Meta is currently testing its upcoming Muse Video model in beta with selected partners. The model, labeled “Beta,” was first previewed in July alongside Muse Image. At that time, Meta shared initial samples and announced that Muse Video would soon be available to creators and Meta AI.
TestingCatalog recently gained access to Muse Video and tested it directly. Based on our early generations, the model shows state-of-the-art potential, particularly in fine detail, world understanding, and temporal consistency. It currently produces 10-second videos, but the output quality is remarkably high. Meta has also confirmed that Muse Video supports native audio, although the company previously acknowledged remaining gaps around audio-video synchronization and physically accurate fast motion.
Muse Video samples 👀
"Cyberpunk hacker robot working in front of many monitors"
"A shaky, low-quality iPhone video recording. A guy holding the camera selfie-style walks up to random people on a busy city street and asks each one, "How do you feel about being AI generated?" The video has authentic smartphone artifacts—slight motion blur, overexposed sky, wind noise, and the occasional finger over the lens."
"The rocket at the rocket station is launching. Everything looks normal until the rocket explodes into confetti pieces and leaves nothing behind."
"The man couldn't believe it when he finally became a kitten dad. Excitedly he shouted "I'm a dad now! A cat dad!". He's so happy that he starts tearing up. The kitten meows before the video ends."
"A cat made out of Lego technic in the rain made out of fluffy plastic rain"
"A glass of red wine tips over on a white marble counter, spilling toward the camera. Static shot"
"A woman with curly red hair and a green scarf walks toward camera down a crowded Tokyo street at night, stops, and looks up."
"Orbiting shot around a chef plating a dish, 180-degree arc, shallow depth of field."
"A neon sign reading ‘OPEN 24 HOURS’ flickers on above a diner door in the rain."
"A car’s headlights sweep across a bedroom wall at night, shadows shifting."
Two swordsmen in a bamboo forest exchange three strikes, blades meeting mid-frame. Wide shot, overcast light.
"Two fighters in a dimly lit warehouse; one throws a punch, the other blocks and counters. Handheld camera, shallow depth of field."
There is still no confirmed public release date. Meta has already stated that Muse Video is coming to Meta AI, making Meta.ai and the Meta AI app the most obvious initial destinations. Given that Muse Image is available for free everyday creation, Muse Video could follow a similar model, although its pricing or generation limits remain unknown.
The broader distribution possibilities are particularly important. Muse Video could become part of Meta’s Vibes feed for AI-generated videos and later expand across Instagram, Facebook, and other Meta products. Instagram’s video-heavy ecosystem is an obvious fit, while Meta’s Edits video creation app could also benefit from native generative video capabilities.
For Meta, video generation fits directly into its wider strategy of building its own media models and distributing them across products used by creators and consumers. Facebook and Instagram already revolve heavily around visual content, giving Meta a natural distribution advantage if Muse Video proves competitive at scale.
Our current access indicates that development has moved beyond Meta’s original public preview into working beta testing. Don't forget to take a look at the video samples we have collected so far.
Test prompts from @MarsForTech, @bughuntergeek, @BartokGabi17
