Skip to main content
POST
Submit a OmniHuman 2.0 video task
  1. After submission, a task_id will be returned. If you provided a callback_url, when the task status becomes finished or failed, a POST request will be sent to the callback_url.
  2. Regardless of whether callback_url is provided, you can retrieve the response result through the unified Query Task Status endpoint.
OmniHuman 2.0 creates an audio-driven character video from one image and a driving audio file. Use an optional prompt to guide the character’s motion and performance.

Models

  • omnihuman-2.0 — Audio-driven character animation

Features

  • Animate one character image with a driving audio track.
  • Guide motion and performance with an optional text prompt.

Required parameters

  • image_urls (array of strings): Exactly one character image URL.
  • audio_url (string): Driving audio URL. Audio must be 4–300 seconds long and no larger than 15 MB.

Optional parameters

  • prompt (string): Optional instructions for motion and performance.

Examples

The request example uses only the required image_urls and audio_url fields. Add prompt inside input when performance instructions are needed.

Notes

  • Put all generation parameters inside input.
  • Images must use publicly accessible HTTP or HTTPS URLs.
  • audio_url must be a publicly accessible HTTP or HTTPS URL.
  • A separate duration parameter is not accepted; the driving audio determines the requested performance length.

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

Public model identifier.

Available options:
omnihuman-2.0
input
object
required
callback_url
string<uri>

Optional webhook URL for task completion or failure notifications.

Response

Task submitted successfully

code
integer
required
Example:

200

data
object
required