Skip to content

feat: Migrate from OpenAI to Gemini Live for speech-to-speech#1

Merged
Dhravya merged 6 commits intomainfrom
gemini-live
Jan 21, 2026
Merged

feat: Migrate from OpenAI to Gemini Live for speech-to-speech#1
Dhravya merged 6 commits intomainfrom
gemini-live

Conversation

@Prasanna721
Copy link
Member

@Prasanna721 Prasanna721 commented Jan 18, 2026

Summary

  • Switch backend from OpenAI (STT + LLM + TTS) to Gemini Live speech-to-speech
  • Update frontend to handle TTS text streaming for bot transcription
  • Fix RTVI pipeline positioning for proper client communication

Dhravya and others added 2 commits January 16, 2026 12:07
- Switch backend from OpenAI (STT + LLM + TTS) to Gemini Live
- Use LLMContextAggregatorPair instead of OpenAILLMContext
- Configure Gemini VAD parameters for voice detection
- Update frontend to handle TTS text streaming for bot transcription
- Add TTS buffer refs to accumulate bot speech chunks into single message
- Use onBotTtsText callback instead of onBotTranscript

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
@Prasanna721 Prasanna721 requested a review from Dhravya January 18, 2026 03:29
Prasanna721 and others added 2 commits January 17, 2026 19:44
- Delete @modelcontextprotocol/sdk@1.23.0 patch (transitive dep updated to 1.25.2)
- Remove patch-package from devDependencies
- Remove postinstall script since no patches remain

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
@Prasanna721 Prasanna721 self-assigned this Jan 18, 2026
@Dhravya Dhravya merged commit 5dce394 into main Jan 21, 2026
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants