ATTN` | `sdpa` | Attention impl; set `flash_attention_2` on Ampere+ CUDA with `flash-attn` installed. |
+
+## Common errors
+
+### `MOSS-TTS-v1.5 venv not found. Set OMNIVOICE_MOSS_TTS_V15_DIR ...`
+
+You haven't pointed OmniVoice at a MOSS-TTS clone yet. Follow **Install**.
+
+### `uv pip install -e failed ... '[torch-runtime]' extra (cu128) cannot resolve`
+
+You're on a non-CUDA host. The upstream `torch-runtime` extra is CUDA-only;
+set up the venv manually with plain `torch`/`transformers==5.0.0` (step 2).
+
+## License
+
+Apache-2.0 (code and weights) — no acceptance gate. See the upstream
+[README](https://github.com/OpenMOSS/MOSS-TTS/blob/main/README.md).
+
+---
+
+MOSS-TTS-v1.5 runs in a dedicated sidecar venv (it pins `transformers==5.0`,
+which conflicts with the parent's `transformers>=5.3`). For why that adds
+disk and how uv keeps the cost down, see
+[Engine venvs & disk usage](disk-usage.md).

docs/features.yaml

@@ -46,6 +46,15 @@ tts_engines:
     doc: docs/engines/indextts.md
   - id: omnivoice-gguf
   - id: supertonic3
+  - id: moss-tts-v15
+    readme: "**MOSS-TTS-v1.5**"
+    doc: docs/engines/moss-tts-v15.md
+  - id: dots-tts
+    readme: "**dots.tts**"
+    doc: docs/engines/dots-tts.md
+  - id: confucius4-tts
+    readme: "**Confucius4-TTS**"
+    doc: docs/engines/confucius4-tts.md
 
 # Same contract against backend/services/asr_backend.py _REGISTRY.
 asr_engines:
@@ -63,6 +72,8 @@ asr_engines:
     readme: Moonshine
   - id: funasr
     readme: FunASR
+  - id: sherpa-onnx-asr
+    readme: "**sherpa-onnx** (live dictation)"
 
 # Doc files that must exist (the install path users are sent to).
 docs:

docs/install/linux.md

@@ -11,6 +11,8 @@ working OmniVoice Studio install on a Debian / Ubuntu / Fedora / Arch host.
   `sudo dnf install python3.11` on Fedora, or already installed on Arch.
 - **Bun** — `curl -fsSL https://bun.sh/install | bash`.
 - **FFmpeg** — `sudo apt install ffmpeg` (Debian/Ubuntu), `sudo dnf install ffmpeg-free` (Fedora), or `sudo pacman -S ffmpeg` (Arch).
+- **Rust / Cargo** (required for building from source only) — `curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh` or via your package manager (e.g., `sudo apt install rustc cargo`).
+  If you use rustup, reopen the shell or source `"$HOME/.cargo/env"` before running `bun run desktop-prod`.
 - **GTK/WebKit deps** for the Tauri shell:
 
   ```bash

docs/install/macos.md

@@ -1,20 +1,30 @@
 # OmniVoice Studio — Install on macOS
 
 This page is self-contained: follow it top to bottom and you'll end up with a
-working OmniVoice Studio install on macOS (Apple Silicon or Intel).
+working OmniVoice Studio install on macOS (Apple Silicon).
 
-> **Intel Macs:** the pre-built `.app`/DMG currently ships **Apple Silicon
-> only** — on Intel, install **from source** (works fully; ASR falls back to
-> CTranslate2). A pre-built Intel bundle is tracked in
-> [#279](https://github.com/debpalash/OmniVoice-Studio/issues/279).
