Chatterbox model support #4541
Chatterbox model support #4541
Conversation
📝 WalkthroughWalkthroughAdds a new TTSModels literal type and exposes it from the package; threads an optional Changes
Sequence Diagram(s)sequenceDiagram
participant Client
participant TTS
participant ResembleAPI
participant AudioSink
Client->>TTS: instantiate TTS(model="chatterbox")
Client->>TTS: request synthesis (text)
alt REST path
TTS->>ResembleAPI: HTTP POST { voice_uuid, model?, audio_chunk }
ResembleAPI-->>TTS: synthesized audio chunks
else WebSocket streaming
TTS->>ResembleAPI: WS send token payload { token, model? }
ResembleAPI-->>TTS: WS audio frames
end
TTS->>AudioSink: deliver synthesized audio
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
📜 Recent review detailsConfiguration used: Organization UI Review profile: CHILL Plan: Pro 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (2)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
✏️ Tip: You can disable this entire section by setting Comment |
livekit-plugins/livekit-plugins-resemble/livekit/plugins/resemble/models.py
Show resolved
Hide resolved
…s and updating default model settings in the TTS class.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
livekit-plugins/livekit-plugins-resemble/livekit/plugins/resemble/tts.py (1)
143-157: Bug:update_optionsalways resets model to"resemble"when not explicitly provided.The default value
model: TTSModels | str = "resemble"combined with the checkmodel if model is not None else self._opts.modelmeans the model will always be overwritten to"resemble"when callingupdate_options()without explicitly specifying a model. This silently resets any previously configured model.For example, if a user sets
model="chatterbox"in__init__, then later callsupdate_options(voice_uuid="new-voice"), the model will unexpectedly revert to"resemble".🐛 Proposed fix
def update_options( self, *, voice_uuid: str | None = None, - model: TTSModels | str = "resemble", + model: TTSModels | str | None = None, ) -> None: """ Update the Text-to-Speech (TTS) configuration options. Args: voice_uuid (str, optional): The voice UUID for the desired voice. - model (TTSModels | str, optional): The model to use for synthesis. + model (TTSModels | str | None, optional): The model to use for synthesis. """ # noqa: E501 self._opts.voice_uuid = voice_uuid or self._opts.voice_uuid self._opts.model = model if model is not None else self._opts.model
📜 Review details
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
livekit-plugins/livekit-plugins-resemble/livekit/plugins/resemble/models.pylivekit-plugins/livekit-plugins-resemble/livekit/plugins/resemble/tts.py
🧰 Additional context used
📓 Path-based instructions (1)
**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
**/*.py: Format code with ruff
Run ruff linter and auto-fix issues
Run mypy type checker in strict mode
Maintain line length of 100 characters maximum
Ensure Python 3.9+ compatibility
Use Google-style docstrings
Files:
livekit-plugins/livekit-plugins-resemble/livekit/plugins/resemble/models.pylivekit-plugins/livekit-plugins-resemble/livekit/plugins/resemble/tts.py
🧬 Code graph analysis (1)
livekit-plugins/livekit-plugins-resemble/livekit/plugins/resemble/tts.py (7)
livekit-plugins/livekit-plugins-elevenlabs/livekit/plugins/elevenlabs/tts.py (2)
model(204-205)_ensure_session(211-214)livekit-agents/livekit/agents/tts/tts.py (1)
model(89-98)livekit-plugins/livekit-plugins-smallestai/livekit/plugins/smallestai/tts.py (2)
model(122-123)_ensure_session(129-133)livekit-plugins/livekit-plugins-groq/livekit/plugins/groq/tts.py (2)
model(99-100)_ensure_session(106-110)livekit-plugins/livekit-plugins-google/livekit/plugins/google/tts.py (1)
model(174-175)livekit-plugins/livekit-plugins-deepgram/livekit/plugins/deepgram/tts.py (2)
model(104-105)_ensure_session(154-157)livekit-plugins/livekit-plugins-clova/livekit/plugins/clova/stt.py (1)
_ensure_session(94-97)
🔇 Additional comments (6)
livekit-plugins/livekit-plugins-resemble/livekit/plugins/resemble/models.py (1)
7-9: LGTM!The
TTSModelstype alias correctly defines the supported models as aLiteralunion, and includes"resemble"as a valid option to maintain backward compatibility as the default.livekit-plugins/livekit-plugins-resemble/livekit/plugins/resemble/tts.py (5)
39-39: LGTM!Import of
TTSModelsis correctly added.
55-105: LGTM!The
modelparameter is correctly added to__init__with a sensible default of"resemble"for backward compatibility. The docstring clearly documents the available options.
114-116: LGTM!The
modelproperty now correctly returns the configured model, consistent with other TTS plugin implementations.
187-204: LGTM!The REST payload correctly includes the
modelfield for synthesis requests.
318-332: LGTM!The WebSocket payload correctly includes the
modelfield, consistent with the REST implementation.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
…els and updating model type to allow None. Adjusted default model settings and payload handling for TTS requests.
2 participants
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.