ByteDance Launches Seedance 2.5: Generates 30-Second Video Clips with Built-in Audio

The Decoder · rss · 2026-08-01

ByteDance has released Seedance 2.5, an AI video model capable of generating video and audio together in a single pass. Each clip can be up to 30 seconds long, which is three times the output length of Google's Gemini Omni Flash.

The model allows users to input dozens of images, video clips, and audio files as multimodal references. This capability could significantly streamline workflows for ad teams and creators by eliminating the traditional process of stitching together short individual clips.

Original post →

More from Multimodal

Multimodal channel →