API docs / Video models
Kling 3.0 Motion Control API
Transfer motion from a reference video to any character image, generating videos where the character's appearance is based on the reference image while performing actions from the reference video. Takes a reference image and reference video as inputs to produce animated videos that combine visual appearance with motion patterns. Supports two character orientation modes: 'image' maintains the character's original facing direction for up to 10 seconds, while 'video' matches the character's orientation to the reference video for up to 30 seconds. Includes standard mode for 720p output and professional mode for 1080p quality. Improved consistency and quality compared to previous versions with better preservation of character identity and smoother motion transfer. Suitable for dance and gesture transfer, character animation, social media content creation, and marketing applications.
- Model id
kwaivgi/kling-v3-motion-control- Provider
- Kling
- Output
- Video
- Price
- Depends on the options; the same as on voor.ai.
Request
POST https://voor.ai/v1/generations with "model": "kwaivgi/kling-v3-motion-control". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.
curl https://voor.ai/v1/generations \
-H "Authorization: Bearer $VOOR_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "kwaivgi/kling-v3-motion-control",
"input": {
"prompt": "",
"first_frame": [
"https://example.com/input.png"
],
"source_video": [
"https://example.com/input.png"
]
},
"callback_url": "https://example.com/webhooks/voor"
}'
# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
-H "Authorization: Bearer $VOOR_API_KEY"Input parameters
| Name | Type | Details |
|---|---|---|
prompt | string | Text prompt for video generation. You can add elements to the screen and achieve motion effects through prompt words. Default: |
first_framerequired | array of URLs | Reference image. The characters, backgrounds, and other elements in the generated video are based on the reference image. Supports .jpg/.jpeg/.png, max 10MB, dimensions 340px-3850px, aspect ratio 1:2.5 to 2.5:1. Each file: up to 10 MB. Up to 1 files · Accepts image/* |
source_videorequired | array of URLs | Reference video. The character actions in the generated video are consistent with the reference video. Supports .mp4/.mov, max 100MB, 3-30 seconds duration depending on character_orientation. Each file: 3–30.5s. Up to 1 files · Accepts video/* |
character_orientation | string | Default: One of: image, video |
keep_original_sound | boolean | Whether to keep the original sound of the reference video Default: |
mode | string | Default: One of: std, pro |