Meta Muse rolls out real-time voice and expressive avatars in the US
Meta’s personal AI agent Muse is rolling out real-time voice conversations and expressive avatars to users in the United States.
AT A GLANCE
Key points
- Real-time voice is rolling out gradually in the US.
- The expressive avatar moves in sync with generated speech.
- Users can describe a preferred voice in natural language.
What is changing?
Meta has started gradually rolling out real-time voice conversations and expressive avatars in the Muse app in the United States. Instead of typing, users can speak with the agent while its avatar produces facial and body movements synchronized with the generated voice. A voice can be selected from presets or described in natural language. The rollout moves Meta’s Muse Realtime Voice and Realtime Avatar technologies from a September research demonstration into a user-facing experience.
According to Meta’s technical explanation, the avatar system processes speech tokens and video generation in one streaming pipeline to keep voice, lip motion and expression synchronized. Initial access is limited to the Muse app and US users, with no broader regional timetable announced. Transparency, consent and misuse controls remain important when avatars resemble real people or generate live video.
Explore the original sources
Source date: 5 November 2026.
Published by AI Radar: 5 Nov 2026, 23:08 (Istanbul, UTC+3).
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…