Generate a video from text prompt using the kling-v1 model.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Positive text prompt. Max 2500 characters.
2500"A cat walking through a field of sunflowers at golden hour"
Model name
kling-v1 "kling-v1"
Negative text prompt. Max 2500 characters.
2500std: Standard (cost-effective). pro: Professional (higher quality).
std, pro Video duration in seconds (3-15).
3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 "5"
Aspect ratio of generated video (width:height).
16:9, 9:16, 1:1 "16:9"
Prompt relevance (0-1). Higher = stronger adherence. Not supported by kling-v2.x models.
0 <= x <= 1Enable multi-shot storyboarding. When true, prompt is ignored; use multi_prompt instead.
Storyboard method. Required when multi_shot is true.
customize, intelligence Storyboard shots (1-6). Required when multi_shot is true and shot_type is customize.
Generate sound with video. Only V2.6+ models.
on, off Camera movement control.
Callback URL for task status notifications
Custom task ID. Must be unique per account.