88Z AI, 7 August — Volcano Engine has officially launched the Seedance 2.5 API, delivering significant improvements over version 2.0 in instruction following, long-form narrative, human-like realism, and audio-visual quality. The service natively supports direct generation of 30-second videos, allows up to 50 full-modality reference materials, and is compatible with over ten languages. The model is now simultaneously available on platforms including LibTV, Qixiang AI, and TapNow.
At a glance
- Seedance 2.5 significantly upgrades instruction following, long narrative, and audio-visual quality over version 2.0
- Supports 30-second video generation and 50 full-modality references, now live on multiple platforms
The update
Volcano Engine has announced the official launch of the Seedance 2.5 API service. Compared to the previous version 2.0, the new model achieves significant upgrades in several core dimensions, including more precise instruction following, smoother long-form narrative performance, more realistic human-like presence, and superior audio-visual quality. In terms of features, Seedance 2.5 natively supports the direct generation of videos up to 30 seconds in length and can process up to 50 full-modality materials as reference inputs, while remaining compatible with over ten languages. Currently, the model is simultaneously available on third-party platforms such as LibTV, Qixiang AI, and TapNow, providing users with advanced video generation capabilities.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 火山引擎Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.