API docs / Audio models

music-01 API

Generate music with lyrics and vocals based on a reference track style. Analyzes uploaded reference music to learn musical patterns, rhythms, and vocal characteristics, then creates new compositions up to 60 seconds long that incorporate the learned style. Supports multiple genres including classical, pop, rock, and electronic music. Takes lyrics as input (up to 400 characters) and can generate both accompaniment and vocals simultaneously. Allows reuse of previously processed voice and instrumental references through ID system. Suitable for film and TV soundtrack creation, AI singer compositions, musical reinterpretations, and general music production.

Model id
minimax/music-01
Provider
minimax
Output
Audio
Price
From 13 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "minimax/music-01". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "minimax/music-01",
  "input": {},
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
voicestring

Reuse a previously uploaded voice ID

bitratenumber

Default: 256000

One of: 32000, 64000, 128000, 256000

instrumental_filearray of URLs

Instrumental reference. Must be a .wav or .mp3 file longer than 15 seconds. If only an instrumental reference is given, a track without vocals will be generated. Each file: over 15s.

Up to 1 files · Accepts audio/*

instrumental_idstring

Reuse a previously uploaded instrumental ID

lyricsstring

Lyrics with optional formatting. You can use a newline to separate each line of lyrics. You can use two newlines to add a pause between lines. You can use double hash marks (##) at the beginning and end of the lyrics to add accompaniment. Maximum 350 to 400 characters.

Default:

sample_ratenumber

Default: 44100

One of: 16000, 24000, 32000, 44100

song_filearray of URLs

Reference song, should contain music and vocals. Must be a .wav or .mp3 file longer than 15 seconds. Each file: over 15s.

Up to 1 files · Accepts audio/*

voice_filearray of URLs

Voice reference. Must be a .wav or .mp3 file longer than 15 seconds. If only a voice reference is given, an a cappella vocal hum will be generated. Each file: over 15s.

Up to 1 files · Accepts audio/*