# MiniMax Music-01 - Core.Today AI API

> MiniMax Music-01 via Replicate. Quickly generates up to 1 minute of music with lyrics and vocals in the style of a reference track. Give a song, voice and/or instrumental reference file (WAV or MP3 longer than 15 seconds) and optional lyrics.

- **Provider**: MiniMax
- **Model ID**: minimax/music-01
- **Category**: Audio & TTS
- **Credits**: 82 per generation
- **Speed**: Fast
- **Quality**: Standard

## Features
- Style transfer from a reference song, voice or instrumental
- Up to 1 minute per generation
- Voice-only reference gives an a cappella; instrumental-only gives an instrumental
- 82 credits per generation

## Use Cases
- Songs in the style of an existing track
- Singing new lyrics with a reference voice
- Quick covers and remix sketches

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Optional
- **lyrics**: string - Lyrics with optional formatting: newline per line, blank line per section, [intro] [verse] [chorus] [bridge] [outro] tags
- **song_file**: string - Reference song containing music and vocals (WAV/MP3 longer than 15s)
- **voice_file**: string - Voice reference (WAV/MP3 longer than 15s). Alone it produces an a cappella
- **instrumental_file**: string - Instrumental reference (WAV/MP3 longer than 15s). Alone it produces an instrumental
- **sample_rate**: integer (default: 44100) - Sample rate for the generated music
  Options: 16000, 24000, 32000, 44100
- **bitrate**: integer (default: 256000) - Bitrate for the generated music
  Options: 32000, 64000, 128000, 256000

## Examples

### Core.Today song in a reference style
Same lyrics sung in the style of the MiniMax Music 2.6 company song used as the reference
```json
{
  "model": "minimax/music-01",
  "input": {
    "lyrics": "[verse]\n아침부터 AI, 커피보다 진해\n코딩하다 보니 벌써 새벽 두 시네!\n안 되는 건 없어, 일단 만들어 봐\n상상이 현실 되는 마법 같은 회사!\n\n[chorus]\n코어! 닷! 투데이!\n오늘의 상상이 내일의 기술로!\n코어! 닷! 투데이!\nAI도 놀라는 우리의 아이디어!",
    "song_file": "https://files.core.today/aiapi/94bbce570e24c705/public/pwHULgjyXBJdRg9ba0MHHQ99Wca61CgM/0.mp3"
  }
}
```

### Song in a reference style
New lyrics sung in the style of a reference jazz track generated by MiniMax Music 1.5
```json
{
  "model": "minimax/music-01",
  "input": {
    "lyrics": "[intro]\n\nUpload my heart to the digital sky\nAlgorithm love, you make me feel so high\n\n[chorus]\nYour neural network's got me feeling so alive",
    "song_file": "https://files.core.today/aiapi/94bbce570e24c705/public/qvqGcyWS6iAq46kbXHkeAYgnJNFVFE6d/0.mp3"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Reference files must be longer than 15 seconds
- Combine voice_file and instrumental_file to control the singer and the backing separately
- Output is at most about one minute — for full songs use Music 1.5 / 2.5 / 2.6