GET

/v1/schemas/fal/audio/fal-ai/lyria3

Accept:

kind inputactivity audiohash 1b3fcbc1…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `2df6fdcf799d40c61539154022ac9a45bef1112ab811ad9fbcf4fdac05bc8b62` { "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. Include genre, mood, instrumentation, tempo, and vocal style for best results. Lyria 3 supports vocals, lyrics, and multi-language generation.	length ≥ 1 · length ≤ 5000
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true
image_url	string	Optional image URL to use as inspiration for music generation. The model will create music that matches the mood and theme of the image.	nullable
negative_prompt	string	Negative prompting is not supported by Lyria 3.	default: "" · deprecated

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/lyria3","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}