GET

/v1/schemas/fal/video/mirelo-ai/sfx2.0/video-to-video

Accept:

kind inputactivity videohash 7e515f67…extracted Oct 22, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `f75decc194db41cd13333fa57979389b11edc89da460e136806e3b15f2788e42` { "fetchedAt": 1792645225, "extractorVersion": "1", "verifiedAt": null }

Request body

7 properties · 1 required · 0 $defs

property	type	description	constraints
video_url*	string	Video to add sound to: an http(s) URL, or a base64 data URI up to 8 MB.
duration	number	Seconds of sound to generate, from 1 s to 600 s, clamped to the video's length. Over 10 s generates in 10 s windows. A video shorter than 1 s answers 400.	1 ≤ n ≤ 600 · default: 10
text_prompt	string	Optional text guiding the soundtrack. Name sounds the picture does not show, such as off-screen sounds or an ambience bed, to have them worked into it.	length ≤ 2000 · nullable
negative_prompt	string	Sounds to keep out of the result, as a short comma-separated list.	length ≤ 1000 · nullable
num_samples	integer	Number of variations to generate. Billed per sample.	1 ≤ n ≤ 4 · default: 2
preserve_speech	boolean	Keep the speech in the input's audio and generate the rest of the soundtrack around it. False generates sound effects only and suppresses speech.	default: true
seed	integer	Seed for generation. -1 or None for random.	-1 ≤ n ≤ 18446744073709552000 · nullable

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"mirelo-ai/sfx2.0/video-to-video","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}