Meta 向美国用户全量开放 Muse AI 实时视频通话
Meta 把 Muse 视频通话开放给全部美国用户了，虚拟形象能边听边反应，870ms 就接话，测试里赢过 Runway 和 HeyGen，挺想试试。
Meta 的 Muse 智能体现在支持美国所有用户进行实时视频通话，用户可将虚拟形象定制为人物或动物，且形象会边听边做出反应。技术上，Muse Realtime Voice 输出同时包含文字和语气的语音 token，Muse Realtime Avatar 将该流转换为口型同步视频，通过训练学生模型将教师模型的 120 步压缩为每视频块 2 步。系统以 25fps 流式传输 448x768 竖屏视频，用户停止说话后约 870ms 即开始回应。经 4-bit 量化、缓存和动态批处理优化后，一块 Nvidia GB200 可同时运行 12 路视频流。在 2-3 分钟通话的内部测试中，评分者以 78% 对 22% 偏好其优于 Runway Characters，以 88% 对 12% 优于 HeyGen LiveAvatar。
Meta just opened live video calls with its Muse AI agent to every US user.
Callers see an animated avatar they can restyle as a person, animal or other character, and it reacts while listening.
Muse Realtime Voice emits speech tokens carrying words and delivery, and Muse Realtime Avatar turns the same stream into lip-synced video.
To run that live, Meta trained a student model to reproduce in 2 passes per video chunk what a teacher built in 120.
the system streams 448x768 portrait video at 25 frames per second and starts replying about 870ms after a user stops talking.
Adding 4-bit quantization, caching and dynamic batching lets a single Nvidia GB200 run 12 video streams at once.
In company-run tests of 2- to 3-minute calls, raters preferred the avatar to Runway Characters 78% to 22% and HeyGen LiveAvatar 88% to 12%.
At 12 streams per GB200, 1M simultaneous callers would need about 83K of them for video alone, so serving cost could cap the avatar’s reach.