+> [!IMPORTANT]
+> **Intel Macs are not supported.** The app UI installs and launches, but the
+> local Python backend **cannot run**: PyTorch stopped shipping Intel-Mac
+> (macOS x86_64) wheels after 2.2.x, and OmniVoice's dependencies require a
+> newer torch — so the first-run dependency install can never succeed, from
+> the DMG *or* from source
+> ([#889](https://github.com/debpalash/OmniVoice-Studio/issues/889)). The app
+> detects this at first launch and tells you directly instead of failing with
+> a raw installer error. Your options on an Intel Mac: point the UI at a
+> remote backend running on another machine (**Settings → Sharing → Remote
+> backend**), or run OmniVoice on an Apple Silicon Mac, Windows, or Linux.
 
 ## Prerequisites
 
-- **macOS 12 (Monterey) or newer** — Apple Silicon or Intel.
+- **macOS 12 (Monterey) or newer** — Apple Silicon (Intel: UI only, see the
+  note above).
 - **Python 3.11+** — `brew install python@3.11` (or use `pyenv` / the system Python if you already have ≥3.11).
 - **Bun** — `curl -fsSL https://bun.sh/install | bash`.
 - **Xcode Command Line Tools** — `xcode-select --install`.
 - **FFmpeg** (used by the dubbing + capture pipelines) — `brew install ffmpeg`.
+- **Rust / Cargo** (required for building from source only) — `curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh` or `brew install rust`.
+  If you use rustup, reopen the terminal or source `"$HOME/.cargo/env"` before running `bun run desktop-prod`.
 
 Optional but recommended:
 
@@ -45,13 +55,15 @@ Pick the DMG that matches your Mac (check **Apple menu → About This Mac → Ch
 | Mac | DMG to download |
 |-----|-----------------|
 | Apple Silicon (M1/M2/M3/M4…) | `OmniVoice.Studio_<version>_aarch64.dmg` |
-| Intel | `OmniVoice.Studio_<version>_x64.dmg` |
+| Intel | `OmniVoice.Studio_<version>_x64.dmg` — **UI only**: the local backend cannot run on Intel ([#889](https://github.com/debpalash/OmniVoice-Studio/issues/889)) |
 
 The architectures are **not** interchangeable: an Intel Mac cannot run the
 `aarch64` build (Rosetta 2 only translates the other direction — it lets Apple
-Silicon run Intel apps, never the reverse). If a release predates the Intel
-build target and has no `x64` DMG, use the
-[install-from-source path](#install-from-source) above instead.
+Silicon run Intel apps, never the reverse). And note the Intel caveat above:
+the `x64` DMG installs and launches, but is only useful together with a
+remote backend — the local Python backend cannot install on Intel because
+PyTorch no longer ships Intel-Mac wheels. Installing from source does not
+help; the dependency resolution fails the same way.
 
 If the first launch is blocked by macOS Gatekeeper ("OmniVoice Studio cannot be
 opened because the developer cannot be verified"), see the next section — it
@@ -121,8 +133,11 @@ without the quarantine step.
 - **Apple Silicon (M-series):** OmniVoice automatically picks the `mlx-whisper`
   and `mlx-audio` backends where available — these use the Apple Neural Engine
   and Metal Performance Shaders for ~2× the throughput of the CPU path.
-- **Intel macs:** falls back to `faster-whisper` (CTranslate2) on CPU. Still
-  fast; just no ANE acceleration.
+- **Intel Macs:** the local backend is **unsupported** — PyTorch no longer
+  ships Intel-Mac wheels, so the Python environment can never install
+  ([#889](https://github.com/debpalash/OmniVoice-Studio/issues/889)). The UI
+  works only when pointed at a remote backend (**Settings → Sharing → Remote
+  backend**).
 
 The picker in **Settings → Engines** shows which backend is active.
 

docs/install/troubleshooting.md

@@ -61,6 +61,29 @@ fresh install heals itself.
 **Linked issues:** [#58](https://github.com/debpalash/OmniVoice-Studio/issues/58),
 [#248](https://github.com/debpalash/OmniVoice-Studio/issues/248)
 
+### 1a. Model load fails: `[Errno 2] No such file or directory: '…/transformers/…/modeling_*.py'`
+
+**Symptom:** the System Check / model load fails with e.g.
