wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add changelog entry

Browse Source
This commit is contained in:
Mark Backman
2024-12-09 10:52:32 -05:00
parent 1cc2da571e
commit 29a042a101
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
CHANGELOG.md
View File

@@ -9,9 +9,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Added ### Added
- New `STTMuteStrategy` called `FUNCTION_CALL` which mutes the STT service
during LLM function calls.
- `DeepgramSTTService` now exposes two event handlers `on_speech_started` and - `DeepgramSTTService` now exposes two event handlers `on_speech_started` and
`on_utterance_end` that could be used to implement interruptions. See new `on_utterance_end` that could be used to implement interruptions. See new
example `examples/foundational/07c-interruptible-deepgram-vad.py` example `examples/foundational/07c-interruptible-deepgram-vad.py`.
- Added `GroqLLMService`, `GrokLLMService`, and `NimLLMService` for Groq, Grok, - Added `GroqLLMService`, `GrokLLMService`, and `NimLLMService` for Groq, Grok,
and NVIDIA NIM API integration, with an OpenAI-compatible interface. and NVIDIA NIM API integration, with an OpenAI-compatible interface.
@@ -38,6 +41,8 @@ async def on_audio_data(processor, audio, sample_rate, num_channels):
### Changed ### Changed
- `STTMuteFilter` now supports multiple simultaneous muting strategies
- `XTTSService` language now defaults to `Language.EN`. - `XTTSService` language now defaults to `Language.EN`.
- `SoundfileMixer` doesn't resample input files anymore to avoid startup - `SoundfileMixer` doesn't resample input files anymore to avoid startup