Kling VIDEO O3 Standard

Identifier for the type of task being performed

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

Video output type.

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

• `MP4`: Widely supported video container (H.264), recommended for general use.
• `WEBM`: Optimized for web delivery.
• `MOV`: QuickTime format, common in professional workflows (Apple ecosystem).

Compression quality of the output. Higher values preserve quality but increase file size.

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Determines how the API delivers task results.

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

Common use cases:

• Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
• CDN integration: Upload to content delivery networks for immediate distribution.

// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg

The content data will be sent as the request body to the specified URL when generation is complete.

Content safety checking configuration for video generation.

Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

Include task cost in the response.

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

List of reference images (UUID, URL, Data URI, or Base64).

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target frame position.

The frameImages parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. This is different from referenceImages, which provide overall visual guidance without constraining specific timeline positions.

When the frame parameter is omitted, automatic distribution rules apply:

• 1 image: Used as the first frame.
• 2 images: First and last frames.

"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]

"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]

"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]

Source video for prompt-based editing. Dimensions and duration match the input video (UUID or URL).

List of reference videos (UUID, URL).

Elements allow you to include reusable assets (images, videos, or voices) in your video generation. Each element is identified by an id and can be referenced in the prompt using <<<element_1>>>, <<<element_2>>>, etc. in order of appearance.

An element can contain:

• Images via frontalImage and optionally images (up to 3 additional angles).
• Videos via videos (cannot be combined with images).
• Voices via voices (can only be combined with images, not videos).

"positivePrompt": "A video of <<<element_1>>> walking through a futuristic city",
"inputs": {
  "elements": [
    {
      "id": "my-character-id",
      "description": "A young woman with red hair",
      "frontalImage": "c64351d5-4c59-42f7-95e1-eace013eddab",
      "tags": ["Character"]
    }
  ]
}

"positivePrompt": "A video of <<<element_1>>> sitting in a coffee shop, reading a book",
"inputs": {
  "elements": [
    {
      "id": "my-character-id"
    }
  ]
}

Identifier of the model to use for generation.

Text prompt describing elements to include in the generated output.

Width of the generated media in pixels.

Height of the generated media in pixels.

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

Source for character orientation reference.

Maintain the original sound from the reference video.

Sequential prompt segments for multi-shot generation. The sum of all segment durations must equal the root-level duration.

Enable native audio generation.