Loading the page…
Meta Muse video with sound and speech: from a prompt, a frame or photo references, up to 60 seconds.
Muse Video is available in IIshki Studio — video generation from a prompt, paid for with tokens. IIshki club members get reduced prices on every model. Pick a model above, set the parameters and start the generation.
Muse Video is Meta's video model: it creates clips with sound and character speech from text, from a starting frame (optionally a last frame too) or from 1–4 photo references. Clips run 5 to 60 seconds at 720p, with seven style presets from cinematic to anime and cyberpunk.
A red fox runs through a snowy forest at dawn, a man on screen quietly says: what a morning
The character from the photo walks through a rainy neon city at night, the camera follows
Muse Video generates 5 to 60 second clips with sound from a prompt, a first (and last) frame or 1–4 photo references. Ratios 16:9, 9:16, 1:1, 4:3 and 3:4 at 720p, with presets: cinematic, 2D anime, 3D fantasy, US comic, cyberpunk and product UGC.
Yes — Muse Video makes clips up to a minute: 5, 10, 20, 30, 40, 50 or 60 seconds in one generation, no stitching. The final length can differ slightly from the selected one.
The price depends on length: longer clips cost more, but not proportionally — 30 seconds costs the same as 20. The current token price is on the model card; club members get the club price.