# Minimax Music | V1.5

MiniMax Music v1.5 turns simple text prompts into high-quality, expressive music. It offers a wide range of styles and moods, creating melodies and rhythms that feel natural and engaging.

## API Information

- **Model Slug:** minimax-music-v1-5
- **Branded URL:** https://www.eachlabs.ai/minimax/minimax-music/minimax-music-v1-5
- **Provider:** MiniMax
- **Category:** Text to Voice
- **Output Type:** audio
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** $0.03 per execution
- **Estimated Processing Time:** 25 seconds
- **Last Updated:** 2026-06-08
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/minimax-music-v1-5

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.03 per execution
- **Pricing Details:** default: $0.03

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Lyrics, supports [intro][verse][chorus][bridge][outro] sections. 10-600 characters. |
| lyrics_prompt | string | Yes | - | - | Control music generation. 10-3000 characters. |

## 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-v1-5",
  "input": {
    "prompt": "[verse]  \nIn the heart of creation, where ideas ignite,  \nEachlabs is shining, taking brands to new heights.  \nFrom images to videos, the magic we design,  \nTech with a rhythm, innovation on the line.  \n\n[chorus]  \nEachlabs, the future, the flow, the vibe,  \nTurning every vision into something alive.  \nFast, fearless, building dreams that last,  \nWith rhythm and soul, we’re moving so fast.",
    "lyrics_prompt": "R&B, energetic"
  }
}'
```

## 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-v1.5 — Text-to-Audio AI Model**

Developed by Minimax as part of the **minimax-music** family, **minimax-music-v1.5** transforms simple text prompts into complete, professional-grade songs up to 4 minutes long, solving the challenge of rapid music creation for creators without instruments or studios. This **text-to-voice AI model** excels in generating natural vocals, rich instrumentation, and structured tracks with lyrics, making it ideal for **Minimax text-to-voice** applications in content production. Users input a music prompt describing style, mood, and scenario—plus optional structured lyrics—and receive high-fidelity audio in formats like MP3 or WAV within 1-2 minutes.

## 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.