Alibaba Wan 3.0 video with sound: from a prompt, a frame or references.
Wan 3.0 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.
Wan 3.0 (Wan AI) is Alibaba's video model and a newer generation than Wan 2.5: it creates clips with sound built in from text, from a starting frame or from references — photo, video and audio. Up to 30 seconds, up to 1080p, with Standard and Fast plans.
Wan 3.0 generates video up to 30 seconds with sound from a prompt, a starting frame or references (photo, video, audio). Ratios 16:9, 9:16, 1:1, 4:3 and 3:4; resolution 480p, 720p or 1080p.
Yes — audio is created together with the video and is not billed separately, which makes it handy for atmospheric clips and speech without a separate voice-over step.
The price depends on resolution — 720p costs more than 480p and 1080p more still — and the Fast plan costs more than Standard. The current token price is on the model card; club members get the club price.