Model · Google · Realtime-Voice
Gemini 3.1 Flash Live Preview
Google's low-latency audio-to-audio Live API model for real-time dialogue and voice-first applications, built on the Gemini 3.1 stack. Being retired: shutdown 2026-11-17, with gemini-3.8-live as the replacement.
- Modality
- Realtime-Voice
- License
- Proprietary (Proprietary)
- Context window
- 131,072 tokens
- Released
- March 11, 2026
- Last verified
- October 28, 2026
- Runs locally
- No
Strengths
- Low-latency audio-to-audio interaction
- Multimodal awareness across text, image, audio, and video inputs
- Designed as the migration target for Gemini 2.5 Flash Live workloads
Weaknesses
- Preview model with some live features still missing
- Closed weights
Try it
| Where | Type | Notes |
|---|---|---|
| Google AI Studio | hosted-api | Live API preview |
Version history
- Gemini 3.8 Flash Sep 2026
- Gemini 3.5 Flash-Lite Jul 2026
- Gemini 3.5 Flash May 2026 Deprecated
- Gemini 3.1 Flash-Lite May 2026 Deprecated
- Gemini 3.1 Flash Live Preview Mar 2026 Current Deprecated
Official sources
- Model docs docs
- Live API guide docs
Change log
- — Deprecated — Google's deprecations page sets a shutdown date of 2026-11-17 and names gemini-3.8-live (GA 2026-09-15) as the replacement.
- — Release date corrected to 2026-03-11 from Google's deprecations page. The previous 2026-05-07 was the models page's global 'last updated' stamp. Verified still current with no shutdown announced.
- — Added after verification of the Gemini 3 family rollout in current Google model docs.
Esc