gemini-live-api-examples
https://github.com/google-gemini/gemini-live-api-examples
TypeScript
Gemini Live provides multimodal realtime agent capabilities. Build voice agents that can process vision and text in realtime.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
TypeScript not yet supported1 Subscribers
Add a CodeTriage badge to gemini-live-api-examples
Help out
- Issues
- chore: bump aiohttp dependency version in uv.lock
- chore(deps): bump pyasn1 from 0.6.3 to 0.6.5 in /gemini-live-ephemeral-tokens-websocket
- chore(deps): bump certifi from 2026.4.22 to 2026.10.18 in /gemini-live-ephemeral-tokens-websocket
- chore(deps): bump aiohttp from 3.13.5 to 3.14.4 in /gemini-live-ephemeral-tokens-websocket
- chore(deps): bump multidict from 6.7.1 to 6.9.1 in /gemini-live-ephemeral-tokens-websocket
- chore(deps): bump urllib3 from 2.6.3 to 2.8.0 in /gemini-live-ephemeral-tokens-websocket
- gemini-3.8-live: an interrupted BLOCKING call gets no toolCallCancellation, and the model re-issues it with a new id
- gemini-3.8-live: after a silent connection loss, every session resume is refused with 1011 while the server still holds the old connection
- gemini-3.8-live: agent never acts on a pending request after a session handoff — connects cleanly, no error, silent until new input arrives
- gemini-3.1-flash-live-preview: no turnComplete for 50s+ after inputTranscription, sometimes with duplicate re-transcription of the same utterance
- Docs
- TypeScript not yet supported