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(deps): bump anyio from 4.13.0 to 4.14.2 in /gemini-live-ephemeral-tokens-websocket
- chore(deps): bump pyasn1 from 0.6.3 to 0.6.4 in /gemini-live-ephemeral-tokens-websocket
- chore(deps): bump cryptography from 47.0.0 to 50.0.0 in /gemini-live-ephemeral-tokens-websocket
- chore(deps): bump aiohttp from 3.13.5 to 3.14.3 in /gemini-live-ephemeral-tokens-websocket
- input_audio_transcription returns fabricated content in unspoken languages while the model understands the audio correctly (Arabic, gemini-3.1-flash-live-preview)
- `gemini-3.1-flash-live-preview`: the model repeats the same sentence 2–4 times inside one generation (~7 s of silence between each) before releasing the toolCall
- gemini-live-2.5-flash-native-audio on Vertex: the model streams full-length audio at near-zero amplitude — the caller hears silence while every metric looks healthy (5.9% of production calls)
- Reconnect penalty
- `gemini-3.1-flash-live-preview`: a 1.0 s mid-sentence pause closes the turn while the caller is still speaking (+ empty generation when `thinking_level` is set)
- `gemini-3.1-flash-live-preview`: a turn left open after an ignored utterance never closes on its own; the caller's next sentence is consumed to close it with zero output tokens
- Docs
- TypeScript not yet supported