Alibaba's Wan 3.0 enters public beta: 30-second video from your documents, slides and webpages
Alibaba's Tongyi Lab put its Wan 3.0 video model into public beta on Wednesday. The new version generates videos up to 30 seconds with sound, and folds what used to be separate models — text-to-video, image-to-video, reference-based generation and editing — into one system. The headline trick: it accepts documents, spreadsheets, presentations and webpages as input, turning static, text-heavy material into finished video.
Why it mattersThirty seconds with native audio moves AI video past the clip-toy stage, but the document-to-video angle is the bigger shift: it aims the tool at offices, classrooms and e-commerce rather than filmmakers. Alibaba's Wan family also underpins much of the open video ecosystem, so what lands in Wan usually spreads well beyond Alibaba.
Read in the app — free, in 9 languages
Related stories
DeepSeek's cheap workhorse can now see — and on agent tasks that need eyes it says it is close to Anthropic's best2026-08-21Adobe will now generate the music, the voiceover and the door slam — and it says the licence covers you
2026-08-21Show the robot once — three to twelve seconds — and it gets the job right 59 times out of 100 with no training at all
2026-08-21Six months ago Hollywood sent ByteDance a cease-and-desist. This week they signed a truce — and no money changed hands.
2026-08-20The model invents its own tasks, builds the rig to test them, then trains on the results — and DeepReinforce gave the weights away
2026-08-20