Merge pull request #1672 from golbin/main

Use "use_original_timestamps" only for sonic-2 model
This commit is contained in:
Mark Backman
2025-05-18 07:24:58 -04:00
committed by GitHub
2 changed files with 5 additions and 1 deletions

View File

@@ -74,6 +74,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- Removed `SileroVAD` frame processor, just use `SileroVADAnalyzer`
instead. Also removed, `07a-interruptible-vad.py` example.
### Fixed
- Fixed an issue with `CartesiaTTSService` where `TTSTextFrame` messages weren't being emitted when the model was set to `sonic`. This resulted in the assistant context not being updated with assistant messages.
### Other
- Added foundation example `07y-minimax-http.py` to show how to use the

View File

@@ -167,7 +167,7 @@ class CartesiaTTSService(AudioContextWordTTSService):
"output_format": self._settings["output_format"],
"language": self._settings["language"],
"add_timestamps": add_timestamps,
"use_original_timestamps": True,
"use_original_timestamps": False if self.model_name == "sonic" else True,
}
return json.dumps(msg)