OmniHuman 2.0 API reference
Check OmniHuman 2.0 availability, inputs, parameters, file requirements, credit pricing, and request examples for Rivya Public API v1. Model ID: omnihuman-2-0.
omnihuman-2-0
file
Required for reference modes
Credit rate: 14 per second of input The final cost is rounded up to whole credits.
Video
METERED
300 characters
Request fields
Set model at the top level. Put model-specific controls and reference inputs in params, using the format documented for this model.
| Key | Type | Required | Default | Description |
|---|---|---|---|---|
| model | string | Yes | omnihuman-2-0 | Set model to omnihuman-2-0. |
| prompt | string | No | - | Maximum 300 characters for this model. |
| params | object | Yes | - | The model-specific params object. Use the documented keys and reference-file format for this model. |
| client_request_id | string | No | - | Optional ID for tracing this request in your system. It does not replace Idempotency-Key. |
Model parameters
| Key | Type | Required | Default | Range | Options | Description |
|---|---|---|---|---|---|---|
| enable_watermark | select | No | true | - | true, false | Add watermark |
Upload policy
Upload reference files through Files API first. Keep the original URLs, verified metadata, and tokens. Follow this model's request example: some models use params.referenceMediaItems, while others use different fields.
Image and audio: Upload 1 JPEG, PNG, or WebP image under 30 MB and 1 MP3 or WAV audio file under 15 MB. Audio must be 4–300 seconds.
2
image, audio
When duration verification is required, use duration_token from /api/v1/files as durationToken in the request. Keep any additional signed metadata this model requires.
| kind | Max size | MIME types |
|---|---|---|
| image | 30 MB | image/jpeg, image/png, image/webp |
| audio | 15 MB | audio/mpeg, audio/wav, audio/x-wav |
No runnable Public API example is shown for this model.
Reference-file request
{
"model": "omnihuman-2-0",
"params": {
"enable_watermark": "true",
"referenceMediaItems": [
{
"url": "https://cdn.example.com/reference-image.png",
"kind": "image",
"name": "reference-image.png",
"mimeType": "image/png",
"width": 1024,
"height": 1024,
"sizeBytes": 1048576,
"imageDimensionsToken": "image_dimensions_token_from_original_files_api_upload_response"
},
{
"url": "https://cdn.example.com/reference-audio.wav",
"kind": "audio",
"name": "reference-audio.wav",
"mimeType": "audio/wav",
"durationSeconds": 12,
"durationToken": "audio_duration_token_from_files_api",
"sizeBytes": 1048576
}
]
}
}Example response
An accepted generation request returns a task ID. Poll the status endpoint until the task succeeds or fails. A status request failure does not mean generation failed.
{
"id": "task_omnihuman_2_0_example",
"status": "queued",
"model": "omnihuman-2-0",
"reserved_credits": 56,
"final_credits": 0,
"settlement_status": "RESERVED",
"created_at": "2026-05-11T00:00:00.000Z",
"updated_at": "2026-05-11T00:00:00.000Z",
"result": null,
"error": null
}Common errors
validation_failed, insufficient_credits, idempotency_conflict, rate_limited, not_found
Some modes require Files API reference uploads.
