Meta has launched real-time voice conversation and expressive avatar features for its personal AI assistant Muse, rolling out first to US users across mobile, web and Mac. Two models, Muse Realtime Voice and Muse Realtime Avatar, drive the experience, streaming 448×768 portrait video at 25 fps with roughly 870 ms latency to first audio-video response, plus interruptible turn-taking and swappable avatars and voice styles.
Termsslug: real-time-voice-conversation
Real-Time Voice Conversation
实时语音对话
A low-latency, bidirectional speech interaction paradigm between users and AI models, typically spanning speech recognition, mod
Curated Intelligence
IT之家 · 智能时代T2·Agents
72 pts
The Verge AIT2·product_launch
58 pts
Meta has rolled out real-time voice conversations to its Muse AI agent, with avatars animating in sync with speech and voice tone adjustable via natural language or settings. The feature is live on iOS, with Meta promising expansion to its AI glasses and the forthcoming Muse Charm device later this year.