klingai-text-to-video

name	klingai-text-to-video
description	Generate videos from text prompts with Kling AI. Use when creating videos from descriptions, learning prompt techniques, or building T2V pipelines. Trigger with phrases like 'kling ai text to video', 'klingai prompt', 'generate video from text', 'text2video kling'.
allowed-tools	Read, Write, Edit, Bash(npm:*), Grep
version	1.18.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","kling-ai","text-to-video","video-generation"]
compatibility	Designed for Claude Code, also compatible with Codex and OpenClaw

Kling AI Text-to-Video

Overview

Generate videos from text prompts using the /v1/videos/text2video endpoint. Supports models v1 through v2.6, standard/professional modes, camera control, negative prompts, and native audio (v2.6+).

Endpoint: POST https://api.klingai.com/v1/videos/text2video

Request Parameters

Parameter	Type	Required	Description
model_name	string	Yes	Model version (see model catalog)
prompt	string	Yes	Video description, max 2500 chars
negative_prompt	string	No	What to exclude from generation
duration	string	Yes	"5" or "10" seconds
aspect_ratio	string	No	"16:9" (default), "9:16", "1:1", etc.
mode	string	No	"standard" (default) or "professional"
cfg_scale	float	No	Prompt adherence (0.0-1.0, default 0.5)
camera_control	object	No	Camera movement config
callback_url	string	No	Webhook URL for completion notification

Complete Example — Python

import jwt, time, os, requests

BASE = "https://api.klingai.com/v1"

def get_headers():
    ak, sk = os.environ["KLING_ACCESS_KEY"], os.environ["KLING_SECRET_KEY"]
    token = jwt.encode(
        {"iss": ak, : (time.time()) + , : (time.time()) - },
        sk, algorithm=, headers={: , : }
    )
     {: , : }


response = requests.post(, headers=get_headers(), json={
    : ,
    : 
              
              ,
    : ,
    : ,
    : ,
    : ,
    : ,
})

task = response.json()
task_id = task[][]


 :
    time.sleep()
    result = requests.get(
        , headers=get_headers()
    ).json()

    status = result[][]
     status == :
        video = result[][][][]
        ()
        ()
        
     status == :
         RuntimeError(result[][])