Gemini 3.8 Live

Google · proprietary · gemini-3.8-live

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.