GET

/v1/schemas/fal/audio/fal-ai/mmaudio-v2/text-to-audio

Accept:

kind inputactivity audiohash 1b4782fe…extracted Jul 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `d1b7a962cf2bac6d7851d1fd68d6b36b90876f6b7f4a9b0cad243843bc7b3599` { "fetchedAt": 1783329487, "extractorVersion": "1", "verifiedAt": null }

Request body

7 properties · 1 required · 0 $defs

property	type	description	constraints
prompt*	string	The prompt to generate the audio for.
cfg_strength	number	The strength of Classifier Free Guidance.	0 ≤ n ≤ 20 · default: 4.5
negative_prompt	string	The negative prompt to generate the audio for.	default: ""
seed	integer	The seed for the random number generator	0 ≤ n ≤ 65535 · nullable
num_steps	integer	The number of steps to generate the audio for.	4 ≤ n ≤ 50 · default: 25
mask_away_clip	boolean	Whether to mask away the clip.	default: false
duration	number	The duration of the audio to generate.	1 ≤ n ≤ 30 · default: 8

Validate a payload

before you spend tokens

shell

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