Skip to main content
POST
Seedance 2.5 T2V
seedance-2.5-t2v is the text-to-video mode model of ByteDance Seedance 2.5: 4 to 30 second clips with optional native audio. Confirm live rates on the models page.
string
required
Set to seedance-2.5-t2v.
string
required
Describe the subject, action, camera movement, lighting, and audio intent.
string
default:"10"
Output length: 4 to 30 seconds.
string
One of 21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive. adaptive follows the input image or video. Send it explicitly; do not send a pixel size.
string
default:"720p"
One of 480p, 720p. The price depends on the resolution.
boolean
default:"true"
Set to false for a silent video.

Request

The response returns a queued task id. Poll and download with the same model:
See the Video API workflow for polling intervals, webhooks, and failure handling.

Price examples

Media inputs must be public http or https URLs. Private network addresses and local files are rejected. Failed generations are not charged.