Kling / Video
kling-4.0
Create videos from text, keyframes or reference images.
https://orux.top/api/v1/tasksRequest body
model: kling-4.0. Place model parameters inside input.
Examples use configured defaults. Replace placeholders in angle brackets with actual values.
Parameters
Fields accepted in the request body for this model.
prompttextfirst_frame_urlimage URLMention uploaded frames as @first_frame and @last_frame in the prompt.
last_frame_urlimage URLMention uploaded frames as @first_frame and @last_frame in the prompt.
resolutionenumdurationintegerChoose an exact output duration. Automatic duration and video references are not available yet.
aspect_ratioenumkeyframe_urlsimage URL[]image_urlsimage URL[]Use reference images or keyframes, not both in one generation.
elementsobjectUp to 7 named subjects, each with 2–4 images. Use @name in your prompt. Video subjects are not available yet.
voicesobjectUp to 3 voices; names must be unique across subjects and voices.
Response examples
Illustrative response structures. Actual content depends on the request.
Retrieve the result
Save task_id and poll the task endpoint. An accepted task has not yet finished generating.