Video
Bytedance Omnihuman V1.5
Animate a person in an image with a supplied audio recording.
- Image to video
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Bytedance Omnihuman V1.5. Review your own result before publishing.
A starting point.
Build a speaking or performing character clip from a clear figure and matching audio.
Before you publish.
Compare mouth timing, gestures and face identity; listen for cut-off speech at the end.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Provide image_url and audio_url. With multiple people, optional mask_url uses white regions to identify the speaker.
Choose resolution: audio must be under 30 seconds at 1080p or under 60 seconds at 720p. turbo_mode trades some quality for faster inference.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for bytedance/omnihuman/v1.5. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
audio_url | Text | Required | — |
image_url | Text | Required | — |
mask_url | Text | Optional | — |
prompt | Text | Optional | — |
resolution | Text | Optional | 720p, 1080p |
turbo_mode | On/off | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Bytedance Omnihuman V1.5 through the API.
Start with this model ID for the endpoint featured on this page:
bytedance/omnihuman/v1.5
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.