A real-time avatar video-generation model introduced by Meta Research on 2026-09-23, generating continuous, synchronized character video conditioned on Muse Realtime Voice speech tokens and reference media.
Meta Research has introduced this real-time avatar technology, but has not disclosed a standalone API model ID or public access terms; its post also notes that not all demos reflect avatars available in the Muse app.
Only published specifications are shown.
— Meta Research introduced Muse Realtime Avatar, an audio-driven model that continuously generates synchronized character video from speech tokens and reference media; reported demo specs are 448×768 at 25 fps with about 870 ms to first byte. ↗
Meta describes it as an audio-driven Diffusion Transformer; it reports 448×768 portrait video at 25 fps and about 870 ms from the end of a user turn to the first byte of the synchronized voice-and-video response.
Meta Research introduced Muse Realtime Avatar, an audio-driven model that continuously generates synchronized character video from speech tokens and reference media; reported demo specs are 448×768 at 25 fps with about 870 ms to first byte.
View sourceSelect a card to view the related model.
No related models recorded yet
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.