GET

/v1/schemas/fal/audio/mirelo-ai/sfx2.0/text-to-audio

Accept:

kind inputactivity audiohash c34b6577…extracted Oct 22, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `9ca6e99c0c1486fff295467645eae322956e164919169e054ca75bc4d8b8326c` { "fetchedAt": 1792645225, "extractorVersion": "1", "verifiedAt": null }

Request body

7 properties · 1 required · 0 $defs

property	type	description	constraints
prompt*	string	What the sound effect should sound like	length ≥ 1 · length ≤ 2000
num_samples	integer	Number of variations to generate. Billed per sample.	1 ≤ n ≤ 4 · default: 2
duration	number	Seconds of sound to generate, up to the deployment's text-to-SFX maximum	0.1 ≤ n ≤ 600 · default: 30
negative_prompt	string	Sounds to keep out of the result	length ≤ 1000 · nullable
upload_audio_bitrate_kbps	integer	Bitrate in kbps for an mp3 or aac upload. mp3 is written at exactly this constant rate, one of 32, 40, 48, 56, 64, 80, 96, 112, 128, 160, 192, 224, 256, 320. aac takes 32 to 256 as a target the encoder may undershoot on mono or sparse audio. Unset keeps the default: mp3 at LAME V0 VBR, aac at a 256 kbps target. Refused with a lossless upload_audio_format.	32 ≤ n ≤ 320 · nullable
upload_audio_format	enum	Audio format of each file	wav \| mp3 \| aac \| flac · default: "wav"
seed	integer	Seed of the first sample; -1 or unset is random	-1 ≤ n ≤ 9223372036854776000 · 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/text-to-audio","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}