+`[Errno 2] No such file or directory:
+'…/site-packages/transformers/models/qwen3/modeling_qwen3.py'`.
+
+**Cause:** same class as §1 — a **corrupted/incomplete `transformers` install**.
+A model load lazily resolves a module file that's **missing from `site-packages`**
+(an interrupted `uv sync`, antivirus quarantine, or a partial update). The
+package's metadata is intact, so a plain install no-ops and never restores the
+file. Restarting does **not** help (the file is still gone).
+
+**Fix:** force-reinstall transformers in the backend venv, then restart:
+
+```
+uv pip install --reinstall transformers
+```
+
+Or, as a quick workaround, switch ASR to **faster-whisper** in
+**Settings → Models**. If it recurs, add the backend **`.venv`** to your
+antivirus exclusions (see §1). Newer builds classify this error and show the
+reinstall hint directly instead of a bare path + "try restarting".
+
 ## 2. HF 401 / pyannote license not accepted
 
 **Symptom:** dubbing fails with `HfHubHTTPError: 401 Client Error: Unauthorized
@@ -156,9 +179,11 @@ falling back to faster-whisper`.
 
 **Cause:** `mlx-whisper` and `mlx-audio` only build for arm64 (Apple Silicon).
 
-**Fix:** none needed — `faster-whisper` (CTranslate2) is the supported Intel
-path and is still fast. If you want the latest CT2 wheels, run `uv sync`
-from a fresh source checkout.
+**Fix:** none needed on Apple Silicon setups that log this transiently. Note
+that Intel Macs can no longer run the local backend at all — PyTorch dropped
+Intel-Mac wheels, so this entry only applies to historical installs (see
+[macos.md](macos.md) and
+[#889](https://github.com/debpalash/OmniVoice-Studio/issues/889)).
 
 ## 10. Windows: `Could not locate cudnn_ops_infer64_8.dll` during transcription
 
@@ -168,14 +193,30 @@ WhisperX or faster-whisper selected.
 
 **Cause:** WhisperX and faster-whisper run on **CTranslate2**, which needs
 **cuDNN 8**, but PyTorch 2.8 ships cuDNN 9. OmniVoice side-loads a cuDNN-8 copy
-from `.venv\Lib\site-packages\cudnn8_compat\`; if that folder is missing
-(some upgrade paths don't install it), CTranslate2 can't find the DLL.
+from `.venv\Lib\site-packages\cudnn8_compat\` — but the step that installs that
+folder only ever lived in the dev-loop setup script, which isn't bundled into
+the packaged app. **Packaged installs never had these libraries at all**, so
+reinstalling never fixed it ([#827](https://github.com/debpalash/OmniVoice-Studio/issues/827)).
 
-**Fix:** switch the ASR backend to **PyTorch Whisper** in **Settings → Models**.
-It runs on PyTorch's own stack (cuDNN 9, bundled with torch) and needs no
-cuDNN-8 DLL — it loads its Whisper pipeline on demand (no extra env var). To
-keep using faster-whisper/WhisperX instead, reinstall to restore the bundled
-`cudnn8_compat` libraries.
+**Fix:** update to the latest build and relaunch — the app's bootstrap now
+detects a CUDA machine and installs the cuDNN-8 libraries into the backend venv
+automatically at launch ([#869](https://github.com/debpalash/OmniVoice-Studio/pull/869)).
+(The check is skipped — and its negative result cached — on CPU/AMD/Apple
+machines, so non-NVIDIA launches stay instant.)
+
+If the automatic install can't run (offline / restricted network), install
+manually into the backend venv, then restart:
+
+```
+uv pip install --no-deps --python .venv\Scripts\python.exe --target .venv\Lib\site-packages\cudnn8_compat nvidia-cudnn-cu12==8.9.7.29
+```
+
+(On Linux the target is `.venv/lib/pythonX.Y/site-packages/cudnn8_compat`.)
