ByteDance's Seedance 2.5 generates 30-second video clips with built-in audio

ByteDance has launched Seedance 2.5, an AI video model that generates video and audio together in a single pass.

It can produce clips up to 30 seconds long and use multiple image, video, and audio references for scene generation.

The model is available now on Jimeng AI and Doubao Pro, with API access planned through BytePlus ModelArk.

Built-in audio and longer outputs could streamline ad and content production by reducing the need to assemble clips separately.