Kling v3 비디오 생성
Generate videos with official Kling v3 using explicit reference-image and frame-role semantics
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
- Supports text-to-video, image-to-video, explicit first/last frame control, and audio video
mode=stdmaps to 720P,mode=promaps to 1080Paudio=truegenerates an audio video and is billed as Sounddurationsupports3s,4s,5s,6s,7s,8s,9s,10s,11s,12s,13s,14s,15s
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-v3.
promptstring본문필수Text prompt. Describe the subject, action, scene, camera movement, and style.
modestring본문기본값: stdGeneration mode.
std- standard mode, 720Ppro- professional mode, 1080P
durationinteger본문기본값: 5Video duration in seconds.
Options: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
aspect_ratiostring본문기본값: 16:9Video aspect ratio. Common values: 16:9, 9:16, 1:1
reference_imagesstring[]본문Normal reference images.
- These images are treated as references only
- They are not automatically converted into first/last frames
- Use
image_with_rolesfor explicit frame control
image_with_rolesobject[]본문Explicit image-role array for frame control and mixed inputs.
Show image_with_roles object fields
urlstring본문필수Publicly accessible image URL.
rolestring본문필수Image role.
Supported values:
first_framelast_framereferencereference_image
last_frame is only sent when explicitly declared in image_with_roles. The system no longer infers the last frame from reference_images[1].
audioboolean본문기본값: falseWhether to generate an audio video.
metadataobject본문Extended parameters.
Show metadata fields
negative_promptstring본문Negative prompt describing content to avoid.
watermarkboolean본문Whether to add watermark.
Input Rules
| Input shape | Behavior |
|---|---|
reference_images only | Normal references |
image_with_roles with only first_frame / last_frame | Frame control |
| Both fields used together, or roles include both frame and reference semantics | Mixed mode |
Examples
Text-to-Video
{
"model": "kling-v3",
"prompt": "A golden cat running on a sunlit meadow, slow motion, cinematic quality",
"mode": "std",
"duration": 5,
"aspect_ratio": "16:9"
}Image Reference
{
"model": "kling-v3",
"prompt": "Use the reference character and animate a subtle smile",
"reference_images": ["https://example.com/reference.jpg"],
"mode": "std",
"duration": 5
}First and Last Frame Control
{
"model": "kling-v3",
"prompt": "The city naturally transitions from day to night",
"image_with_roles": [
{ "url": "https://example.com/day.jpg", "role": "first_frame" },
{ "url": "https://example.com/night.jpg", "role": "last_frame" }
],
"mode": "pro",
"duration": 5
}Mixed Reference and Frame Input
{
"model": "kling-v3",
"prompt": "Keep the character identity consistent while transitioning scenes",
"reference_images": ["https://example.com/character-reference.jpg"],
"image_with_roles": [
{ "url": "https://example.com/start-scene.jpg", "role": "first_frame" },
{ "url": "https://example.com/end-scene.jpg", "role": "last_frame" }
],
"mode": "pro",
"duration": 5
}Audio Video
{
"model": "kling-v3",
"prompt": "A singer performing on stage, crowd cheering, flashing lights",
"mode": "std",
"duration": 5,
"audio": true
}Video generation is asynchronous. Use the Get Video Task 상태 endpoint to query progress and results.