Gemini 3.8 Live
by Google
Gemini 3.8 Live is a model from Google, released on September 15, 2026.
Gemini 3.8 Live is Google's default low-latency audio-to-audio model for real-time voice agents and dialogue, built for fluid conversation without reasoning-induced delays. It accepts text, image, audio, and video input and produces text and audio output, with a 131,072-token input limit and 65,536-token output limit. It supports interleaved reasoning (thinking), asynchronous function calling, full session client content updates, built-in audio streaming, and search grounding, but does not support caching, code execution, file search, image generation, structured outputs, URL context, or the Batch API. It replaces gemini-3.1-flash-live-preview as the stable Live API model string.
Key specs
| Provider | |
|---|---|
| Release date | 2026-09-15 |
| License | proprietary |
Quick answers
Is Gemini 3.8 Live open source?
No. Gemini 3.8 Live is a proprietary model from Google (proprietary license).
When was Gemini 3.8 Live released?
Google released Gemini 3.8 Live on September 15, 2026.
Compare on the AI leaderboard · All AI models
More models from Google
- Gemini 4 Carbon — Google
- Gemini 4 Argon — Google
- Gemini 3.8 Flash — Google
- Gemini 3.1 Pro — Google
- Gemini 3.8 Flash Cyber — Google
- Gemini 3.5 Flash Cyber — Google