Skip to main content
Video models

Kling Omni — Video edit API

Video edit with Kling Omni: request parameters, examples and response handling.

← Kling Omni

Endpoint: POST https://api.higgsfield.ai/kling-video/omni/video-edit

Endpoint ID: kling-video/omni/video-edit

▶Open API PlaygroundKling Omni · Video edit↗

#Usage notes

  • Supply exactly one source video from 3 to 10 seconds long and no larger than 200 MB. Duration is derived from the video; do not send a separate duration field.
  • You may also supply up to four image_urls and up to four elements.
  • Keep the top-level prompt within 2,500 characters; longer prompts are truncated.
  • elements contains Kling element IDs as decimal strings. Each ID must belong to the account making the request; arbitrary provider IDs are rejected.
  • The example.com media URLs are placeholders. Replace them with public HTTPS URLs to your own media before submitting.

#Quick start

Replace the example media URLs with publicly accessible URLs for your own files before submitting.

cURL
curl --request POST \
  --url https://api.higgsfield.ai/kling-video/omni/video-edit \
  --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" \
  --header "Content-Type: application/json" \
  --header "Idempotency-Key: ${IDEMPOTENCY_KEY}" \
  --data '{
  "prompt": "Change the background to a sunlit garden while preserving the subject and motion.",
  "video_urls": [
    "https://example.com/source-video.mp4"
  ]
}'

#Input schema

mode string (default: pro)

Allowed values: "std", "pro".

prompt string required

Write your prompt here

elements array

Minimum items: 0. Maximum items: 4. Each item: string.

image_urls array

Ordered public image reference URLs. Minimum items: 0. Maximum items: 4. Each item: string. Format: uri.

video_urls array required

Ordered public video reference URLs. Minimum items: 1. Maximum items: 1. Each item: string. Format: uri.

Complete JSON schema
json
{
  "type": "object",
  "title": "Kling Omni Playground",
  "required": [
    "prompt",
    "video_urls"
  ],
  "properties": {
    "mode": {
      "enum": [
        "std",
        "pro"
      ],
      "type": "string",
      "default": "pro"
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "description": "Write your prompt here"
    },
    "elements": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 4,
      "minItems": 0
    },
    "image_urls": {
      "type": "array",
      "items": {
        "type": "string",
        "title": "Image URL",
        "format": "uri"
      },
      "maxItems": 4,
      "minItems": 0
    },
    "video_urls": {
      "type": "array",
      "items": {
        "type": "string",
        "title": "Video URL",
        "format": "uri"
      },
      "maxItems": 1,
      "minItems": 1
    }
  }
}

#Response

Submission returns a request handle. Poll status_url until status is completed, or use webhooks.

Accepted
{
  "status": "queued",
  "request_id": "REQUEST_ID",
  "status_url": "https://api.higgsfield.ai/requests/REQUEST_ID/status",
  "cancel_url": "https://api.higgsfield.ai/requests/REQUEST_ID/cancel"
}

A completed response includes the following output fields:

json
{
  "status": "completed",
  "request_id": "REQUEST_ID",
  "video": {
    "url": "https://example.com/output.mp4"
  }
}

See idempotent requests, polling, request errors and authentication for shared request handling.

Was this page helpful?
Navigation