# Canonical feature inventory — the single source of truth that the daily # docs-drift job (.github/workflows/docs-drift.yml) diffs against README.md, # docs/, and the engine registries via scripts/check-docs-drift.py. # # When a PR adds or removes an engine or user-facing feature, update this # file in the same PR — otherwise the nightly job opens/updates the rolling # `docs-drift` issue. Spec: docs/competitive-analysis.md Spec 9a / # docs/specs/2026-06-12-elevenlabs-parity-program.md Wave 0.1. # Each name must appear verbatim in README.md (the Features grid). features: - Voice Cloning - Voice Design - Video Dubbing - Dictation Widget - Vocal Isolation - Speaker Diarization - Batch Queue - MCP Server - AI Watermark - Local-first - GPU Auto-Detect - Remote Model Downloads - Extensible # id: must exactly match the registry keys in backend/services/tts_backend.py # (_REGISTRY eager entries + _LAZY_REGISTRY). # readme (optional): a string that must appear in README.md (engine table row). # doc (optional): a repo-relative doc file that must exist. tts_engines: - id: omnivoice readme: "**VoiceStudio** (default, powered by k2-fsa/OmniVoice)" - id: omnivoice-subprocess doc: docs/engines/omnivoice-subprocess.md - id: cosyvoice readme: CosyVoice 3 doc: docs/engines/cosyvoice.md - id: kittentts readme: KittenTTS - id: mlx-audio readme: MLX-Audio - id: voxcpm2 readme: VoxCPM2 - id: moss-tts-nano readme: MOSS-TTS-Nano - id: gpt-sovits - id: sherpa-onnx - id: indextts2 readme: "**IndexTTS 2.5** ⚡" 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 - id: pockettts # Same contract against backend/services/asr_backend.py _REGISTRY. asr_engines: - id: whisperx readme: "**WhisperX** (default)" - id: faster-whisper readme: Faster-Whisper - id: mlx-whisper readme: MLX Whisper - id: pytorch-whisper readme: PyTorch Whisper - id: nemo-parakeet readme: Parakeet TDT - id: parakeet-mlx readme: Parakeet TDT v3 (MLX) - id: moonshine readme: Moonshine - id: funasr readme: FunASR - id: sherpa-onnx-asr readme: "**sherpa-onnx** (live dictation)" - id: openai-compat-asr readme: "**OpenAI-compatible** ⚠️ configured server" # Doc files that must exist (the install path users are sent to). docs: - docs/downloading-models.md - docs/remote-workers.md - docs/adr/inbound-node-mode.md - docs/branding.md - docs/install/macos.md - docs/install/windows.md - docs/install/linux.md - docs/install/docker.md - docs/install/troubleshooting.md - docs/features/dictation.md - docs/migration/real-time-voice-cloning.md