Google introduces Gemini 3.8 Live with Live Avatar for real-time visual presence

Google has introduced Gemini 3.8 Live with Live Avatar, a feature that adds near real-time visual presence to its native live dialogue models. By coupling live dialogue capabilities with low-latency streaming video, the update enables enterprises to create more natural and intuitive conversational experiences.

Multimodal Conversations and Tool Execution

The feature processes visual and audio inputs simultaneously, allowing agents to listen, see, and speak with a dynamic visual persona. This includes precise lip-syncing, natural expressions, and fluid turn-taking. Additionally, asynchronous tool execution allows the model to trigger tool calls and fetch data in the background while maintaining an uninterrupted conversational flow.

Global Scale and Customization

Live Avatar supports native multilingual speech-to-speech synchronization, seamlessly transitioning across 97 languages without degrading video fidelity or introducing visual drift. Organizations can choose from a library of preset avatars or create custom ones from high-quality reference images, though custom avatar creation is currently limited to enterprise allowlisting.

Safety and Availability

All output generated by the feature is watermarked with SynthID to ensure AI-generated content remains detectable. Gemini 3.8 Live with Live Avatar is available starting today in Gemini Enterprise.