video

OmniHuman 1.5 - Create human animation

Generate animated video of a human figure driven by audio using OmniHuman 1.5 model (ByteDance). Supports natural head movements, facial expressions, and body motion synchronized to audio input.

post/v1/ai/video/omni-human-1-5

Request

  • Base URL: https://api.magnific.com
  • URL: https://api.magnific.com/v1/ai/video/omni-human-1-5
  • Auth: API key in header x-magnific-api-key

Request body

webhook_urlstring uri

Webhook URL to notify the user when the task is completed

image_urlstring uri required

URL of the human figure image to animate. Image must be publicly accessible, contain a visible human figure, and be in jpg, jpeg, png, or webp format.

audio_urlstring uri required

URL of the audio file that drives the animation. Must be publicly accessible. Supported formats: MP3, OGG, WAV, M4A, AAC. Duration limits: 720p max 60 seconds, 1080p max 30 seconds.

promptstring

Optional text guidance for the generation. Can describe desired motion, expression, or style.

turbo_modeboolean

Enable faster generation with potentially reduced quality

resolution'720p' | '1080p'

Video resolution. 1080p allows max 30 seconds audio, 720p allows max 60 seconds audio.

Example request

{
  "image_url": "https://example.com/human-figure.jpg",
  "audio_url": "https://example.com/audio.mp3",
  "prompt": "A person speaking naturally with subtle head movements"
}

Response

OK - The task exists and the status is returned

Example response

{
  "data": {
    "generated": [
      "https://openapi-generator.tech",
      "https://openapi-generator.tech"
    ],
    "task_id": "046b6c7f-0b8a-43b9-b35d-6489e6daee91",
    "status": "CREATED"
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.