Gemini 3.8 Live
URL: https://knowledge.ivjn.us/en/works/gemini-3-8-live.html

Google DeepMind's real-time voice model, generally available on 15 September 2026 and serving low-latency audio conversations through the Live API.

Gemini 3.8 Live is the real-time voice model in the Gemini 3.8 family, generally available on 15 September 2026 under the model IDs `gemini-3.8-live` and `gemini-3.8-live-extended-thinking`. It serves audio-to-audio conversations through the Live API with interleaved reasoning, asynchronous function calling by default and full session client content updates.

Google highlights improved voice quality, reliability and real-time agent orchestration. The Extended Thinking variant adds background reasoning during live audio interaction.

Updated: 2026-10-30

Relations:
- Published by: Google DeepMind https://knowledge.ivjn.us/en/organizations/google-deepmind.html

Mentioned in:
- Gemini 3.8 Live Extended Thinking https://knowledge.ivjn.us/en/works/gemini-3-8-live-extended-thinking.html

Sources:
- Gemini API release notes https://ai.google.dev/gemini-api/docs/changelog
- Google models https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models