Mini toolsMuse Video Preview
Muse Video is Meta Superintelligence Labs' early preview video generation model, built on the same pretraining base as Muse Image. It offers competitive performance in prompt adherence, visual fidelity, and temporal consistency, and includes native audio support so generated clips can carry synchronized sound rather than requiring a separate audio pass. Meta notes it is still investing in areas with current performance gaps, including audio video synchronization and physically accurate fast motion. On the Arena leaderboard, Muse Video ranks No. 3 in human preference Elo for text to video as of July 2026. It is being previewed alongside the general availability of Muse Image and is coming soon to creators and to Meta AI, rather than being broadly available yet.
New
Video
Overview
Muse Video is Meta's preview video generation model, built on the same pretraining base as Muse Image. It delivers strong prompt adherence, visual fidelity, and temporal consistency, with native audio support, and is coming soon to creators and Meta AI.
About Meta Platforms
We're connecting people to what they care about, powering new, meaningful experiences, and advancing the state-of-the-art through open research and accessible tooling.
Industry:
Technology, Information and Media
Company Size:
78865
Location:
Menlo Park, California, US
Website:
ai.meta.com
Last updated: July 8, 2026