+
+Or sidestep cuDNN 8 entirely: switch the ASR backend to **PyTorch Whisper** in
+**Settings → Models**. It runs on PyTorch's own stack (cuDNN 9, bundled with
+torch) and needs no cuDNN-8 DLL — it loads its Whisper pipeline on demand (no
+extra env var).
 
 ## 11. IndexTTS / CosyVoice / ChatterboxTTS clash
 
@@ -192,6 +233,209 @@ for the dedicated CosyVoice path.
 
 **Linked issue:** [#55](https://github.com/debpalash/OmniVoice-Studio/issues/55)
 
+## 12. CUDA PyTorch wheel download fails on first run
+
+**Symptom:** first-run setup stops at **Installing dependencies** with a failure
+that mentions `torch` and a `download.pytorch.org` (or `download-r2.pytorch.org`)
+URL — e.g. `Failed to download torch==2.8.0+cu128 …win_amd64.whl`. The app then
+won't launch.
+
+**Cause:** on Windows/Linux NVIDIA machines, OmniVoice installs the CUDA PyTorch
+build (`torch` + `torchaudio`) from PyTorch's own index. That CUDA wheel is
+large (~2.5 GB), so a flaky or restricted network drops it partway. This is a
+download/network problem, **not** a bug in OmniVoice — but the CUDA wheels come
+from a *named, explicit* index that a PyPI mirror (`UV_DEFAULT_INDEX`) cannot
+redirect, so the generic mirror trick doesn't help here.
+
+**Fix, in order:**
+
+1. **Clean & Retry.** Large downloads frequently succeed on a second attempt —
+   OmniVoice already retries each request 5× with long timeouts, and a fresh
+   attempt restarts cleanly.
+2. **Use a VPN** if your network throttles or blocks the PyTorch CDN.
+3. **Provide the wheels manually (offline path).** Download the two wheels that
+   match your machine from a source you *can* reach (the official
+   [pytorch.org](https://pytorch.org/get-started/locally/) wheel index or a
+   regional mirror), then drop them in the wheel folder and **Clean & Retry** —
+   OmniVoice will install from your local copies instead of the network:
+   - Folder: **`<env dir>/wheels`** (the exact path is printed in the error
+     message and in the setup log; `<env dir>` is your chosen install/storage
+     location).
+   - Files: the `torch` **and** `torchaudio` wheels for your exact Python/OS/CUDA
+     — e.g. `torch-2.8.0+cu128-cp311-cp311-win_amd64.whl` and the matching
+     `torchaudio-2.8.0+cu128-cp311-cp311-win_amd64.whl`. They must match the
+     pinned versions (shown in the failing URL).
+   - On retry, OmniVoice re-resolves the install using those local wheels; the
+     rest of the (small) dependencies still come from PyPI/your mirror.
+
+If you don't have an NVIDIA GPU, you don't need the CUDA build at all — a CPU /
+Apple-Silicon install skips this index entirely.
+
+**Linked issue:** [#569](https://github.com/debpalash/OmniVoice-Studio/issues/569)
+
+## 13. Stuck on the download page / incomplete model cache ("only `refs/`")
+
+**Symptom:** the setup screen never finishes the model download and you can't
+reach the main app. Looking in the HF cache, a model folder
+(`models--k2-fsa--OmniVoice`, `models--Systran--faster-whisper-large-v3`) has
+`refs/` and maybe `config.json` but **no weight files** (`blobs/` empty or tiny).
+
+**Cause:** the download started but the large weight shards never finished —
+almost always the connection **dropping, throttling, or being blocked** mid-pull
+(corporate/school proxy, VPN, antivirus quarantining the multi-GB file, or a
+region where `huggingface.co` is slow/blocked). The app retries and verifies
+weights, but a connection that *trickles* rather than dies can stall for a long
+time.
+
+**Fix — force a clean re-download:**
+
+1. **Fully quit OmniVoice.** Check Task Manager (Windows) / Activity Monitor
+   (macOS) and end any leftover `omnivoice` / `python` process — a half-running
+   one keeps the cache locked.
