Production teams needing 30-second AI clips with audio; mainly in ByteDance's Chinese apps so far, with no stated price.
Kenning's take
What it does
Seedance 2.5 generates up to 30 seconds of video with matching audio in a single pass, which can be extended twice. It reads reference videos more closely, edits more reliably, and adds tools such as green-screen editing for production work. Press reports it launched on 31 July 2026 in ByteDance's own apps, with BytePlus API access after.
- Up to 30-second clips, extendable twice
- Joint audio and video
- Reference video understanding
- Green-screen and white-model control
Who it suits. Video creators and production teams who need longer AI clips.
Key facts
- Category
- AI models
- Part of
- Dreamina (CapCut)
- Made by
- ByteDance
- Based in
- China
- Released
- 31 July 2026
- How to get it
- in ByteDance apps such as Jimeng and Doubao, and through the BytePlus API
- Works on
- Web, API
Reviews and write-ups
- The Decoder
- TechNode 2026-07-31
FAQ
When was Seedance 2.5 released?
TechNode reported the launch on 31 July 2026.
How long are Seedance 2.5 videos?
Up to 30 seconds in one generation, and they can be extended twice.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
Seedance 2.0
ByteDance's video model that makes clips with sound from text, image, audio and video references
Seedream 4.5
ByteDance's image model with stronger multi-image editing, typography and dense text
Seedream 5.0 Lite
ByteDance's image model that reasons over prompts and can search the web before drawing
Seedream 5.0 Pro
ByteDance's image model for infographics, precise region edits and multilingual text