# Google Gemini Omni Flash 1.1 Text to Video - Core.Today AI API

> Google Gemini Omni Flash 1.1 text-to-video via Fal.AI. Generates 3-10 second video with synchronized native audio from a text prompt, grounded in Gemini's real-world knowledge and physics understanding, with cinematic camera control in natural language — 16:9 or 9:16 at 360p to 4K.

- **Provider**: Google
- **Model ID**: google/gemini-omni-flash/v1.1/text-to-video
- **Category**: Video Generation
- **Credits**: 1860 per 8s 720p video — billed per second (360p 70/s, 720p 233/s, 1080p 349/s, 4k 698/s)
- **Speed**: Fast
- **Quality**: High

## Features
- Synchronized native audio (dialogue, music, ambience) from the prompt
- Physics-aware motion grounded in Gemini's world knowledge
- Cinematic camera control in natural language
- Four resolution tiers from 360p to 4K, billed per second

## Use Cases
- Short ads and social clips with sound
- Cinematic establishing shots and b-roll
- Fast 360p concept previews before a high-resolution render
- Explainer scenes that need plausible real-world physics

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - The text prompt describing the video. Describe scene, camera movement, lighting, mood and audio.

### Optional
- **duration**: integer (default: 8) - The duration of the generated video in seconds (3-10), billed per second.
- **aspect_ratio**: string (default: 16:9) - The aspect ratio of the generated video.
  Options: 16:9, 9:16
- **resolution**: string (default: 720p) - The resolution of the generated video. Higher resolutions cost more per second.
  Options: 360p, 720p, 1080p, 4k

## Examples

### Lighthouse at dusk
A cinematic wide shot at the default 720p and 8 seconds.
```json
{
  "model": "google/gemini-omni-flash/v1.1/text-to-video",
  "input": {
    "prompt": "A cinematic wide shot of a lighthouse on a rocky cliff at dusk, waves crashing below, the beam sweeping across the dark sea.",
    "duration": 8,
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }
}
```

### Vertical street-food clip
A 5-second 9:16 clip with ambient sound at 1080p.
```json
{
  "model": "google/gemini-omni-flash/v1.1/text-to-video",
  "input": {
    "prompt": "Close-up of sizzling skewers on a night-market grill, smoke rising, vendors chatting in the background, handheld camera.",
    "duration": 5,
    "aspect_ratio": "9:16",
    "resolution": "1080p"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Describe audio (dialogue, music, ambience) directly in the prompt — it is generated with the video.
- Draft at 360p (70/s), then re-render the keeper at 720p, 1080p or 4k.
- Billing is duration x per-second rate, so shorter clips cost proportionally less.
- The same model is also available as google/gemini-omni-1.1 with editing and reference modes.

## Documentation
https://fal.ai/models/google/gemini-omni-flash/v1.1/text-to-video