Model releaseHigh global significanceConfirmed confidence
Google releases Gemini 3.1 Flash Live Preview
Google releases a new low-latency, audio-to-audio real-time conversation model in preview.
What happened
Event details
The model succeeds Gemini 2.5 Flash Native Audio, accepts text, image, audio and video input, and produces text and audio output.
Assessment
Why it matters
It updates the main Gemini Live real-time audio-to-audio line and broadens the multimodal context available to voice-first applications.
72/100Global significance score. Regional effects are recorded only when the evidence supports a meaningful difference.
Availability
Access notes
Available as gemini-3.1-flash-live-preview from March 26, 2026. It currently does not support Gemini 2.5's proactive-audio or affective-dialogue settings.