Google DeepMind has unveiled Gemini 3.8 Live with Live Avatar, bringing near real-time visual presence to its native live dialogue models and marking one of the most ambitious enterprise AI launches this year. The feature pairs near real-time video generation with speech to create an experience that listens, sees, and speaks with a dynamic visual persona, moving well beyond text and voice into embodied interaction.
With precise lip-syncing, natural expressions, and fluid turn-taking, Live Avatar enables enterprises to expand their virtual offerings more interactively. Whether providing engaging customer service, delivering interactive product walkthroughs, or powering virtual receptionists, the feature transforms digital exchanges into richer and more accessible experiences that feel considerably more human than current chatbot interfaces.
Beyond visual presence, the feature is backed by Gemini's advanced reasoning capabilities. With asynchronous tool calling, Live Avatar can trigger tool calls and fetch data in the background while continuing active dialogue, handling complex multi-step tasks while ensuring an uninterrupted conversational flow. This means the avatar can check a hotel reservation, pull up a customer's order history, or query a database while maintaining eye contact and natural conversation rhythm.
The feature supports native multilingual speech-to-speech synchronization across 97 languages, dynamically adapting lip-sync and expressions without degrading video fidelity or introducing visual drift. Organizations can also customize Live Avatars from a single reference image while preserving likeness and brand styling. All output is watermarked with SynthID, Google's imperceptible digital watermarking system, to ensure AI-generated content remains detectable.