Last Update: 2025/3/26

Kling Text to Video API

The Text to Video API enables you to create video content from text descriptions using Kling's AI models. This document provides details about the API endpoint, parameters, and response structure.

Endpoint

POST https://platform.llmprovider.ai/v1/videos/text2video

Request Headers

Header	Value
Authorization	Bearer YOUR_API_KEY
Content-Type	application/json

Request Body

The request body should be a JSON object with the following parameters:

Field	Type	Description
model	string	The model to use. Options: kling-video-v1, kling-video-v1-6
prompt	string	Text prompt for video generation (max 2500 characters).
negative_prompt	string	(Optional) Negative text prompt (max 2500 characters).
cfg_scale	float	(Optional) Generation freedom scale [0, 1]. Higher values mean stricter adherence to prompt. Default: 0.5
mode	string	(Optional) Generation mode. Options: std (standard), pro (professional quality). Default: std
camera_control	object	(Optional) Camera movement controls. Optional
aspect_ratio	string	(Optional) Video aspect ratio. Options: 16:9, 9:16, 1:1. Default: 16:9
duration	string	(Optional) Video duration in seconds. Options: 5, 10. Default: 5
external_task_id	string	(Optional) Custom task identifier. Optional

Camera Control Object

Field	Type	Description
type	string	Camera movement type: simple, down_back, forward_up, right_turn_forward, left_turn_forward
config	object	Camera configuration (required when type is simple)

Camera Config Object

All fields are optional with range [-10, 10]:

• horizontal: Horizontal movement
• vertical: Vertical movement
• pan: Horizontal rotation (Y-axis)
• tilt: Vertical rotation (X-axis)
• roll: Roll rotation (Z-axis)
• zoom: Zoom level change

Example Request

{
  "model": "kling-video-v1",
  "prompt": "A beautiful sunset over the ocean",
  "camera_control": {
    "type": "simple",
    "config": {
      "pan": 1
    }
  }
}

Response Body

The API returns a JSON object with the following structure:

Field	Type	Description
task_id	string	Generated task identifier
task_info	object	Task creation parameters
task_status	string	Task status: submitted, processing, succeed, failed
created_at	integer	Task creation timestamp (milliseconds)
updated_at	integer	Last update timestamp (milliseconds)

Example Response

{
  "task_id": "task_xyz789",
  "task_info": {
    "external_task_id": "custom_id_123"
  },
  "task_status": "submitted",
  "created_at": 1722769557708,
  "updated_at": 1722769557708
}

Example Request

Shell

curl -X POST https://platform.llmprovider.ai/v1/videos/text2video \
-H "Authorization: Bearer $YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "kling-video-v1",
    "prompt": "A beautiful sunset over the ocean",
    "camera_control":{
        "type": "simple",
        "config":{
            "pan": 1
        }
    }
}'

nodejs

const axios = require('axios');
const apiKey = 'YOUR_API_KEY';
const url = 'https://platform.llmprovider.ai/v1/videos/text2video';

const data = {
    model: 'kling-video-v1',
    prompt: 'A beautiful sunset over the ocean',
    camera_control:{
        "type": "simple",
        "config":{
            "pan": 1
        }
    }
};

const headers = {
    'Authorization': `Bearer ${apiKey}`,
    'Content-Type': 'application/json'
};

axios.post(url, data, { headers })
.then(response => {
    console.log('Response:', response.data);
})
.catch(error => {
    console.error('Error:', error);
});

python

import requests
import json

api_key = 'YOUR_API_KEY'
url = 'https://platform.llmprovider.ai/v1/videos/text2video'

headers = {
    'Authorization': f'Bearer {api_key}',
    'Content-Type': 'application/json'
}

data = {
    'model': 'kling-video-v1',
    'prompt': 'A beautiful sunset over the ocean',
    'camera_control': {
        'type': 'simple',
        'config': {
            'pan': 1
        }
    }
}

response = requests.post(url, headers=headers, data=json.dumps(data))

if response.status_code == 200:
    print('Response:', response.json())
else:
    print('Error:', response.status_code, response.text)

For any questions or further assistance, please contact us at [email protected].