← All models
Kling V3 Video
Generate up to 15 seconds of cinematic video with native audio, lip sync, and multi-shot control. Text-to-video and image-to-video at up to 1080p.
Example
Details
- Accepts
- text + image
Pricing
- Price
- 21 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| mode | —enum: standard, pro, 4k | 'standard' generates 720p, 'pro' generates 1080p, '4k' generates 4K. |
| promptrequired | string | Text prompt for video generation. Max 2500 characters. |
| duration | integer | Video duration in seconds. |
| end_image | string | Last frame image. Requires start_image. Supports .jpg/.jpeg/.png, max 10MB, min 300px. |
| start_image | string | First frame image. Supports .jpg/.jpeg/.png, max 10MB, min 300px, aspect ratio 1:2.5 to 2.5:1. |
| aspect_ratio | —enum: 16:9, 9:16, 1:1 | Aspect ratio. Ignored when start_image is provided. |
| multi_prompt | string | JSON array of shot definitions for multi-shot mode. Each shot: {"prompt": "...", "duration": N}. Max 6 shots, min 1s per shot, total must equal duration. |
| generate_audio | boolean | Generate native audio for the video. |
| negative_prompt | string | Things you do not want to see in the video. Max 2500 characters. |