Enterprise Plans
AI Application Development
AI Translator API
AI SEO/GEO Service
Web Scraping Service
Log in
import fs from "fs";
import fetch from "node-fetch";
const main = async () => {
const url = "https://api.ai.cc/v2/generate/audio/minimax/generate";
const voiceId = "vocal-2025010100000000-a0AAAaaa";
const referInstrumental = "instrumental-2025010100000000-Aaa0aAaA";
const lyrics = `##Swift and Boundless \n In the realm of innovation, where visions align, \n\nAIML API's the name, making tech shine.
\nIntelligent solutions, breaking the mold, \n\nSwift inference power, bold and untold.\n##`;
const payload = {
refer_voice: voiceId,
refer_instrumental: referInstrumental,
lyrics: lyrics,
model: 'music-01'',
};
const headers = {
"Content-Type": "application/json",
"Authorization": `Bearer `,
};
try {
const response = await fetch(url, {
method: "POST",
headers: headers,
body: JSON.stringify(payload),
});
const data = await response.json();
if (response.ok) {
const audioHex = data.data.audio;
const decodedHex = Buffer.from(audioHex, "hex");
fs.writeFileSync("generated_audio.mp3", decodedHex);
console.log("Audio file saved as generated_audio.mp3");
} else {
console.error("Failed to generate music:", data);
}
} catch (error) {
console.error("Error during API request:", error);
}
}
main();
import requests
def main():
url = 'https://api.ai.cc/v2/generate/audio/minimax/generate'
voice_id = 'vocal-2025010100000000-a0AAAaaa'
refer_instrumental = 'instrumental-2025010100000000-Aaa0aAaA'
lyrics = '''
##Swift and Boundless \n In the realm of innovation, where visions align, \n\nAIML API's the name, making tech shine.
\nIntelligent solutions, breaking the mold, \n\nSwift inference power, bold and untold.\n##
'''
payload = {
'refer_voice': voice_id,
'refer_instrumental': refer_instrumental,
'lyrics': lyrics,
'model': 'music-01',
}
headers = {
'Content-Type': 'application/json',
'authorization': 'Bearer ',
}
response = requests.post(url, headers=headers, json=payload)
audio_hex = response.json()['data']['audio']
decoded_hex = bytes.fromhex(audio_hex)
with open('generated_audio.mp3', 'wb') as f:
f.write(decoded_hex)
if __name__ == '__main__':
main()
-
AI Playground
Test all API models in the sandbox environment before you integrate.
We provide more than 300 models to integrate into your app.
Product Detail
🎵 Discover MiniMax Music: Your Advanced AI Music Generation Solution
Developed by Hailuo AI, MiniMax Music is a cutting-edge AI model, officially released in August 2024 (Version 1.0). This innovative platform specializes in generating high-quality musical compositions from simple text prompts. It offers users the unique ability to create diverse tracks by analyzing and replicating intricate musical patterns, rhythms, and vocal styles from provided reference tracks.
Model Name: MiniMax Music
Developer/Creator: Hailuo AI
Release Date: August 2024
Version: 1.0
Model Type: AI Music Generation Model
✨ Key Features Driving Musical Innovation
-
🎤
Simultaneous Accompaniment and Vocals: Generates complete musical pieces by creating both instrumental accompaniment and vocal tracks simultaneously.
-
🎶
Style Learning from Reference Tracks: Users can upload their own reference music to guide the AI, ensuring the generated output aligns with a specific desired style.
-
📝
Lyrics-to-Music Generation: Seamlessly converts written lyrics into full musical compositions, streamlining the songwriting process.
-
🎸
Multiple Genre Support: Supports a diverse range of genres, including classical, pop, rock, electronic, and many more, catering to varied musical tastes.
-
⏱️
Maximum Output Duration: Currently capable of generating up to 60 seconds of music, with future releases planned to extend this to 3 minutes.
💡 Who Benefits from MiniMax Music?
The MiniMax Music model is an invaluable tool crafted for a wide array of creators and professionals, including:
- • Music Producers seeking fresh ideas and efficient workflow.
- • Film/TV Soundtrack Creators in need of bespoke musical scores.
- • AI Singer Composers looking to bring virtual artists to life.
- • Anyone interested in generating unique music for reinterpretations or general production.
While the model primarily supports English for text prompts, it is designed to accommodate multiple languages based on specific user requirements.
⚙️ Technical Foundation & Architecture
Architecture Overview
MiniMax Music harnesses sophisticated deep learning techniques. This advanced architecture enables the model to meticulously analyze and accurately reproduce complex musical patterns, rhythms, and vocal styles extracted from an extensive library of reference tracks.
Training Data Insights
The model's exceptional and robust performance across a spectrum of genres and styles is attributed to its intensive training on a highly diverse dataset of music tracks.
-
•
Data Source and Size: The training dataset comprises a wide range of musical styles, ensuring versatility. Specific dataset sizes are not publicly disclosed by Hailuo AI.
-
•
Diversity and Bias Management: The training data was carefully curated to maximize diversity in musical styles while actively minimizing potential biases, thereby enhancing the model's effectiveness in generating varied and fair outputs.
📊 Verified Performance Metrics
MiniMax Music has consistently demonstrated impressive performance metrics since its release:
Note: The above metric presentation is designed for optimal readability across various devices.
🚀 Getting Started with MiniMax Music API
Code Samples and API Access
The MiniMax Music model is conveniently accessible on the AI/ML API platform. Look for it under its official name: "MiniMax Music".
How to Upload Audio (Snippet)
<snippet data-name="minimax.upload-audio"></snippet>How to Get Generated Audio (Snippet)
<snippet data-name="minimax.create-audio-generation" data-model="music-01"></snippet>Comprehensive API Documentation
For detailed technical specifications, integration guides, and further information, please refer to the Official API Documentation.
💰 Transparent API Pricing
- • Experience seamless music generation at an affordable rate of $0.03675 per generation.
🛡️ Ethical Use & Commercial Licensing
Ethical Guidelines
Hailuo AI is deeply committed to ethical AI development. We promote utmost transparency regarding MiniMax Music's capabilities and inherent limitations. Users are strongly encouraged to engage in responsible usage to prevent any potential misuse or harmful applications of the generated music.
Licensing Information
The MiniMax Music model is distributed under a comprehensive commercial license. This license grants extensive rights for both academic research and commercial applications, ensuring full compliance with ethical standards concerning creator rights and intellectual property.
Ready to integrate advanced AI music generation into your projects?
Get MiniMax Music API Access Here!❓ Frequently Asked Questions (FAQ)
A1: MiniMax Music is an advanced AI model developed by Hailuo AI. It generates high-quality music, including both accompaniment and vocals, from text prompts and can learn styles from reference tracks.
A2: Currently, MiniMax Music can generate musical outputs up to 60 seconds in duration. Hailuo AI has plans to extend this capability to 3 minutes in future releases.
A3: Yes, a key feature allows users to upload their own reference music. MiniMax Music will then analyze these tracks to guide the style of the generated output, ensuring it matches your desired aesthetic.
A4: MiniMax Music is ideally suited for music producers, creators of film and TV soundtracks, developers of AI singer compositions, and anyone seeking to generate unique music for various production or reinterpretation purposes.
A5: The MiniMax Music API is priced at an economical rate of $0.03675 per music generation.
Learn how you can transformyour company with AICC APIs
