2 models · video
OmniHuman API
OmniHuman is a family of AI video models made by ByteDance. varg runs 2 of them on one API key: OmniHuman v2 and OmniHuman v1.5. Between them they cover lip sync and image to video; they return video.
- Price
- From $2.00 per run OmniHuman v1.5
- OmniHuman v2
- From $2.80 per run
- Made by
- ByteDance
- Flagship id
omnihuman_v2
Every OmniHuman model runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.
curl -X POST https://api.varg.ai/v2/tools/video/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "omnihuman_v2",
"prompt": "a person speaking confidently",
"files": [
{
"url": "https://example.com/voice.mp3"
},
{
"url": "https://example.com/portrait.png"
}
]
}'OmniHuman models and prices
OmniHuman on varg starts from $2.00 per run (OmniHuman v1.5). Prices are in US dollars and are the provider's own, with no markup. A "from" price is the cheapest request the catalog states for that model; each model's page has every rate and input. The descriptions are the catalog's own, shortened.
| Model | Catalog description | Takes | Price | Typical time |
|---|---|---|---|---|
OmniHuman v2omnihuman_ | OmniHuman v2 by ByteDance. A talking video from one image and an audio track. | Lip sync, Image to video | From $2.80 per run | ~3 min |
OmniHuman v1.5omnihuman_ | ByteDance OmniHuman. Full-body animation from image + audio. | Lip sync | From $2.00 per run | ~2 min |
Call the OmniHuman API
The call below runs OmniHuman v2. For another OmniHuman model, put its id from the table in "model"; the rest of the request keeps its shape.
REST
POST https://api.varg.ai/v2/tools/video/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away; poll GET /v2/jobs/{id} until its status is completed, then read output.outputs[0].url.
curl -X POST https://api.varg.ai/v2/tools/video/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "omnihuman_v2",
"prompt": "a person speaking confidently",
"files": [
{
"url": "https://example.com/voice.mp3"
},
{
"url": "https://example.com/portrait.png"
}
]
}'From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs OmniHuman v2 with call_tool. Sign in with varg, no API key to paste. How to connect it
claude mcp add --transport http varg https://mcp.varg.ai/mcp{
"tool": "video",
"input": {
"model": "omnihuman_v2",
"prompt": "a person speaking confidently",
"files": [
{
"url": "https://example.com/voice.mp3"
},
{
"url": "https://example.com/portrait.png"
}
]
},
"wait": true
}From a terminal (CLI)
vargai is the varg command line: every tool of the MCP server is a command. Install and log in
curl -fsSL https://varg.ai/install | sh
vargai call_tool --tool video '{"model":"omnihuman_v2","prompt":"a person speaking confidently","files":[{"url":"https://example.com/voice.mp3"},{"url":"https://example.com/portrait.png"}]}'How billing works
Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. varg's fee is on the top-up, not on the run: 5.5% of the credits you buy ($0.80 at the least), or 8% for a team workspace. Pricing
How to use OmniHuman
Step-by-step pages on varg how to.
OmniHuman API: questions
- How much does the OmniHuman API cost on varg?
- The lowest price the catalog states in the OmniHuman family is from $2.00 per run, on OmniHuman v1.5. Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
- Which OmniHuman models are on varg?
- 2: OmniHuman v2 (from $2.80 per run) and OmniHuman v1.5 (from $2.00 per run). Each has its own page with the parameters and a call to copy.
- Which OmniHuman models take an image?
- 1 of the 2: OmniHuman v2. The catalog lists image to video for it; pass the image as a URL in "files".
- How long do OmniHuman requests take?
- Typically from about 2 min (OmniHuman v1.5) to about 3 min (OmniHuman v2), by the catalog's estimates for each model's fastest route. The API answers at once with a job id, so nothing waits on an open connection while it runs.
- How do I call the OmniHuman API?
- Send POST https://api.varg.ai/v2/tools/video/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model", for example "model": "omnihuman_v2". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
- Can I use OmniHuman from Claude, ChatGPT or Cursor?
- Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs a model with call_tool, passing tool "video" and the model id, for example "model": "omnihuman_v2".
More model APIs
Same API key, same request shape: change the model string to switch.
For AI agents: each model above has its full spec as Markdown at varg.ai/models/omnihuman_v2.md (swap the id), and every model is listed in varg.ai/models/llms.txt.