# MiniMax Music 3.0

MiniMax Music 3.0 creates complete songs from prompts, lyrics, or instrumental direction, producing MP3 tracks for video, game, and app soundtracks.

## API Information

- **Model Slug:** minimax-music-03
- **Branded URL:** https://www.eachlabs.ai/minimax/minimax-music/minimax-music-03
- **Provider:** Minimax
- **Category:** Music Generation
- **Output Type:** audio
- **Status:** active
- **Base Cost:** $0.15 per execution
- **Estimated Processing Time:** 60 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/minimax-music-03

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.15 per execution
- **Pricing Details:** default: $0.15

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| lyrics | string | No | [Verse] City lights are fading slow Rain is tapping on my window Midnight thoughts I can't ignore Your name echoes even more  [Chorus] Dancing in the afterglow Of a love we used to know Pop melodies and broken hearts We shine bright even in the dark | - | Song lyrics. Use \n to separate lines. Supports structure tags such as [Intro], [Verse], [Pre Chorus], [Chorus], [Bridge], and [Outro]. |
| prompt | string | No | Pop, melancholic, atmospheric, female vocal, emotional, soft synths, light piano, slow tempo, rainy night mood. | - | Style, mood, instruments, voice, and scenario for the generated song. |
| lyrics_optimizer | boolean | No | false | - | When true, MiniMax can automatically generate lyrics from the style prompt if lyrics are empty. |
| is_instrumental | boolean | No | false | - | Generate instrumental music without vocals. |
| audio_settings | object | No | {"bitrate":256000,"format":"mp3","sample_rate":44100} | - | - |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-music-03",
  "input": {}
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated audio)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**MiniMax Music 3.0 Overview**

MiniMax Music 3.0 is a next-generation **music-generation** model from Minimax that turns creative concepts and optional lyrics into fully produced, studio-quality songs in a single pass. As the flagship of the **minimax-music** family, it replaces earlier versions such as MiniMax Music 2.6 and is now the recommended text-to-music model for both API users and open-weight workflows. Its primary differentiator is long-form, structurally coherent songs of up to about five minutes, with expressive vocals, evolving arrangements, and stable audio quality over the full track. Integrated into each::labs, MiniMax Music 3.0 lets you generate vocal songs, instrumentals, or automatically written lyrics and export them as standard audio formats suitable for streaming, editing, and distribution.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.