Kling 2.6

Overview

Kling 2.6 is Kuaishou’s latest video generation model with built-in audio generation capability. It supports both Text-to-Video and Image-to-Video modes, producing high-quality videos with optional synchronized sound effects.


Test API KEY: key_00000000000000000000000000000000

Endpoints

1. Create Task

Request


POST https://api.pixwith.ai/api/task/create

Headers

Header	Value	Required
Content-Type	application/json	Yes
Api-Key	{API_KEY}	Yes

Request Parameters

Parameter	Type	Required	Description
prompt	string	Yes	The input prompt (e.g., “A cat playing with a ball in the garden”)
image_urls	array	Conditional	[“https://cdn.pixwith.ai/xxx.jpg ”]. Provide exactly 1 image for Image-to-Video mode.
model_id	string	Yes	`2-33`
options	object	Yes	Configuration options for the task
options.prompt_optimization	boolean	Yes	If true, all prompt words will be automatically translated into English.
options.num_outputs	int	No	Number of videos to generate. Valid values: `1` to `4`. Default: `1`.
options.sound	boolean	Yes	If true, generates synchronized audio for the video. Default: `true`.
options.aspect_ratio	string	Conditional	Aspect ratio of the output. Valid values: `'1:1'` (Default), `'16:9'`, `'9:16'`. Only for Text-to-Video. Image-to-Video auto-detects from input image.
options.duration	int	Yes	Duration of the video in seconds. Valid values: `5` or `10`. Default: `5`.

Example Request - Text-to-Video


{
  "prompt": "A cat playing with a ball in the garden",
  "model_id": "2-33",
  "options": {
    "prompt_optimization": true,
    "num_outputs": 1,
    "sound": true,
    "aspect_ratio": "16:9",
    "duration": 5
  }
}

Example Request - Image-to-Video


{
  "prompt": "The person in the photo starts walking forward",
  "image_urls": ["https://cdn.pixwith.ai/example.jpg"],
  "model_id": "2-33",
  "options": {
    "prompt_optimization": true,
    "num_outputs": 1,
    "sound": false,
    "duration": 10
  }
}

Response Parameters

Parameter	Type	Description
code	int	1=success, 0=error
message	string	Success and failure messages
data	object
data.task_id	string
data.estimated_time	int	Estimated time in seconds

Response


{
  "code": 1,
  "message": "success",
  "data": {
    "task_id": "d425ab4dc256f0ebaa84862b9cea8a3d",
    "estimated_time": 150
  }
}

Credits

Duration	Sound Off	Sound On
5 seconds	45	90
10 seconds	90	180