API docs / Video models

kling-v3-omni-video API

Generate and edit videos from text prompts, images, and reference videos with native audio support. Supports text-to-video, image-to-video, video editing, and style transfer in a single unified model. Create videos up to 15 seconds at resolutions from 720p to 4K using reference images to maintain character and style consistency across scenes. Features multi-shot mode for creating videos with multiple scenes, each with custom prompts and durations. Use reference videos for style transfer or as a base for video editing with text instructions. Supports template references in prompts using <<<image_1>>>, <<<video_1>>> syntax to incorporate uploaded reference materials. Generate native audio synchronized to video content or preserve original audio from reference videos.

Model id
kwaivgi/kling-v3-omni-video
Provider
Kling
Output
Video
Price
From 293 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-v3-omni-video". 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-omni-video",
  "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

NameTypeDetails
promptrequiredstring

Text prompt for video generation. Supports <<<image_1>>>, <<<video_1>>> template references. Max 2500 characters.

Up to 2500 characters

first_framearray of URLs

First frame image. Supports .jpg/.jpeg/.png, max 10MB, min 300px, aspect ratio 1:2.5 to 2.5:1. Each file: up to 10 MB.

Up to 1 files · Accepts image/*

last_framearray of URLs

Last frame image. Requires start_image. Supports .jpg/.jpeg/.png, max 10MB, min 300px. Each file: up to 10 MB.

Up to 1 files · Accepts image/*

reference_imagesarray of URLs

Reference images for elements, scenes, or styles. Supports .jpg/.jpeg/.png. Max 7 without video, 4 with video. Upload up to 7 reference images. They are numbered in upload order and can be inserted into the prompt as <<<image_1>>>, <<<image_2>>>, and so on.

Up to 7 files · Accepts image/*

reference_videosarray of URLs

Reference video (.mp4/.mov). Duration 3-10s, resolution 720-2160px per side, max 200MB. Each file: 3–10s. Upload reference videos. They are numbered in upload order and can be inserted into the prompt as <<<video_1>>>, <<<video_2>>>, and so on.

Up to 1 files · Accepts video/*

aspect_ratiostring

Default: 16:9

One of: 16:9, 9:16, 1:1

duration_secondsnumber

Video duration in seconds (3-15). Ignored for video editing (base).

Default: 5

Min 3 · Max 15

generate_audioboolean

Generate native audio. Mutually exclusive with reference video.

Default: false

multi_promptstring

JSON array of shot definitions for multi-shot mode. Each shot: {"prompt": "...", "duration": N}. Max 6 shots, min duration 1s per shot, total must equal duration. Example: [{"prompt":"A cat jumps","duration":3},{"prompt":"It lands","duration":2}]

keep_original_soundboolean

Keep original sound from reference video.

Default: true

modestring

Default: standard

One of: standard, pro

video_reference_typestring

Default: feature

One of: feature, base