Introducing Gemini 3.8 Live with Live Avatar

Google has announced Gemini 3.8 Live with Live Avatar, a feature that adds near real-time visual presence to its conversational AI. Building on last week's Gemini 3.8 Live launch, Live Avatar pairs video generation with speech to create avatars that listen, see, and speak with precise lip-syncing, natural expressions, and fluid turn-taking. The feature processes visual and audio inputs simultaneously for richer multimodal conversations and supports asynchronous tool calling, allowing it to execute background tasks while maintaining uninterrupted dialogue. Live Avatar offers native multilingual speech-to-speech synchronization across 97 languages without degrading video fidelity. Organizations can choose from a library of preset avatars or generate custom ones from reference images (currently available via enterprise allowlisting). All output is watermarked with SynthID for transparency. Gemini 3.8 Live with Live Avatar is available starting today in Gemini Enterprise.

(Source：Gemini)