Models Hub
API ReferenceVideo

Kling text-to-video.

Generate video from a text description using the Kling model. Supported models: kling-v1, kling-v1-5, etc.

Edit this page
POST
/kling/v1/videos/text2video

Authorization

bearerAuth
AuthorizationBearer <token>

Authenticate using an Authorization Bearer API Key.

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

Video generation request

Response Body

application/json

application/json

curl -X POST "https://example.com/kling/v1/videos/text2video" \  -H "Content-Type: application/json" \  -d '{    "model": "kling-v1",    "prompt": "The astronaut stands up and walks away",    "duration": 5,    "width": 1280,    "height": 720,    "fps": 30  }'
{
  "task_id": "abcd1234efgh",
  "status": "queued"
}
{
  "error": {
    "code": "string",
    "message": "string",
    "request_id": "string"
  }
}

Kling image-to-video.

Generate video from an image using the Kling model. The `image` parameter accepts an image URL or Base64-encoded image data.

OpenAI-compatible video generation.

Create a video generation task via the OpenAI-compatible `/v1/videos` endpoint, for compatible providers such as PixVerse, Veo, and Seedance.