GET

/v1/schemas/fal/video/fal-ai/wan/v2.7/text-to-video

Accept:

kind inputactivity videohash bd51b0cd…extracted Aug 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `0201a380d827f63e2e9d5272d93808e7670afc6713e1087903effa198f956ac0` { "fetchedAt": 1786338105, "extractorVersion": "1", "verifiedAt": null }

Request body

9 properties · 1 required · 0 $defs

property	type	description	constraints
prompt*	string	Text prompt describing the desired video. Max 5000 characters.	length ≥ 1
aspect_ratio	enum	Aspect ratio of the generated video.	16:9 \| 9:16 \| 1:1 \| 4:3 \| 3:4 · default: "16:9"
enable_prompt_expansion	boolean	Enable intelligent prompt rewriting.	default: true
seed	integer	Random seed for reproducibility (0-2147483647).	nullable
resolution	enum	Output video resolution tier.	720p \| 1080p · default: "1080p"
audio_url	string	URL of driving audio. Supports WAV and MP3. Duration: 3-30s. Max 15 MB. If not provided, the model auto-generates matching background music.	nullable
duration	enum	Output video duration in seconds (2-15).	2 \| 3 \| 4 \| 5 \| 6 \| 7 · +8 more · default: 5
enable_safety_checker	boolean	Enable content moderation for input and output. Disabling it requires account authorization; unauthorized requests are always checked.	default: true
negative_prompt	string	Content to avoid in the video. Max 500 characters.	nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/wan/v2.7/text-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}