Google has introduced Gemini 3.8 Live with Live Avatar, a feature that pairs near real-time video generation with speech to create dynamic visual personas for native live dialogue models.
- The feature enables enterprises to expand virtual offerings through precise lip-syncing, natural expressions, and fluid turn-taking.
- It supports asynchronous tool execution, allowing the avatar to fetch data in the background while maintaining an uninterrupted conversational flow.
- Live Avatar features native multilingual speech-to-speech synchronization, seamlessly transitioning across 97 languages without degrading video fidelity.
- Organizations can customize avatars from high-quality reference images to preserve brand styling or character identity, though this is currently available only through enterprise allowlisting.
- All AI-generated output is watermarked with SynthID to ensure transparency and help minimize misinformation.
Gemini 3.8 Live with Live Avatar is now available in Gemini Enterprise, allowing developers to build richer, more accessible digital exchanges.