+2. **Delete the incomplete model folder(s) entirely** from the HF cache (the
+   whole `models--…` folder, not just `refs/`). Leave other models alone:
+   - `models--k2-fsa--OmniVoice`
+   - `models--Systran--faster-whisper-large-v3`
+3. **Relaunch** — the download page re-pulls from scratch.
+
+**If it stalls again at the same spot**, the download is being blocked — try, in
+order:
+
+- **Antivirus/firewall** — temporarily disable it for the download (large model
+  files are a common false-positive quarantine), then re-enable.
+- **Connection** — use a stable, direct connection; pause any VPN; avoid
+  corporate/school networks.
+- **Region mirror** — if `huggingface.co` is slow/blocked where you are, set a
+  mirror **before** launching and relaunch:
+  - macOS/Linux: `export HF_ENDPOINT=https://hf-mirror.com`
+  - Windows (PowerShell): `[Environment]::SetEnvironmentVariable("HF_ENDPOINT","https://hf-mirror.com","User")`
+
+**Manual fallback** (if downloads keep failing), pull the weights yourself into
+the same cache, then relaunch:
+
+```bash
+pip install -U "huggingface_hub[cli]"
+huggingface-cli download k2-fsa/OmniVoice
+huggingface-cli download Systran/faster-whisper-large-v3
+```
+
+(If OmniVoice uses a custom models directory, set `HF_HOME` to it first so the
+files land where the app looks.)
+
+> Newer builds detect an incomplete cache and re-offer the download instead of
+> stranding you on this page — update once the fix is in your channel.
+
+**Linked issue:** [#622](https://github.com/debpalash/OmniVoice-Studio/issues/622)
+
+## 14. "Can't reach the local backend" *during* generation / transcription / dubbing
+
+**Symptom:** the app worked at startup (you reached the main menu and the model
+loaded), but the moment you **generate audio, dub a video, transcribe, or
+dictate**, it spins for a long time and then shows **"Can't reach the local
+backend."** The backend log ends right after a line like `whisperx transcribing
+…tmpXXXX.wav` (or a generate) with nothing after it — i.e. the backend is
+**alive**, the GPU *job* is what stalled.
+
+**Cause:** this is **not** a connection, download, or "network mirror" problem —
+the backend started fine. A GPU job (a **generate** on the TTS model, or an ASR
+transcribe with WhisperX/faster-whisper **large-v3**) is too heavy for the
+available compute and runs for minutes; because it wedges its GPU-pool worker,
+every *other* request — including the next generate and the health check — is
+starved, which the UI surfaces as an unreachable backend. The usual trigger is
+**VRAM starvation on NVIDIA**: models contend for memory on an 8 GB-class GPU
+(the log shows e.g. `GPU pool sized … 7.0 GB free`). CPU-only machines hit the
+same wall on long clips. This is the same root cause whether the last thing you
+did was `generate:start (audio)`, a dub, or a dictation.
+
+> There is **no "Network → Restricted/Global mirror" toggle** in Settings — that
+> control (the footer/Sharing **Network** button) is for **LAN sharing**, not
+> downloads. If someone pointed you there for this error, it was the wrong knob.
+
+**Fix — reduce ASR load (any one of these):**
+
+1. **Pick a smaller ASR model / engine** in **Settings → Models** — e.g.
+   faster-whisper **medium** or **small**, instead of large-v3. Biggest win on
+   low-VRAM GPUs.
+2. **Free VRAM**: **Flush the TTS model** before dubbing so ASR isn't competing
+   for memory, or
+3. **Run ASR on CPU** (slower but reliable) if your GPU is small.
+4. **Test with a 10-second clip** first — if that returns quickly, it confirms a
+   compute/VRAM limit rather than a true hang.
