LiveGemini Omni 1.1 Flash is live: image references, 4K output and scene extensions up to 40 seconds. Try it now →
The Gemini Omni
API.
Generate AI video programmatically with Google's Gemini Omni 1.1 Flash model. One REST call turns a prompt or image into a finished MP4 with native sound.
One endpoint for AI video generation.
Text-to-video & image-to-video
Send a prompt, an image, or both. The Omni API runs the same Gemini Omni 1.1 Flash model as the studio, with native sound, image references and up to 3 video clips per request.
Async, webhook-driven
Submit a job and get an ID back instantly. Poll the status endpoint or register a webhook, we call you when the render is ready so you never hold a request open.
Predictable, usage-based pricing
You pay per generated second of video, billed from the credits on your plan. No per-seat fees, no minimums, scale from a prototype to production on the same key.
Generate a video in one call.
curl https://omnirender.ai/api/v1/generate \
-H "Authorization: Bearer $OMNI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-omni-1.1-flash",
"prompt": "A cinematic dolly shot of a neon-lit alley at night, rain, steam",
"duration": 8,
"aspect_ratio": "16:9",
"resolution": "1080p"
}'The call returns a job ID. Poll the status endpoint or register a webhook, and download the finished MP4 with sound when the render completes.
From key to rendered clip.
- 01
Get an API key
Create an account and generate a key from your dashboard. Every paid plan includes API access.
- 02
Submit a generation job
POST a prompt, references and options to the generate endpoint. You get a job ID back immediately.
- 03
Receive the finished video
Poll the job or listen on your webhook. When it's done, download the MP4 with sound from the returned URL.
Usage-based, billed from your plan credits.
API access is included on every paid plan, starting at $14/month. You pay per second of generated video, no per-seat fees, no minimums. See full Omni pricing.
Omni API FAQ.
What is the Omni API?+
The Omni API is a REST endpoint that generates AI video programmatically using Google's Gemini Omni 1.1 Flash model. You send a prompt and optional references, and receive a rendered MP4 with native sound, the same output as the OmniRender app, driven from your own code.
How much does the Omni API cost?+
API usage is billed from the credits included in your plan (from $14/month), so you effectively pay per second of generated video, from 360p drafts to 4K. There are no per-seat fees or minimums, and the same key works from prototype to production.
How do I get access to the Omni API?+
Create an account, choose any paid plan, and generate an API key from your dashboard. Authenticate requests with a bearer token and you're ready to submit generation jobs.
Does the Omni API support image-to-video?+
Yes. You can send text prompts, image references, first/last frames and up to 3 short video references in a single request for text-to-video, image-to-video and reference-driven generation, plus Edit and Extend operations on finished clips.
Is the API synchronous or asynchronous?+
It's asynchronous. Submitting a job returns an ID immediately; you then poll the status endpoint or register a webhook, so a slow render never blocks your request.
Build with the Omni API.
Grab a key and ship AI video generation into your product today.
Get an API key