API docs / Video models
Kling 2.5 Turbo Pro API
Generates videos from text prompts or images with smooth motion, cinematic depth, and strong prompt adherence. Supports both text-to-video and image-to-video creation with customizable duration (5 or 10 seconds) and aspect ratios (16:9, 9:16, 1:1). Can use a start image as the first frame and optionally an end image as the last frame to create videos with specific beginning and ending points.
- Model id
kwaivgi/kling-v2.5-turbo-pro- Provider
- Kling
- Output
- Video
- Price
- From 122 credits per run, the same as on voor.ai. Options such as length or resolution can change it.
Request
POST https://voor.ai/v1/generations with "model": "kwaivgi/kling-v2.5-turbo-pro". 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-v2.5-turbo-pro",
"input": {
"prompt": "A red fox standing in fresh snow at golden hour, soft light"
},
"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 |
|---|---|---|
promptrequired | string | Text prompt for video generation |
first_frame | array of URLs | Deprecated: Use start_image instead. Up to 1 files · Accepts image/* |
last_frame | array of URLs | Last frame of the video Up to 1 files · Accepts image/* |
aspect_ratio | string | Default: One of: 16:9, 9:16, 1:1 |
duration_seconds | number | Default: One of: 5, 10 |
negative_prompt | string | Things you do not want to see in the video Default: |
guidance | number | Kept for backwards compatibility. This parameter is not used. |
start_image | array of URLs | First frame of the video Up to 1 files · Accepts image/* |