GET
/v1/schemas/fal/audio/mureka/v9/generate/song
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace0e5e1eff136b266bc5234b27dbb04ce00f0f243bf29b5ba6c1b0465c9bdf0d9d{
"fetchedAt": 1793422802,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
8 properties · 0 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| gender | enum | Preferred vocal gender for lyrics-to-song generation. An uploaded or cloned voice takes precedence. | female | male · nullable |
| vocal_id | string | Voice ID returned by /voice/clone. | length ≥ 1 · nullable |
| styles | enum[] | One or more musical genres for prompt-to-song generation. This cannot be used when lyrics is provided. | items ≥ 1 · nullable |
| reference_id | string | Reference-music ID returned by /files/upload with purpose='reference'. | length ≥ 1 · nullable |
| lyrics | string | Lyrics to sing, up to 5,000 characters. Provide this for lyrics-to-song generation; otherwise provide prompt for prompt-to-song generation. | length ≥ 1 · length ≤ 5000 · nullable |
| prompt | string | Describe the desired song, mood, instrumentation, and vocals. Required when lyrics is omitted, up to 2,000 characters. With lyrics, it acts as a music-style control and supports up to 1,024 characters. | length ≥ 1 · length ≤ 2000 · nullable |
| melody_id | string | Melody ID returned by /files/upload with purpose='melody'. This cannot be combined with prompt, reference_id, or vocal_id. | length ≥ 1 · nullable |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. | default: true |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"mureka/v9/generate/song","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}