ByteDance
OmniHuman 1.5
The person in a photo speaks, sings or raps your recording, with the face, hands and body moving to it. Billed by the length of the recording. On Leap, it sits beside 130 other models in one studio.
- Talking avatar
- Lip-sync
- Up to 1080p
- Start free, no card
- Every top model, one account
- Pay per run, priced before it starts
- 01Describe what you want to see
- 02See the exact price, then press go
- 03Keep it in your library, or take it further
Start with an idea
Bring a photo to OmniHuman 1.5
OmniHuman 1.5 works on a picture you already have. Open it in the studio, add your photo, and see the result in seconds.
Side by side
More video models on Leap
Questions
OmniHuman 1.5 on Leap, answered.
- Is this the real OmniHuman 1.5?
- Yes. Leap sends your request to ByteDance's model through its provider and gives you back what it makes. Switch to any other model in the same studio when an idea needs it.
- What does it cost?
- In dollars, per run: the provider's list price plus 10%. You see the exact price before every run, a run that fails costs nothing, and there is no subscription. Every model's price is on the pricing page.
- Do I need a ByteDance account?
- No. One Leap account and one balance run OmniHuman 1.5 and every other model, in the studio, through the API and from your agents.
- What happens to what I make?
- It stays in your library while your account is active, ready to use anywhere.
Your idea, OmniHuman 1.5.
Start free, no card. Every run shows its price before it starts.
Make it with OmniHuman 1.5For developers
Run OmniHuman 1.5 from code
- Model ID
- bytedance/omnihuman-1.5
- Makes
- Video
- Pricing
- Per run, quoted first: POST /v1/quotes
Inputs
What the model takes. Leave out anything with a default.
Promptprompt
Text, up to 4,000 characters
Audioaudio_file
An image, requiredThe recording to use: an uploaded file, by ID. Up to 30 seconds.
Charactercharacter_image
An image, requiredAn image of the person or character: an uploaded file, by ID.
Maskmask_image
An imageWhere the model acts, in white on black, the size of the image: an uploaded file, by ID.
Resolutionresolution
720p, 1080p. Default: 1080p
Turbo Modesettings.turbo_mode
On or off. Default: offGenerate a video at a faster rate with a slight quality trade-off.
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result. Agents can call it through the MCP server at mcp.tryleap.ai.
curl https://api.tryleap.ai/v1/generations \ -H "x-api-key: $LEAP_API_KEY" \ -H "content-type: application/json" \ -H "prefer: wait=60" \ -d '{ "model": "bytedance/omnihuman-1.5", "input": { "character_image": "file_...", "audio_file": "file_..." } }'