# MiniMax Music 1.5 - Core.Today AI API

> MiniMax Music 1.5 via Replicate. Full-length songs up to 4 minutes with natural vocals and rich instrumentation from a style prompt and structured lyrics. The previous generation to Music 2.5 / 2.6 at a fifth of the price.

- **Provider**: MiniMax
- **Model ID**: minimax/music-1.5
- **Category**: Audio & TTS
- **Credits**: 70 per song
- **Speed**: Medium
- **Quality**: Standard

## Features
- Full songs up to 4 minutes with vocals
- Structured lyrics with [intro] [verse] [chorus] [bridge] [outro] tags
- MP3 or WAV output with sample rate and bitrate control
- 70 credits per song

## Use Cases
- Budget demos from written lyrics
- Volume generation of song variations
- Jingles with sung lyrics

## 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

### Required
- **prompt**: string - Style prompt (genre, mood, instruments). Must be 10-300 characters — shorter or longer is rejected with 400
- **lyrics**: string - Lyrics, one line per newline, with [intro] [verse] [chorus] [bridge] [outro] tags. Must be 10-600 characters counting tags, line breaks and spaces — longer lyrics are rejected with 400, not trimmed

### Optional
- **audio_format**: string (default: mp3) - Audio format of the output
  Options: mp3, wav
- **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 company song
The same Korean company-song lyrics given to every music model — compare how each one sings them
```json
{
  "model": "minimax/music-1.5",
  "input": {
    "prompt": "Bright upbeat K-pop electro-pop company jingle, 128 BPM, energetic female vocals, catchy chant chorus, synth brass, punchy drums",
    "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[chorus]\n코어! 닷! 투데이!\n오늘의 상상이 내일의 기술로!\n코어! 닷! 투데이!\nAI도 놀라는 우리의 아이디어!\n[outro]\n뚝딱뚝딱 만들고, 반짝반짝 빛내고!\n기술을 넘어 경험으로!\n코어닷투데이, Hey!",
    "audio_format": "mp3"
  }
}
```

### Lazy jazz ballad
Short tagged lyrics with a jazz style prompt
```json
{
  "model": "minimax/music-1.5",
  "input": {
    "prompt": "Lazy late-night jazz, warm male vocals, brushed drums, upright bass, soft piano",
    "lyrics": "[verse]\nIn the hush of night we find our space,\nwrapped in moonlight's gentle embrace.\n[chorus]\nJust you and me in this lazy jazz,\nour souls entwined, nothing else we ask.",
    "audio_format": "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
- Both prompt (10-300 chars) and lyrics (10-600 chars) are required — the limits are hard: out-of-range text returns 400 instead of being trimmed
- Keep section tags on their own lines
- 600 characters is roughly 2-3 verses plus a chorus — for longer lyrics use minimax/music-2.5 or 2.6, which accept up to 3,500 characters