kling-3.0-turbo 비디오 생성
Generate videos with the official kling-3.0-turbo model through the standard ToAPIs async video endpoint
중국 본토 사용자 안내: 중국 본토 사용자는 https://toapis.cn 를 API 엔드포인트(Base URL)로 사용해 주세요. 본 문서의 예시에서 https://toapis.com 을 https://toapis.cn 로 바꿔 주세요.
- Async task API, returns a task ID after submission
- Uses the new official Kling Turbo upstream protocol
- Supports text-to-video and image-to-video with first-frame input only
resolutionsupports720pand1080pdurationsupports3s,4s,5s,6s,7s,8s,9s,10s,11s,12s,13s,14s,15saspect_ratioapplies to text-to-video requestswatermarkis a boolean toggle only; custom watermark payloads are not supported
Use publicly accessible image URLs. Do not pass base64 image data. Upload local images with the Upload 이미지 API first.
Authorization
Authorizationstring헤더필수All endpoints require Bearer Token authentication.
Authorization: Bearer YOUR_API_KEY요청 파라미터
modelstring본문필수Video generation model name, fixed as kling-3.0-turbo.
promptstring본문필수Text prompt. For image-to-video, this is sent to Kling Turbo as the prompt content item.
reference_imagesstring[]본문선택 input images. For Kling Turbo image-to-video, only the first image is used as first_frame.
Tail frame input is not supported in this integration. Additional input images are ignored.
resolutionstring본문기본값: 720pVideo resolution.
Supported values:
720p1080p
durationinteger본문기본값: 5Video duration in seconds.
Supported values: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
aspect_ratiostring본문기본값: 16:9Video aspect ratio for text-to-video.
Supported values:
16:99:161:1
watermarkboolean본문기본값: falseWhether to add the official Kling watermark.
Examples
Text-to-Video
{
"model": "kling-3.0-turbo",
"prompt": "A cinematic shot of a red sports car driving through rain",
"resolution": "720p",
"duration": 5,
"aspect_ratio": "16:9"
}Image-to-Video
{
"model": "kling-3.0-turbo",
"prompt": "Animate the character with subtle camera motion",
"reference_images": ["https://example.com/first-frame.png"],
"resolution": "1080p",
"duration": 5,
"watermark": true
}Video generation is asynchronous. Use the Get Video Task 상태 endpoint to query progress and results.