Skip to main content

Try OmniHuman 2.0 in the Workbench

Run this model interactively, tune parameters, and compare outputs.
Model ID: bytedance-omnihuman-2-0 OmniHuman 2.0 is ByteDance’s audio-driven human animation model: it turns a single image and a voice track into a video of the subject speaking or singing, with lip sync, facial expression, and body gesture that follow the rhythm and meaning of the audio. It works from any framing, from close-up portraits to full-body shots, and on photographs as well as illustrated, 3D-rendered, and non-human characters. Images with several people produce multi-person scenes. An optional text prompt directs camera movement, specific actions, and added elements that are not in the source image; prompts can be written in English, Chinese, Japanese, Korean, Mexican Spanish, or Indonesian. The video runs as long as the audio, from 4 seconds up to 5 minutes, and is billed per second of output. Output is 720p-class with its aspect ratio following the input image. Audio must be WAV or MP3 under 15 MB; the image must be between 300 and 6000 pixels per side with an aspect ratio between 0.4 and 2.5. *Quantization refers to whether the served weights are reduced-precision.

Example request

Use the Workbench as a request builder: configure parameters for this model in the UI, then open the API tab to copy the exact cURL or Python call.
This blocks until the video is ready (typically 5-15 minutes). Prefer Async or Async with SSE for anything beyond quick experimentation.See the video generation reference for more details.

Fetch model details

The models endpoint returns the full model object, including its json_request_schema.

Request parameters

Required parameters

Optional parameters