Seedance 2.5

Audio-video joint generation model: produces up to a 30-second clip in one pass with multi-round extension, takes up to 30 images, 10 videos and 10 audio clips as references, and supports timestamp-level editing.

вендор — ByteDance (команда Seed); раскатывается в Jimeng AI и Doubao, доступ по API вендор обещает через ModelArk/Volcano Engine

Understands

text, images, video, audio

Produces

video, speech, sound effects

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.