# ByteDance releases Seedance 2.5 video model with 30-second clips and multi-file references

Canonical page: https://technooptimist.io/stories/bytedance-releases-seedance-2-5-video-model-with-30-second-clips-and-3da46c0d
Date: 31 Jul 2026
About: [ByteDance](https://technooptimist.io/companies/bytedance.md) · [Seedance 2.0](https://technooptimist.io/ai/seedance.md)
Original source: https://technode.com/2026/07/31/bytedance-launches-seedance-2-5-video-generation-model/

ByteDance has released Seedance 2.5, the newest version of its Seed video-generation model. It can generate a 30-second clip in one run and extend clips over several turns for longer sequences. The model is rolling out to the Jimeng AI app and the Pro version of Doubao first.

## Key facts

- Clips up to 30 seconds in a single run, with multi-turn extension for longer sequences.
- One input can take up to 30 images, 10 videos and 10 audio clips as references.
- Rolling out to Jimeng AI and the Pro version of Doubao at launch.
- API access on Volcano Engine's Ark platform was expected soon, according to the report.

---

The Techno Optimist tracks every frontier of technology, program by program: https://technooptimist.io/ (a Markdown version of any page: add .md to its URL; site map for agents: https://technooptimist.io/llms.txt).
Data API (JSON, realtime stream): https://technooptimist.io/developers. People read 5 pages free, then Reader $10/month; these Markdown pages are open to agents.