Merge feat/frameless-dictation-widget: v0.2.7 — frameless dictation widget, GHCR Docker

# Conflicts:
#	README.md

.github/workflows/docker.yml

@@ -0,0 +1,68 @@
+# Publish Docker images to GitHub Container Registry (GHCR).
+#
+# Triggers:
+#   - push of a tag matching `v*` (e.g. `v0.2.7`) → pushed as :0.2.7 + :latest
+#   - workflow_dispatch → pushed as :sha-<short> (for testing)
+#
+# Images land at: ghcr.io/debpalash/omnivoice-studio
+
+name: Docker (GHCR)
+
+on:
+  push:
+    tags: ['v*']
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  packages: write
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v4
+
+      # QEMU enables cross-platform builds (arm64 on x64 runner).
+      # Skipped for now — only building linux/amd64.
+      # - uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GHCR
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      # Extracts semver tags from the git ref:
+      #   v0.2.7 → 0.2.7, latest
+      #   manual dispatch → sha-abc1234
+      - name: Extract metadata (tags, labels)
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=sha,prefix=sha-,format=short
+            type=raw,value=latest,enable={{is_default_branch}}
+
+      - name: Build and push
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: deploy/Dockerfile
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.gitignore

@@ -81,3 +81,6 @@ frontend/src-tauri/binaries/ffmpeg
 # cuDNN 8 compat libs (auto-installed by scripts/setup_cudnn.py)
 cudnn8_compat/
 test-results/
+
+# Research repos (local only)
+research/

README.md

@@ -115,17 +115,51 @@ That's it. Open [localhost:3901](http://localhost:3901) and start cloning voices
 
 ### Docker
 
+Pull the pre-built image from **GitHub Container Registry** — no build step needed:
+
+```bash
+docker pull ghcr.io/debpalash/omnivoice-studio:latest
+```
+
+Run it:
+
 ```bash
 # CPU mode
-docker compose up --build -d
+docker run -d --name omnivoice \
+  -p 127.0.0.1:3900:3900 \
+  -v omnivoice-data:/app/omnivoice_data \
+  ghcr.io/debpalash/omnivoice-studio:latest
 
-# Or with NVIDIA GPU
-docker compose --profile gpu up --build -d
+# NVIDIA GPU mode
+docker run -d --name omnivoice --gpus all \
+  -p 127.0.0.1:3900:3900 \
+  -v omnivoice-data:/app/omnivoice_data \
+  ghcr.io/debpalash/omnivoice-studio:latest
+```
+
+Or use **Docker Compose** with the GHCR image:
+
+```bash
+# CPU mode
+docker compose -f deploy/docker-compose.yml up -d
+
+# GPU mode
+docker compose -f deploy/docker-compose.yml --profile gpu up -d
 ```
 
 Open [http://localhost:3900](http://localhost:3900) once the health check passes. First run downloads ~4 GB of model weights — progress is shown in `docker compose logs -f`.
 
-> **Network access:** the container binds to `127.0.0.1` only. To reach OmniVoice from another machine on your LAN, change the port mapping in `docker-compose.yml` to `"0.0.0.0:3900:3900"`. OmniVoice ships no built-in authentication — when exposing it beyond your machine, put it behind a reverse proxy with auth (Caddy `basic_auth`, nginx + htpasswd, Tailscale, etc.).
+<details>
+<summary><b>Build from source instead of pulling</b></summary>
+<br/>
+
+```bash
+docker compose -f deploy/docker-compose.yml up --build -d
+```
+
+</details>
+
+> **Network access:** the container binds to `127.0.0.1` only. To reach OmniVoice from another machine on your LAN, change the port mapping to `"0.0.0.0:3900:3900"`. OmniVoice ships no built-in authentication — when exposing it beyond your machine, put it behind a reverse proxy with auth (Caddy `basic_auth`, nginx + htpasswd, Tailscale, etc.).
 
 ### Desktop App
 

deploy/Dockerfile

@@ -36,8 +36,8 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 # Install `uv` for blazing-fast reliable pip resolution
 RUN pip install --no-cache-dir uv
 
-# Copy python packaging specs
-COPY pyproject.toml uv.lock ./
+# Copy python packaging specs (README.md required by hatchling metadata)
+COPY pyproject.toml uv.lock README.md ./
 
 # Install the project (non-editable — no need for -e in containers).
 # Uses `uv` for exponentially faster resolution than plain pip.

deploy/docker-compose.yml

@@ -19,9 +19,12 @@
 services:
   # ── CPU mode (default) ──────────────────────────────────────
   omnivoice:
-    build:
-      context: ..
-      dockerfile: deploy/Dockerfile
+    image: ghcr.io/debpalash/omnivoice-studio:latest
+    # To build from source instead of pulling, comment out `image:` and
+    # uncomment the two lines below:
+    # build:
+    #   context: ..
+    #   dockerfile: deploy/Dockerfile
     container_name: omnivoice-studio
     ports:
       - "127.0.0.1:3900:3900"
@@ -42,9 +45,10 @@ services:
 
   # ── GPU mode — activate with: docker compose --profile gpu up
   omnivoice-gpu:
-    build:
-      context: ..
-      dockerfile: deploy/Dockerfile
+    image: ghcr.io/debpalash/omnivoice-studio:latest
+    # build:
+    #   context: ..
+    #   dockerfile: deploy/Dockerfile
     container_name: omnivoice-studio-gpu
     profiles: ["gpu"]
     ports:

uv.lock

@@ -2913,7 +2913,7 @@ wheels = [
 
 [[package]]
 name = "omnivoice"
-version = "0.2.4"
+version = "0.2.7"
 source = { editable = "." }
 dependencies = [
     { name = "accelerate" },