# Kling v2.6 - Core.Today AI API

> Kling 2.6 Pro: top-tier image-to-video with cinematic visuals, fluid motion, and native audio generation. Audio generation is enabled by default.

- **Provider**: Kuaishou
- **Model ID**: kwaivgi/kling-v2.6
- **Category**: Video Generation
- **Credits**: 1630 per 5s video with audio (default) — billed per second (no audio 163/s, with audio 326/s)
- **Speed**: Medium
- **Quality**: Ultra

## Features
- Cinematic visual quality with fluid, natural motion
- Native synchronized audio generation (enabled by default)
- 5 or 10 second duration options
- Text-to-video or image-to-video via start_image
- Negative prompt support to steer away from unwanted elements

## Use Cases
- Cinematic marketing or trailer-style shots
- Image-to-video animation of a key frame with synced ambient sound
- Short narrative clips with dialogue-adjacent sound design
- Silent, cost-optimized clips by explicitly disabling audio
- Vertical or square social clips via aspect_ratio

## 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 - Text prompt for video generation

### Optional
- **start_image**: string - First frame of the video
- **negative_prompt**: string - Things you do not want to see in the video
- **aspect_ratio**: string (default: 16:9) - Aspect ratio of the video. Ignored if start_image is provided
  Options: 16:9, 9:16, 1:1
- **duration**: integer (default: 5) - Duration of the video in seconds
  Options: 5, 10
- **generate_audio**: boolean (default: true) - Generate synchronized audio for the video (enabled by default — doubles the per-second price)

## Examples

### Cinematic Tracking Shot with Audio
Text-to-video with the default synchronized audio generation
```json
{
  "model": "kwaivgi/kling-v2.6",
  "input": {
    "prompt": "A cinematic, low-angle tracking shot follows a cyclist from behind as they weave through busy New York City traffic. The camera then smoothly orbits around to the front, capturing the cyclist's determined expression.",
    "duration": 5,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}
```

### Silent Clip (Cost-Optimized)
Explicitly disabling audio halves the per-second price
```json
{
  "model": "kwaivgi/kling-v2.6",
  "input": {
    "prompt": "A lighthouse beam sweeping across a foggy coastline at dusk, waves crashing below",
    "duration": 10,
    "aspect_ratio": "16:9",
    "generate_audio": false
  }
}
```

## 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
- generate_audio defaults to true — if you omit it, you are billed at the audio-on rate (210/s), so set it to false explicitly to save on silent clips
- Audio roughly doubles the price ($0.07/s → $0.14/s) — turn it off for silent or externally-scored footage
- duration only accepts 5 or 10 seconds
- start_image anchors the first frame; when provided, aspect_ratio is ignored in favor of the image's ratio

## Documentation
https://replicate.com/kwaivgi/kling-v2.6