curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "gemini-omni-1.1-flash",
"callback_url": "https://your-domain.com/callback",
"input": {
"prompt": "A cinematic night city with neon reflections and a slow camera push-in",
"resolution": "720p",
"duration": 8,
"aspect_ratio": "16:9"
}
}
'
{
"code": 200,
"data": {
"task_id": "task-unified-1757165031-uyujaw3d",
"status": "not_started",
"created_time": "2023-11-07T05:31:56Z"
},
"message": "success"
}Google
Gemini Omni 1.1 Flash
The Gemini Omni 1.1 Flash API generates 4–10 second videos from text, one or two keyframes, up to seven reference images, or one 3–10 second reference video at 360p to 4K.
POST
/
api
/
generate
/
submit
curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "gemini-omni-1.1-flash",
"callback_url": "https://your-domain.com/callback",
"input": {
"prompt": "A cinematic night city with neon reflections and a slow camera push-in",
"resolution": "720p",
"duration": 8,
"aspect_ratio": "16:9"
}
}
'
{
"code": 200,
"data": {
"task_id": "task-unified-1757165031-uyujaw3d",
"status": "not_started",
"created_time": "2023-11-07T05:31:56Z"
},
"message": "success"
}- After submission, a
task_idwill be returned. If you provided acallback_url, when the task status becomesfinishedorfailed, a POST request will be sent to thecallback_url. - Regardless of whether
callback_urlis provided, you can retrieve the result through the unified Query Task Status endpoint.
gemini-omni-1.1-flash generates videos from a text prompt, optional first and last frames, ordinary reference images, or one reference video.
Models
- gemini-omni-1.1-flash - Text-to-video, first/last-frame generation, reference image generation, and reference-video generation
Input modes
- Text to video: Send
promptand optional generation settings - First/last frame video: Send one or two images in
image_urls - Reference image video: Send up to seven images in
reference_image_urls - Reference video: Send one video from three to ten seconds in
reference_video_urls, optionally together with up to five reference images
Required parameters
- prompt: Text prompt describing the scene, motion, style, camera behavior, and other generation instructions
Optional parameters
- image_urls: First-frame and optional last-frame image URL array. At most
2images are allowed - reference_image_urls: Ordinary reference image URL array. At most
7images are allowed, or5when a reference video is also provided - reference_video_urls: Reference video URL array. At most
1video is allowed and its duration must be from3to10seconds, inclusive - resolution:
360p,720p,1080p, or4k. Default is720p - duration:
4,6,8, or10seconds. Default is8. This field does not affect output duration when a reference video is provided - aspect_ratio:
16:9or9:16. Default is16:9 - callback_url: Optional webhook URL for completion notifications
Examples
Text to Video
{
"model": "gemini-omni-1.1-flash",
"callback_url": "https://your-domain.com/callback",
"input": {
"prompt": "A cinematic night city with neon reflections, a slow camera push-in, and a character walking into frame",
"resolution": "720p",
"duration": 8,
"aspect_ratio": "16:9"
}
}
First and Last Frames
{
"model": "gemini-omni-1.1-flash",
"input": {
"prompt": "Create a smooth cinematic transition between the opening and closing frames",
"image_urls": [
"https://example.com/first-frame.webp",
"https://example.com/last-frame.webp"
],
"resolution": "1080p",
"duration": 8,
"aspect_ratio": "16:9"
}
}
Reference Images
{
"model": "gemini-omni-1.1-flash",
"input": {
"prompt": "Use the product and environment references to create a polished studio campaign video",
"reference_image_urls": [
"https://example.com/product.webp",
"https://example.com/environment.webp"
],
"resolution": "720p",
"duration": 8,
"aspect_ratio": "9:16"
}
}
Reference Video
{
"model": "gemini-omni-1.1-flash",
"input": {
"prompt": "Follow the motion of the reference video while applying the visual style of the image",
"reference_image_urls": ["https://example.com/style.webp"],
"reference_video_urls": ["https://example.com/reference.mp4"],
"resolution": "720p",
"aspect_ratio": "16:9"
}
}
Notes
image_urlscannot be combined withreference_image_urlsorreference_video_urls- Use public HTTPS media URLs, or upload files through the playground before submitting
- The response returns a
task_id; query task status to retrieve generated video files
Authorizations
All API endpoints require Bearer Token authentication
Get your API Key:
Visit the API Key Management Page to get your API Key
Add it to the request header:
Authorization: Bearer YOUR_API_KEY
Body
application/json
