Introducing Gemini 3.8 Live with Live Avatar
Google DeepMind added Live Avatar real-time video presence to Gemini 3.8 Live in Gemini Enterprise.
Google DeepMind announced Gemini 3.8 Live with Live Avatar, available in Gemini Enterprise as of September 24, 2026. The feature pairs near real-time video with speech for lip-synced avatars that support 97 languages and can call tools asynchronously without interrupting dialogue. Enterprises on an allowlist can generate custom avatars from a reference image, and audio and video outputs are watermarked with SynthID.
- Live Avatar is available in Gemini Enterprise after last week's Gemini 3.8 Live launch.
- Lip-sync and expressions adapt across 97 languages without claimed visual drift.
- Asynchronous tool calls keep dialogue going while background tasks fetch data.
- Custom avatars from a reference image are limited to enterprise allowlisting.
- SynthID watermarks are embedded in generated audio and video.
- Vendors
- Organizations
- Google DeepMind
- AI models
- Gemini 3.8 Live
From the original article
2 min read at deepmind.google
Gemini 3. 8 Live with Live Avatar brings real-time visual presence to Gemini’s conversational AI. By natively coupling our live dialogue capabilities with low-latency streaming video, Live Avatar enables a more natural and intuitive conversational experience for enterprises and their users.
deepmind.google
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.