GET

/v1/schemas/fal/video/sonilo/v1.1/video-to-video

Accept:

kind inputactivity videohash 0b76925d…extracted Jul 17, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `91bdc90bcad0ce1f8044dc0c9f87135ec6e192452c86217d319a3f0e1ed82434` { "fetchedAt": 1784264547, "extractorVersion": "1", "verifiedAt": null }

Request body

6 properties · 1 required · 0 $defs

property	type	description	constraints
video_url*	string	Public http(s) URL of the source video to score.
start_offset	number	Optional. Start scoring from this offset (seconds) into the video. Requires Start Offset + Duration <= Video Duration.	0 ≤ n ≤ 600 · nullable
keep_speech_vocal	boolean	Keep the original video's speech/vocals. When on, the source audio is separated (music source separation), and only the isolated vocals are blended over the generated music with automatic ducking (the music dips under speech). When off (default), the original …	default: false
prompt	string	Optional text prompt steering the musical style. If omitted, a prompt is generated automatically from the video.	nullable
num_samples	integer	How many distinct scored videos to generate.	1 ≤ n ≤ 3 · default: 1
duration	number	Optional. Length (seconds) of the video segment to score. When set, scores a segment of this length starting at Start Offset (or from the beginning if Start Offset is unset). Defaults (None) to the rest of the video.	1 ≤ n ≤ 600 · nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"sonilo/v1.1/video-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}