GET

/v1/schemas/fal/video/fal-ai/kling-video/o3/4k/reference-to-video

kind inputactivity videohash 982f90b1…extracted Oct 14, 2026version currentsource upstream spec ↗
fieldrecorded source
schemaSource linked above.

upstream-spec

Source trace
e7515afc9c3fe2d43f82f58f9f5355d3a6b5da492041be2a2a9d250f3805b6e8
{
  "fetchedAt": 1791954060,
  "extractorVersion": "1",
  "verifiedAt": null
}

Request body

11 properties · 0 required · 2 $defs
propertytypedescriptionconstraints
durationenumVideo duration in seconds (3-15s).3 | 4 | 5 | 6 | 7 | 8 · +7 more · default: "5"
end_image_urlstringImage to use as the last frame of the video.nullable
aspect_ratioenumThe aspect ratio of the generated video frame.16:9 | 9:16 | 1:1 · default: "16:9"
elementsKlingV3ComboElementInput[]Elements (characters/objects) to include. Reference in prompt as @Element1, @Element2.nullable
shot_typeenumThe type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure.customize | intelligent · default: "customize"
promptstringText prompt for video generation. Either prompt or multi_prompt must be provided, but not both.length ≤ 2500 · nullable
generate_audiobooleanWhether to generate native audio for the video.default: false
start_image_urlstringImage to use as the first frame of the video.nullable
image_urlsstring[]Reference images for style/appearance. Reference in prompt as @Image1, @Image2, etc. Maximum 7 total (elements + reference images) is allowed.nullable
multi_promptKlingV3MultiPromptElement[]List of prompts for multi-shot video generation.nullable
enable_safety_checkerbooleanDisabling safety checks requires account authorization; unauthorized requests are always checked.default: true

Types

2 $defs

KlingV3ComboElementInputobject

reference_image_urlsstring[]Additional reference images from different angles. 1-3 images supported. At least one image is required.nullable
frontal_image_urlstringThe frontal image of the element (main view).nullable
voice_idstringThe voice ID for this element. The voice will be binded to the element and references to this element will use the binded voice. Get voice IDs from the following endpoint: https://fal.ai/models/fal-ai/kling-video/create-voicenullable
video_urlstringThe video URL of the element. A request can only have one element with a video.nullable

KlingV3MultiPromptElementobject

durationenumThe duration of this shot in seconds1 | 2 | 3 | 4 | 5 | 6 · +9 more · default: "5"
prompt*stringThe prompt for this shot.

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/kling-video/o3/4k/reference-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}