Skip to main content
POST
Create a video generation task

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
model
enum<string>
required

model ID

Available options:
seedance-2.0
Example:

"seedance-2.0"

content
object[]
required

Input content array. Supports combinations of text, image, video, and audio:

  • Text
  • Text (optional) + image
  • Text (optional) + video
  • Text (optional) + image + audio
  • Text (optional) + image + video
  • Text (optional) + video + audio
  • Text (optional) + image + video + audio
Example:
generate_audio
boolean
default:true

Controls whether the generated video includes synchronized audio.

  • true — automatically generate speech, sound effects, and background music
  • false — silent video
resolution
enum<string>
default:720p

Output video resolution.

Available options:
480p,
720p,
1080p
ratio
enum<string>
default:adaptive

Output aspect ratio. adaptive automatically chooses the best ratio from the input.

Available options:
16:9,
4:3,
1:1,
3:4,
9:16,
21:9,
adaptive
duration
integer
default:5

Video duration in seconds. Integer, 4–15.

Required range: 4 <= x <= 15
tools
object[]

Tools the model can call. Currently supports web search (text-to-video only).

watermark
boolean
default:false

Whether to add a watermark.

return_last_frame
boolean
default:false

Whether to return the last frame of the generated video.

Response

Video generation task created

id
string

Task ID

Example:

"cgt-20260312231129-7db6s"

task_id
string

Task ID (same as id)

Example:

"cgt-20260312231129-7db6s"

object
string
Example:

"video"

model
string
Example:

"seedance-2.0"

status
string

Initially empty

Example:

""

progress
integer
Example:

0

created_at
integer

Unix timestamp

Example:

1773328294