Developer Docs
OmniVideo API Documentation
Create Gemini Omni video tasks with /api/generate, then poll /api/status until the task completes.
Authentication
Send your dashboard API key as a Bearer token.
Authorization: Bearer YOUR_API_KEY Content-Type: application/json
Generate Video
POST https://omnivideoapi.com/api/generate
{
"model": "gemini-omni/video",
"input": {
"prompt": "A cinematic product reveal shot with smooth camera motion",
"mode": "std",
"aspect_ratio": "16:9",
"duration": "5",
"sound": true
}
}Supported Parameters
| Parameter | Values | Description |
|---|---|---|
| model | gemini-omni/video | Public model identifier. |
| input.prompt | string | Required prompt for single-shot generation. |
| input.mode | std, pro | Generation mode. Defaults to std. |
| input.aspect_ratio | 16:9, 9:16, 1:1 | Output framing. |
| input.duration | 3-15 seconds | Clip duration. |
| input.sound | true, false | Request generated audio. |
| input.image_urls | string[] | Optional public image URLs for image-to-video. |
Check Status
GET https://omnivideoapi.com/api/status?task_id=task_abc123
Poll every 5 to 10 seconds. A successful task returns status SUCCESS and result URLs in the response payload.