GET

/v1/schemas/fal/audio/fal-ai/ace-step/prompt-to-audio?kind=output

Accept:

kind outputactivity audiohash ef18c9e3…extracted Jul 6, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. Source trace `e3b1e631fdc09fc66b3ae5aab109020dd4a162f6028e812212387f12cb6e5390` { "fetchedAt": 1783329487, "extractorVersion": "1", "verifiedAt": null }

Response body

4 properties · 4 required · 1 $defs

property	type	description
audio*	File	The generated audio file.
tags*	string	The genre tags used in the generation process.
seed*	integer	The random seed used for the generation process.
lyrics*	string	The lyrics used in the generation process.

Types

1 $defs

Fileobject

file_size	integer	The size of the file in bytes.	nullable
content_type	string	The mime type of the file.	nullable
url*	string	The URL where the file can be downloaded from.
file_name	string	The name of the file. It will be auto-generated if not provided.	nullable

Validate a payload

before you spend tokens

shell

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