GET

/v1/schemas/fal/audio/fal-ai/lyria2

Accept:

kind inputactivity audiohash 8d463803…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `9a282657d9a33cd5205fc3d9fc0fac86187283e7e8499b46401c8d489fc1aced` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

4 properties · 1 required · 0 $defs

property	type	description	constraints
prompt*	string	The text prompt describing the music you want to generate	length ≥ 1 · length ≤ 2000
seed	integer	A seed for deterministic generation. If provided, the model will attempt to produce the same audio given the same prompt and other parameters.	nullable
negative_prompt	string	A description of what to exclude from the generated audio	default: "low quality"
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/lyria2","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}