GET

/v1/schemas/fal/audio/fal-ai/kling-video/video-to-audio

Accept:

kind inputactivity audiohash cdfd1639…extracted Oct 14, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `4b1983687425cc568159a2a48dce2debee309ba7c9ba08c4424997a3351bbb3c` { "fetchedAt": 1791954060, "extractorVersion": "1", "verifiedAt": null }

Request body

5 properties · 1 required · 0 $defs

property	type	description	constraints
video_url*	string	The video URL to extract audio from. Only .mp4/.mov formats are supported. File size does not exceed 100MB. Video duration between 3.0s and 20.0s.
asmr_mode	boolean	Enable ASMR mode. This mode enhances detailed sound effects and is suitable for highly immersive content scenarios.	default: false
sound_effect_prompt	string	Sound effect prompt. Cannot exceed 200 characters.	length ≤ 200 · nullable
background_music_prompt	string	Background music prompt. Cannot exceed 200 characters.	length ≤ 200 · nullable
enable_safety_checker	boolean	Disabling safety checks requires account authorization; unauthorized requests are always checked.	default: true

Validate a payload

before you spend tokens

shell

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