Name: MiniMax Music API
Brand: Hailuo AI

Overview

MiniMax Music Description

Basic Information

Model Name: MiniMax Music
Developer/Creator: Hailuo AI
Release Date: August 2024
Version: 1.0
Model Type: AI Music Generation Model

Overview:

MiniMax Music is an advanced AI model developed by Hailuo AI that generates high-quality music from text prompts. This model allows users to create diverse musical compositions by analyzing and reproducing musical patterns, rhythms, and vocal styles from reference tracks.

Key Features:

Simultaneous Accompaniment and Vocals: Generates both accompaniment and vocals simultaneously, creating a complete musical piece.
Style Learning from Reference Tracks: Users can upload reference music to guide the style of the generated music.
Lyrics-to-Music Generation: Converts lyrics into music, allowing users to create songs with ease.
Multiple Genre Support: Supports various genres including classical, pop, rock, electronic, and more.
Maximum Output Duration: Currently limited to 60 seconds, with plans to extend to 3 minutes in future releases.

Intended Use:

The MiniMax Music model is designed for music producers, film/TV soundtrack creators, AI singer compositions, and anyone looking to generate music for various applications such as musical reinterpretations and general music production.

Language Support:

The model primarily supports English for text prompts but can accommodate multiple languages depending on user requirements.

Technical Details

Architecture:

MiniMax Music utilizes deep learning techniques to analyze and reproduce musical patterns, rhythms, and vocal styles from reference tracks.

Training Data:

The model was trained on a diverse dataset of music tracks to ensure robust performance across different genres and styles.

Data Source and Size: The training dataset includes a wide range of musical styles, although specific sizes are not disclosed.
Diversity and Bias: The training data was curated to minimize biases while maximizing diversity in musical styles, enhancing the model's effectiveness in generating varied outputs.

Performance Metrics:

MiniMax Music has demonstrated strong performance metrics:

Metric	Score
Music Quality	High
Maximum Output Duration	60 seconds

Usage

Code Samples

The model is available on the AI/ML API platform as "MiniMax Music" .

Upload an audio

To get the generated audio

API Documentation

Detailed API Documentation is available here.

Ethical Guidelines

Hailuo AI emphasizes ethical considerations in AI development by promoting transparency regarding the model's capabilities and limitations. The organization encourages responsible usage to prevent misuse or harmful applications of generated music.

Licensing

The MiniMax Music model is available under a commercial license that allows both research and commercial usage rights while ensuring compliance with ethical standards regarding creator rights.

Get MiniMax Music API here.

‍

Use cases

Full Song Creation: Upload a reference + lyrics to produce complete vocal-instrumental songs
Instrumental Backgrounds: Generate music aligned with a reference track for media projects
Remixing: Reinterpret existing music in new genres while maintaining core melody
Lyric-based Music: Turn poetry into music using lyric prompts
Virtual Vocalist: Create synthetic vocal performances for demos or AI singing

‍

How to use MiniMax Music API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to minimax-music.

import requests, time

headers = {"Authorization": "Bearer " + AIMLAPI_KEY}
job = requests.post(
    "https://api.aimlapi.com/v2/generate/audio",
    headers=headers,
    json={
      "model": "minimax-music",
      "prompt": "Upbeat lofi background music"
    },
).json()
gid = job["generation_id"]

while True:
    res = requests.get(f"https://api.aimlapi.com/v2/generate/audio?generation_id={gid}", headers=headers).json()
    if res.get("status") in ("completed", "error", "failed"):
        break
    time.sleep(3)
print(res)

const headers = {
  Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
  "Content-Type": "application/json",
};
const job = await (await fetch("https://api.aimlapi.com/v2/generate/audio", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "minimax-music",
    "prompt": "Upbeat lofi background music"
  }),
})).json();

let res;
do {
  await new Promise((r) => setTimeout(r, 3000));
  res = await (await fetch(`https://api.aimlapi.com/v2/generate/audio?generation_id=${job.generation_id}`, { headers })).json();
} while (!["completed", "error", "failed"].includes(res.status));
console.log(res);

# submit the job — the response contains "generation_id"
curl -X POST https://api.aimlapi.com/v2/generate/audio \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax-music","prompt":"Upbeat lofi background music"}'

# then poll for the result until it is ready
curl "https://api.aimlapi.com/v2/generate/audio?generation_id={generation_id}" -H "Authorization: Bearer $AIMLAPI_KEY"

OpenAI-compatible — swap the base URL and it works with your existing SDK.