Google added Live Avatar to Gemini 3.8 Live on September 24, giving its conversational model a near-real-time on-screen persona and making it available through Gemini Enterprise.
According to the Google documentation, the model can return synchronized speech and avatar video at 24 FPS, with lip-sync, facial expressions, and fluid turn-taking across 97 languages. Google also says conversations can continue while asynchronous tool calls run in the background.
For agent builders, Live Avatar turns voice sessions into visual interactions without a separate avatar layer. The access limits are the catch: preset avatars are available in Gemini Enterprise, while custom avatar creation requires enterprise allowlisting. Google says generated audio and video carry SynthID watermarks.