GET

/v1/schemas/fal/video/kling/v4/text-to-video

Accept:

kind inputactivity videohash 0e27e318…extracted Oct 23, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `b54e4b8233c728af687acc7730c6f46e9e2f827e20dccbb50da6675f3cde8668` { "fetchedAt": 1792731610, "extractorVersion": "1", "verifiedAt": null }

Request body

5 properties · 0 required · 1 $defs

property	type	description	constraints
resolution	enum	Output resolution.	720p \| 1080p · default: "1080p"
multi_prompt	KlingV4Shot[]	Per-shot prompts for multi-shot generation. The video duration is the sum of the shot durations.	items ≥ 1 · nullable
prompt	string	Text prompt. Either prompt or multi_prompt must be provided.	length ≤ 26000 · nullable
duration	integer	Video duration in seconds (3-30).	3 ≤ n ≤ 30 · default: 5
aspect_ratio	enum	Aspect ratio of the generated video.	16:9 \| 9:16 \| 1:1 \| 21:9 · default: "16:9"

Types

1 $defs

KlingV4Shotobject

prompt*	string	The prompt for this shot.	length ≥ 1 · length ≤ 512
duration	integer	Shot duration in seconds.	1 ≤ n ≤ 30 · default: 5

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"kling/v4/text-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}