# Kling v3 Turbo Pro Text to Video - Core.Today AI API

> Kling 3.0 Turbo Pro text-to-video via Fal.AI. Generates high-quality 1080p video with native audio from a text prompt, with improved lip-sync and multi-shot storyboards, 3-15 seconds.

- **Provider**: Kuaishou
- **Model ID**: fal-ai/kling-video/v3/turbo/pro/text-to-video
- **Category**: Video Generation
- **Credits**: 1630 per 5s 1080p video with audio — billed per second, 326/s; multi_prompt requests billed as 15s
- **Speed**: Fast
- **Quality**: High

## Features
- Turbo speed at 1080p with native audio included in the price
- 16:9, 9:16, and 1:1 aspect ratios
- Multi-shot storyboards: up to 6 shots, each with its own prompt and duration
- Improved lip-sync for dialogue scenes
- 3-15 second output, billed per second

## Use Cases
- Social short-form videos from a text idea
- Dialogue scenes with lip-synced native audio
- Multi-shot mini stories in one request
- Fast concepting before a premium render

## 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

### Optional
- **prompt**: string - Text prompt for the video (keep under 2500 characters). Provide either prompt or 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
- **aspect_ratio**: string (default: 16:9) - Aspect ratio of the generated video
  Options: 16:9, 9:16, 1:1
- **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/pro/text-to-video",
  "input": {
    "prompt": "A jazz saxophonist sways gently into the note, cheeks pressing, sweat glistening, smoke drifting through the warm light. The camera eases in slowly. Photorealistic, soulful, moody.",
    "duration": "5",
    "aspect_ratio": "16:9"
  }
}
```

### Multi-Shot Storyboard
Several shots with their own prompts (billed at 15s)
```json
{
  "model": "fal-ai/kling-video/v3/turbo/pro/text-to-video",
  "input": {
    "multi_prompt": [
      {
        "prompt": "Wide shot of a lighthouse on a cliff at dusk, waves crashing",
        "duration": "5"
      },
      {
        "prompt": "The keeper climbs the spiral stairs holding a lantern",
        "duration": "5"
      },
      {
        "prompt": "The beam sweeps across the dark sea",
        "duration": "5"
      }
    ],
    "aspect_ratio": "16:9"
  }
}
```

## 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

## Documentation
https://fal.ai/models/fal-ai/kling-video/v3/turbo/pro/text-to-video