Release dates
— Gemini 3.8 Live and Extended Thinking reached GA together in the Live API, offering real-time voice interaction and background reasoning. ↗
Gemini 3.8 Live
The real-time voice and audiovisual-interaction model in Gemini 3.8; alongside audio and text, Live Avatar can generate MP4 avatar video synchronized with dialogue.
Google announced Gemini 3.8 Live GA in the Live API on 2026-09-15; Live Avatar became available in Gemini Enterprise on September 24, and the dynamic API guide still lists model ID `gemini-3.8-live` with real-time avatar-video output. Custom avatar creation requires enterprise allowlisting.
MODEL NUMBER102
- First public date
- 2026-09-15
- Organization
- Google DeepMind
- Family
- Gemini
01
Specifications
Only published specifications are shown.
02
Overview
Why it mattered
Live Avatar extends Gemini 3.8 Live from real-time voice dialogue to video interaction with a visual persona, without introducing a separate model ID.
03
Architecture & capabilities
Model capabilities
Native audioReal-time audioReal-time videoThinking modeTool use
04
Release history
Gemini 3.8 Live and Extended Thinking reached GA together in the Live API, offering real-time voice interaction and background reasoning.
View sourceGemini 3.8 Live gained Live Avatar on the existing `gemini-3.8-live` model, adding real-time voice/video interaction and MP4 avatar-video output; the feature is available in Gemini Enterprise.
View source05
Related models
Select a card to view the related model.
06
Sources
01
Gemini API release notes: Gemini 3.8 Live GAGoogle · Published 2026-09-15 · Checked 2026-09-18
Official · Verified02Introducing Gemini 3.8 Live with Live AvatarGoogle · Published 2026-09-24 · Checked 2026-09-26
Official · Verified03Gemini Live API overviewGoogle Cloud · Checked 2026-09-26
Official · VerifiedSuggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.