Videoslash API
Creative studioGeneratedModels

Kling O1 Edit

Creative Studio video model reference for the public API.

Kling O1 Edit

Public model ID: kling-o1-edit

Asset type: video

Category: Video Generation

Starting credits: 2 (defaults: 3)

Prompt required.

Start a generation

curl -s -X POST "$API_BASE_URL/v1/creative-studio/generations" \
  -H "Authorization: Bearer vsl_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "modelId": "kling-o1-edit",
    "prompt": "Your prompt here",
    "start_image": ["https://example.com/reference.jpg"],
    "video_reference_type": "feature"
  }' | jq

Poll GET /v1/creative-studio/generations/{id} until status is completed. Completed generations return outputUrl on cdn.videoslash.com.

Media parameters

NameTypeConstraintsDefaultDescription
start_imagestringoptional · max items: 1—First frame image for the video. Supports .jpg/.jpeg/.png, max 10MB.
end_imagestringoptional · max items: 1—Last frame image for the video. Requires start_image to be set. Supports .jpg/.jpeg/.png, max 10MB.
reference_imagesarrayoptional · max items: 7—Reference images for elements, scenes, or styles (up to 7 without video, 4 with video). Supports .jpg/.jpeg/.png.
reference_videostringoptional · max items: 1—Reference video for style, camera movement, or as base for editing. Supports .mp4/.mov, 3-10s duration, max 200MB.

Settings parameters

NameTypeConstraintsDefaultDescription
video_reference_typeenumoptional · enum: feature, basefeatureHow to use the reference video: 'feature' for style/camera reference, 'base' for video editing.
keep_original_soundbooleanoptionaltrueWhether to keep the original sound from the reference video.
modeenumoptional · enum: std, proproVideo generation mode. 'std' is cost-effective, 'pro' has higher quality.
aspect_ratioenumoptional · enum: 16:9, 9:16, 1:116:9Aspect ratio of the generated video. Required for text-to-video. Ignored when using first frame image or video editing.
durationenumoptional · enum: 3, 4, 5, 6, 7, 8, 9, 105Video duration in seconds. For text/image-to-video: 5 or 10. With video reference (feature type): 3-10. Ignored for video editing (base type).

On this page