# Kling v3 Turbo Standard Image to Video - Core.Today AI API

> Kling 3.0 Turbo Standard image-to-video via Fal.AI. Animates a first-frame image into 720p video with native audio — quick, affordable image-driven motion with optional multi-shot storyboards, 3-15 seconds.

- **Provider**: Kuaishou
- **Model ID**: fal-ai/kling-video/v3/turbo/standard/image-to-video
- **Category**: Video Generation
- **Credits**: 1300 per 5s 720p video with audio — billed per second, 260/s; multi_prompt requests billed as 15s
- **Speed**: Fast
- **Quality**: Standard

## Features
- Turbo speed at 720p with native audio included in the price
- Animates a first-frame image; output follows the image's aspect ratio
- Multi-shot storyboards: up to 6 shots, each with its own prompt and duration
- Affordable 720p tier for fast iteration
- 3-15 second output, billed per second

## Use Cases
- Bringing product shots and portraits to life
- Social short-form clips from a single still
- Talking-character clips with native audio
- Multi-shot mini stories from one keyframe

## 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
- **image_url**: string - First-frame image. jpg/jpeg/png, max 50MB, min 300px per side, aspect ratio 1:2.5 to 2.5:1

### Optional
- **prompt**: string - Optional text prompt describing the motion (keep under 2500 characters). Mutually exclusive with multi_prompt
- **duration**: string (default: 5) - Video length in seconds (3-15). Billed per second. Ignored when multi_prompt is used
  Options: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
- **multi_prompt**: array - Multi-shot storyboard: 1-6 shots of {prompt, duration}, totaling at most 15s. Mutually exclusive with prompt. Billed at the 15-second maximum regardless of the shot total
- **enable_safety_checker**: boolean (default: true) - Enable the safety checker

## Examples

### Single Shot
One prompt, 5-second clip
```json
{
  "model": "fal-ai/kling-video/v3/turbo/standard/image-to-video",
  "input": {
    "prompt": "He sways gently into the note, cheeks pressing, sweat glistening, smoke drifting through the warm light. The camera eases in slowly. Photorealistic, soulful, moody.",
    "image_url": "https://v3b.fal.media/files/b/0a9ea079/Y8Pn9lNLLpGQtECV5LgX3_d6533d99ec5f45d88923f8e2bc41ad8d.png",
    "duration": "5"
  }
}
```

### Multi-Shot Storyboard
Several shots with their own prompts (billed at 15s)
```json
{
  "model": "fal-ai/kling-video/v3/turbo/standard/image-to-video",
  "input": {
    "image_url": "https://example.com/keyframe.png",
    "multi_prompt": [
      {
        "prompt": "Wide shot: she steps out of the cafe into the morning street",
        "duration": "5"
      },
      {
        "prompt": "Close-up: she smiles and raises her coffee cup to the camera",
        "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
- duration is a string enum ("3"-"15"), not a number
- multi_prompt requests are billed as the 15-second maximum — use them when your storyboard is close to 15s
- Native audio is included in the price — describe dialogue and sound in the prompt
- Use the Pro tier for 1080p finals once the motion looks right at 720p

## Documentation
https://fal.ai/models/fal-ai/kling-video/v3/turbo/standard/image-to-video