v0.0.33

pipecat-ai/pipecatv0.0.33Jun 25, 2024by aconchillo

AI Summary

Upgraded to Cartesia's new Python library 1.0.0, fixed asynchronous STT issues with interruptions, and resolved a blocking situation in the Daily transport.

Key Highlights

Upgraded Cartesia library to 1.0.0 with new API requirements.
Fixed async STT services (Deepgram/Azure) for proper interruption handling.
Fixed Daily transport blocking issues when reading frames after a participant leaves.

Breaking Changes

CartesiaTTSService now requires a voice ID instead of a voice name.
Audio parameters changed from `output_format` to `sample_rate` and `encoding`.

Full Release Notes

### Changed

- Upgraded to Cartesia's new Python library 1.0.0. `CartesiaTTSService` now expects a voice ID instead of a voice name (you can get the voice ID from Cartesia's playground). You can also specify the audio `sample_rate` and `encoding` instead of the previous `output_format`.

### Fixed

- Fixed an issue with asynchronous STT services (Deepgram and Azure) that could cause static audio issues and interruptions to not work properly when dealing with multiple LLMs sentences.

- Fixed an issue that could mix new LLM responses with previous ones when handling interruptions.

- Fixed a Daily transport blocking situation that occurred while reading audio frames after a participant left the room. Needs daily-python >= 0.10.1.