Gemini 3.8 Live Introduces Real-Time Live Avatar for Enterprise

The Live Avatar feature pairs near real-time video generation with speech, creating a dynamic visual persona that listens, sees, and speaks. It brings precise lip-syncing, natural expressions, and fluid turn-taking to enterprise virtual offerings, transforming digital exchanges into richer experiences.

Live Avatar leverages Gemini’s advanced reasoning to trigger tool calls and fetch data in the background. This ensures an uninterrupted conversational flow, allowing the avatar to handle complex tasks like checking in a guest at a hotel without pausing the interaction.

In addition to a library of diverse preset avatars, organizations can generate custom Live Avatars from high-quality reference images. This preserves brand styling and character identity, though custom avatar creation is currently available only through enterprise allowlisting.

By simultaneously processing visual and audio inputs, Live Avatar facilitates richer conversations that mirror human interaction. This capability allows enterprise agents to engage in dialogues incorporating listening, looking, speaking, and facial expressions for a more comprehensive experience.

The feature includes native multilingual speech-to-speech synchronization, dynamically adapting lip-sync and expressions. It can seamlessly transition across 97 languages without visual degradation or drift, providing natural conversational experiences at a global scale.

All AI-generated audio and video output from Live Avatar is watermarked with SynthID, an imperceptible watermark woven directly into the content. This helps ensure AI-generated content remains detectable, minimizing misinformation and misattribution.