+
+Newer builds **bound** every GPU job — whole-file transcription, **chunked dub
+transcription**, **and** TTS generation: instead of hanging forever and starving
+the backend, a wedged job now fails after a timeout with this exact guidance,
+and the worker pool is reset so capacity is restored automatically (no app
+restart needed). Tune the bounds with `OMNIVOICE_ASR_TRANSCRIBE_TIMEOUT_S`
+(whole-file transcription) and `OMNIVOICE_GENERATE_TIMEOUT_S` (generation) —
+both in seconds, default 300 — and `OMNIVOICE_TRANSCRIBE_CHUNK_TIMEOUT_S`
+(per-chunk dub transcription, default 120). **Raise** them for very long single
+files/generations, **lower** them to fail faster on a small machine.
+
+**If transcribe timeouts keep repeating back-to-back**, pool resets aren't
+recovering the underlying hang — the wedged thread keeps its VRAM until the app
+exits. The error message will then recommend switching the ASR engine to
+**Faster-Whisper (crash-isolated subprocess)** (`faster-whisper-isolated`) in
+**Settings → Engines**: it runs transcription in a separate process that can be
+force-killed to reclaim a hung transcribe *and* its VRAM, at a small per-call
+overhead. It reuses your existing faster-whisper install (nothing extra to
+download). OmniVoice never switches engines automatically — this stays your
+call.
+
+## 15. Stuck at "preparing" forever after a crash / BSOD (Windows)
+
+**Symptom:** after an unclean shutdown (Windows BSOD, forced power-off), every
+launch sits on the "preparing" splash indefinitely — even though the backend is
+actually healthy (its log shows models loaded, and
+`http://127.0.0.1:3900/health` answers `{"status":"ok"}` in a browser). The
+WebView log contains:
+
+```
+IPC custom protocol failed, Tauri will now use the postMessage interface instead
+TypeError: Failed to fetch
+```
+
+**Cause:** the crash corrupted the WebView2 profile cache at
+`%LOCALAPPDATA%\com.debpalash.omnivoice-studio\EBWebView`. Both the IPC custom
+protocol *and* its postMessage fallback break, so the splash never hears the
+"ready" signal from the app shell (issue #879).
+
+**Fix:** current builds handle this automatically — if the splash gets no IPC
+signal within ~10 s it checks the backend over plain HTTP and proceeds on its
+own; if the backend isn't up either, after ~45 s a recovery panel appears with
+**Repair and restart** (Windows), which clears the WebView cache and relaunches.
+Your voices, projects, and settings are not touched — only browser display data
+is cleared.
+
+On older builds (≤ 0.3.8), or if the automatic repair fails, do it manually:
+quit OmniVoice Studio, delete the folder below, then start the app again.
+
+<!-- validate: skip -->
+```powershell
+Remove-Item -Recurse -Force "$env:LOCALAPPDATA\com.debpalash.omnivoice-studio\EBWebView"
+```
+
+## Dub: "translation engine needs the optional … package"
+
+**Symptom:** in the Dub tab, translating fails with e.g. *"The 'google'
+translation engine needs the optional `deep_translator` Python package, which
+isn't installed in this backend."*
+
+**Cause:** the online translation engines (Google / DeepL / Microsoft / MyMemory
+via `deep_translator`, and the LLM provider via `openai`) are **optional** and
+not bundled. Only **Argos** and **NLLB** work out of the box.
+
+**Fix:**
+- **From-source / Docker install:** click the highlighted **Install** button next
+  to the *Engine* label in the Dub tab (or run `uv pip install deep_translator`
+  in the backend venv) and restart the backend.
+- **Packaged installer build:** in-app install is disabled (read-only signed
+  environment). Click the highlighted button to open the popover and **Switch to
+  Argos (bundled, offline)** — or copy the command to run it in a from-source
+  checkout.
+
+Full guide: [dubbing/translation-engines.md](../dubbing/translation-engines.md#installing-optional-translation-engines-from-source-vs-packaged-build).
+
 ## First-run setup fails on a restricted network (GitHub/PyPI blocked)
 
 On networks that block or can't resolve **GitHub**, the first-run bootstrap may