GET

/v1/schemas/fal/audio/fal-ai/minimax-music/v2.5

Accept:

kind inputactivity audiohash 573dd025…extracted Oct 9, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `d0b554d9e8a833c631ae5e4cc2792ace745b8c08b85c4a7e9b5e8d6210ce19dd` { "fetchedAt": 1791522002, "extractorVersion": "1", "verifiedAt": null }

Request body

6 properties · 1 required · 1 $defs

property	type	description	constraints
prompt*	string	A description of the music style, mood, genre, and scenario. Max 2000 characters.	length ≥ 1 · length ≤ 2000
lyrics	string	Lyrics of the song. Use \n to separate lines. Supports structure tags: [Intro], [Verse], [Pre Chorus], [Chorus], [Bridge], [Outro], [Interlude], [Hook], [Break], [Solo], [Inst]. Max 3500 characters. Required when is_instrumental is false and lyrics_optimizer i…	length ≤ 3500 · default: ""
is_instrumental	boolean	When true, generates vocal-free instrumental music.	default: false
lyrics_optimizer	boolean	When true and lyrics is empty, auto-generates lyrics from the prompt.	default: false
audio_setting	AudioSetting25	Audio configuration settings
enable_safety_checker	boolean	Authorized callers may set false to request relaxed screening.	default: true

Types

1 $defs

AudioSetting25object

bitrate	enum	Bitrate of generated audio	32000 \| 64000 \| 128000 \| 256000 · default: 256000
sample_rate	enum	Sample rate of generated audio	16000 \| 24000 \| 32000 \| 44100 · default: 44100
format	enum	Audio format	mp3 \| wav \| pcm · default: "mp3"

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/minimax-music/v2.5","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}