Back to events
Model releaseCritical global significanceConfirmed confidence

ByteDance officially releases Seedance 2.5

ByteDance officially released Seedance 2.5, which generates up to 30 seconds of audio and video in one pass and accepts as references up to 30 images, 10 video clips, and 10 audio clips.

Event details

ByteDance Seed officially released Seedance 2.5 on July 31, 2026. The model generates up to 30 seconds of audio and video in one pass and supports multi-round extension. A single generation can use up to 30 images, 10 video clips, and 10 audio clips as references, with timestamp-level editing for targeted audio and video changes. Seedance 2.5 began rolling out through Jimeng AI, Doubao Pro, and other platforms, while BytePlus ModelArk API access was announced as coming soon.

Why it matters

Seedance 2.5 extended single-pass audio-video generation to 30 seconds, increased multimodal reference capacity, and added stronger long-form storytelling, extension, and targeted editing capabilities.

94/100Global significance score. Regional effects are recorded only when the evidence supports a meaningful difference.

Access notes

The model is rolling out through Jimeng AI, Doubao Pro, and other platforms; BytePlus ModelArk API access is not yet generally available.