# Kling 3.0 Turbo API

Complete API reference for Kling 3.0 Turbo video generation models by Kuaishou.

## Model Variants

This API supports two model variants:

| Model | ID | Description |
|-------|-----|-------------|
| **Kling 3.0 Turbo Text to Video** | `kling-3.0-turbo-text-to-video` | Fast text-to-video generation |
| **Kling 3.0 Turbo Image to Video** | `kling-3.0-turbo-image-to-video` | Fast image-to-video animation |

## Quick Comparison

| Feature | Text to Video | Image to Video |
|---------|---------------|----------------|
| Input | Text prompt | Image + Text prompt |
| Duration Range | 3-15 seconds | 3-15 seconds |
| Resolution Options | 720p, 1080p | 720p, 1080p |
| Aspect Ratios | 16:9, 9:16, 1:1 | Not supported (source-driven) |
| Start Frame | Not supported | Required |

### Supported Aspect Ratios (Text to Video)

| Ratio | Description |
|-------|-------------|
| `16:9` | Landscape (widescreen) |
| `9:16` | Portrait (vertical) |
| `1:1` | Square |

## Kling 3.0 Turbo Text to Video

### Endpoint

```
POST /api/v1/video/task
```

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model_name` | string | Must be `"kling-3.0-turbo-text-to-video"` |
| `prompt` | string | Video generation prompt |
| `resolution` | string | Output resolution: `"720p"` or `"1080p"` |
| `duration` | number | Video duration in seconds (3-15) |

#### Optional

| Parameter | Type | Description |
|-----------|------|-------------|
| `aspect_ratio` | string | Video aspect ratio: `"16:9"`, `"9:16"`, or `"1:1"`. Defaults to `"16:9"` |
| `sound` | boolean | Generate ambient sound for the video |

### Example Request

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'kling-3.0-turbo-text-to-video',
    prompt: 'A girl sits on a train, looking out the window with a melancholic expression, cinematic lighting',
    aspect_ratio: '16:9',
    resolution: '720p',
    duration: 5,
    sound: true
  })
});

const { data } = await response.json();
const taskId = data.task_id;
```

## Kling 3.0 Turbo Image to Video

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model_name` | string | Must be `"kling-3.0-turbo-image-to-video"` |
| `prompt` | string | Motion and scene prompt |
| `image_url` | string | First-frame image URL |
| `resolution` | string | Output resolution: `"720p"` or `"1080p"` |
| `duration` | number | Video duration in seconds (3-15) |

#### Optional

| Parameter | Type | Description |
|-----------|------|-------------|
| `sound` | boolean | Generate ambient sound for the video |

### Example Request

```javascript
{
  model_name: 'kling-3.0-turbo-image-to-video',
  prompt: 'The character slowly turns her head and looks out the window, subtle camera movement',
  image_url: 'https://example.com/test-first-frame.png',
  resolution: '720p',
  duration: 5,
  sound: true
}
```

## Response Format

Submit response:

```json
{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "{task_id}",
    "response_url": "https://api.flaq.ai/api/v1/video/{task_id}",
    "task_status": "submitted"
  }
}
```

Poll with `GET /api/v1/video/{task_id}`. Task statuses: `submitted`, `processing`, `succeed`, `failed`.

## Best Practices

- Keep prompts focused on motion, camera behavior, and scene atmosphere.
- For image-to-video, use a clean first-frame image with a clear subject.
- Use shorter durations for faster iteration, then increase duration for final renders.