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

Merge pull request #1824 from pipecat-ai/mb/gemini-live-transcribe-user-audio

Browse Source 
Update GeminiMultimodalLiveLLMService to use Gemini's user transcription
This commit is contained in:
Mark Backman
2025-05-16 22:51:04 -04:00
committed by GitHub
parent 88e472b3f1 fac6f526f7
commit deb43df0a4
10 changed files with 131 additions and 154 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
CHANGELOG.md
View File

@@ -59,11 +59,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed
- `GeminiMultimodalLiveLLMService` now uses the user transcription and usage
metrics provided by Gemini Live.
- `GoogleLLMService` has been updated to use `google-genai` instead of the
deprecated `google-generativeai`.
### Removed
- Since `GeminiMultimodalLiveLLMService` now transcribes it's own audio, the
`transcribe_user_audio` arg has been removed. Audio is now transcribed
automatically.
- Removed `SileroVAD` frame processor, just use `SileroVADAnalyzer`
instead. Also removed, `07a-interruptible-vad.py` example.