curl --request POST \
--url https://api.omniall.ai/v1/videos \
--header 'Authorization: <authorization>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "omni-fast",
"prompt": "Ocean waves gently rolling onto a beach at golden hour, cinematic, warm sunlight",
"seconds": "8",
"aspect_ratio": "16:9",
"resolution": "720p"
}
'{
"id": "task_xxxxxxxx",
"task_id": "task_xxxxxxxx",
"object": "video",
"model": "omni-fast",
"status": "queued",
"progress": 0,
"created_at": 1775025000
}Google Omni
Create video
Create a Google Omni video task.
Path: POST https://api.omniall.ai/v1/videos
Same endpoint, different use cases: text-to-video · reference images · first/last frame · video reference (omni-fast-v2v).
Auth: Authorization: Bearer sk-...
POST
/
v1
/
videos
curl --request POST \
--url https://api.omniall.ai/v1/videos \
--header 'Authorization: <authorization>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "omni-fast",
"prompt": "Ocean waves gently rolling onto a beach at golden hour, cinematic, warm sunlight",
"seconds": "8",
"aspect_ratio": "16:9",
"resolution": "720p"
}
'{
"id": "task_xxxxxxxx",
"task_id": "task_xxxxxxxx",
"object": "video",
"model": "omni-fast",
"status": "queued",
"progress": 0,
"created_at": 1775025000
}Headers
Example:
"Bearer sk-..."
Body
application/json
omni-fast or omni-fast-v2v (video reference).
Example:
"omni-fast"
Text prompt (motion / camera / subject).
First-frame image URL or base64. Required with last_image_url.
Last-frame image URL or base64. Must use with first_image_url.
Reference video (MP4 URL or data URI). Aliases: video_url, input_video.
Duration seconds, suggested 4–30. Example "8".
e.g. 16:9, 9:16.
e.g. 720p, 1080p, 2k, 4k.
Up to 5 reference images (URL or base64).
Maximum array length:
5