omnihuman-2-0defaultOmniHuman 2.0 API — how to connect and pay
OmniHuman 2.0 — a talking person from one photo and a voice track: lips, facial expression, gestures and body motion follow your audio. Requires image_url and audio_url (wav or mp3, 4 seconds to 5 minutes); the clip is as long as the audio. Optional prompt guides the scene and camera. 720p. Priced per second of output video.
Channel comparison
last 7 days
| Channel | Price |
|---|---|
Pixel omnihuman-2-0default | from ≈ $0.09 / s |
Build the result you need
omnihuman-2-0This model only publishes its minimum price in the catalog.
What is OmniHuman 2.0
OmniHuman 2.0 — a talking person from one photo and a voice track: lips, facial expression, gestures and body motion follow your audio. Requires image_url and audio_url (wav or mp3, 4 seconds to 5 minutes); the clip is as long as the audio. Optional prompt guides the scene and camera. 720p. Priced per second of output video.
Contract at a glance
- Input
- image, audio, text
- Output
- video
- Mode
- async (job + polling)
- Status polling
- every 3 s · up to 600 s
Strengths
- Pricing: per second
- Inputs: image, audio, text
- One API key for media generation
Where it is used
- Social media clips
- Promos and title sequences
- Still-image animation
- Storyboards and animatics
API contract
Generation runs asynchronously: create a job, then poll its status until completion.
- Create job
- POST /api/media/generate
- Check status
- GET /api/media/jobs/{jobId}
- Input
- image, audio, text
- Output
- video
- Polling
- every 3 s · up to 600 s
- Authentication
- Authorization: Bearer sk-pv-…
Example request
Pass your key in the Bearer header. The API returns jobId for polling the status.
curl -sS https://getvibeapi.com/api/media/generate \
-H "Authorization: Bearer $GETVIBE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary '{"model":"omnihuman-2-0","opts":{"image_url":"https://example.com/image_url.png","audio_url":"https://example.com/audio_url.mp3","enable_watermark":false}}'JavaScript
const response = await fetch('https://getvibeapi.com/api/media/generate', {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.GETVIBE_API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "omnihuman-2-0",
"opts": {
"image_url": "https://example.com/image_url.png",
"audio_url": "https://example.com/audio_url.mp3",
"enable_watermark": false
}
}),
});
if (!response.ok) throw new Error(`GetVibe API: ${response.status}`);
const { jobId } = await response.json();
console.log(jobId);API request parameters
Parameters for requests to OmniHuman 2.0 via the GetVibe API.
promptreq.image_urlaudio_urlenable_watermarkimage_file_idimage_base64audio_file_idaudio_base64| Parameter | Type | Values | Default | Price |
|---|---|---|---|---|
promptreq. | text | text description | required | — |
image_url | URL | Public image URL | — | — |
audio_url | URL | Public audio URL | — | — |
enable_watermark | yes/no | Yes · No (default) | No | Included in the base price |
image_file_id | text | Alternative to image_url: the id of your own file from POST /v1/files (file-pv-…) | — | Included in the base price |
image_base64 | text | Alternative to image_url: the file inline, as base64 or a data: URI | — | Included in the base price |
audio_file_id | text | Alternative to audio_url: the id of your own file from POST /v1/files (file-pv-…) | — | Included in the base price |
audio_base64 | text | Alternative to audio_url: the file inline, as base64 or a data: URI | — | Included in the base price |
Request: POST https://getvibeapi.com/api/media/generate. Prices in USD.
Price of OmniHuman 2.0
The cost of OmniHuman 2.0: from $0.09 per second. The price is calculated dynamically at the current exchange rate, and the final charge is shown in the API response (priceRub). Payment in USD, no subscriptions.
What a default request costs
With no parameters sent, the request uses these values: Watermark — No. That request costs $0.09.
Channels and prices for every parameter combination
For every channel, the price of every parameter combination. It is exactly the amount a successful generation is charged, and the same figure as in the machine-readable table linked below.
Pixelomnihuman-2-0some cells are estimates (≈)
| Price | Price |
|---|---|
| Pixel | ≈ $0.09 / s |
Price per second of the generated video. The charge is this price × the actual length of the result.
≈ This price is per second. The length is set by your source file (audio or video), so the charge is this price × its seconds.
Every combination as JSON: /api/media/price-table?model=omnihuman-2-0
README
The machine-readable contract for OmniHuman 2.0 contains the request schema, operations, limits, polling and response examples.
# OmniHuman 2.0
Public model: omnihuman-2-0
Create job: POST /api/media/generate
Check status: GET /api/media/jobs/{jobId}
## Input parameters
- `prompt` (text): text description; default: required
- `image_url` (URL): Public image URL; default: —
- `audio_url` (URL): Public audio URL; default: —
- `enable_watermark` (yes/no): Yes · No (default); default: No
- `image_file_id` (text): Alternative to image_url: the id of your own file from POST /v1/files (file-pv-…); default: —
- `image_base64` (text): Alternative to image_url: the file inline, as base64 or a data: URI; default: —
- `audio_file_id` (text): Alternative to audio_url: the id of your own file from POST /v1/files (file-pv-…); default: —
- `audio_base64` (text): Alternative to audio_url: the file inline, as base64 or a data: URI; default: —
## Public variants
- `omnihuman-2-0`: PixelFAQ about the OmniHuman 2.0 API
How much does OmniHuman 2.0 cost?
The price of OmniHuman 2.0: from $0.09 per second. The price is calculated dynamically at the current exchange rate.
Is it compatible with the OpenAI SDK?
Yes, the API is fully OpenAI-compatible. Just change base_url to https://getvibeapi.com/v1 and set your key — the rest of the code stays the same.