Conversational avatars with expressive real-time responses
AVTR-1 is an open-weights model for avatars that can hold interactive conversations. It generates natural speech and expressive facial reactions while supporting active listening in real time.
Ask the makers a question, share feedback or tell others how you use AVTR-1 Real-Time Open Weights Model.
Sign in to comment, ask the makers a question or share useful feedback.
Build responsive virtual avatars with customizable interaction
Create a personalized Android character with Gemini assistance
Use live avatars in calls and streams across platforms
No comments yet. Be the first to share your thoughts on AVTR-1 Real-Time Open Weights Model.