# Google Gemini Omni Flash - Core.Today AI API

> Google Gemini Omni Flash text-to-video via Fal.AI. Generates a video directly from a descriptive text prompt — pacing and audio (dialogue, background music) are controlled in the prompt itself, in 16:9 or 9:16 at 3-10 second durations.

- **Provider**: Google
- **Model ID**: google/gemini-omni-flash
- **Category**: Video Generation
- **Credits**: 2320 per second
- **Speed**: Fast
- **Quality**: High

## Features
- Text-to-video generation from a single descriptive prompt
- Dialogue and background music controlled directly in the prompt text — no separate audio toggle
- 16:9 (landscape) or 9:16 (vertical) aspect ratios
- 3-10 second adjustable duration
- Fast, single-tier pricing with no resolution parameter to choose

## Use Cases
- Short social media clips with narrated dialogue
- Quick ad or product teaser videos from a text brief
- Vertical short-form content for Stories/Reels-style placements
- Storyboard or concept previews before committing to a full production shoot

## 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 you want to generate.

### Optional
- **aspect_ratio**: string (default: 16:9) - The aspect ratio of the generated video.
  Options: 16:9, 9:16
- **duration**: integer (default: 8) - The duration of the generated video, in seconds.

## Examples

### Cinematic landscape shot with ambient sound
Generate an 8-second landscape video from a purely descriptive prompt, including the implied ambient audio.
```json
{
  "model": "google/gemini-omni-flash",
  "input": {
    "prompt": "A cinematic wide shot of a lighthouse on a rocky cliff at dusk, waves crashing below, the beam slowly sweeping across the dark sea.",
    "aspect_ratio": "16:9",
    "duration": 8
  }
}
```

### Vertical clip with narrated dialogue
Generate a short vertical clip where a character's spoken dialogue is described directly in the prompt.
```json
{
  "model": "google/gemini-omni-flash",
  "input": {
    "prompt": "A barista behind a counter smiles at the camera and says, \"Your order's ready!\" as steam rises from a fresh cup, upbeat background music playing.",
    "aspect_ratio": "9:16",
    "duration": 5
  }
}
```

## 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 dialogue and music directly in the prompt — there's no separate audio toggle for this model.
- Keep the prompt focused on one clear scene and camera move; overly long prompts can dilute pacing over the short duration.
- Choose 9:16 for Stories/Reels-style placements and 16:9 for traditional video surfaces.
- Since there's no resolution parameter, tune output quality mainly through a well-specified, detailed prompt.

## Documentation
https://fal.ai/models/google/gemini-omni-flash