Back
AI summary
Written by AI from the official notes. Check them for exact details.Google released two new audio-to-audio models, Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, for real-time voice applications.
- Gemini 3.8 Live is optimized for low-latency voice interactions.
- Gemini 3.8 Live supports interleaved reasoning and asynchronous function calling.
- Gemini 3.8 Live Extended Thinking offers high-reasoning capabilities during live interactions.
Why it matters: Developers and businesses using voice applications should consider these models for improved performance and reasoning capabilities.
Full release notes2 changes
- Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking generally available (GA): Released two new audio-to-audio models for real-time voice applications using the Live API: Gemini 3.8 Live (
gemini-3.8-live): The default option for most low-latency voice agent experiences and real-time dialogue without reasoning delays. Features interleaved reasoning, default asynchronous function calling, and full session client content updates. - Gemini 3.8 Live Extended Thinking (
gemini-3.8-live-extended-thinking): High-reasoning audio-to-audio model supporting background reasoning during live audio interactions, recommended when higher background reasoning is required.
To get started, see the Live API guide, the Capabilities guide, and the Thinking guide.