



const main = async () => {
const response = await fetch('https://api.ai.cc/v2/generate/audio', {
method: 'POST',
headers: {
Authorization: 'Bearer ',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'minimax/music-2.0',
prompt: 'A calm and soothing instrumental music with gentle piano and soft strings.',
lyrics: `[Verse]\nStreetlights flicker, the night breeze sighs\nShadows stretch as I walk alone\nAn old coat wraps my silent sorrow\nWandering, longing, where should I go\n[Chorus]\nPushing the wooden door, the aroma spreads\nIn a familiar corner, a stranger gazes back\nWarm lights flicker, memories awaken\nIn this small cafe, I find my way\n[Verse]\nRaindrops tap on the windowpane\nA melody plays, soft and low\nThe clink of cups, the murmur of dreams\nIn this haven, I find my home\n[Chorus]\nPushing the wooden door, the aroma spreads\nIn a familiar corner, a stranger gazes back\nWarm lights flicker, memories awaken\nIn this small cafe, I find my way`,
}),
}).then((res) => res.json());
console.log('Generation:', response);
};
main()
import requests
def main():
response = requests.post('https://api.ai.cc/v2/generate/audio', headers={
'Authorization': 'Bearer ',
'Content-Type': 'application/json',
}, json={
'model': 'minimax/music-2.0',
'prompt': 'A calm and soothing instrumental music with gentle piano and soft strings.',
'lyrics': '''[Verse]
Streetlights flicker, the night breeze sighs
Shadows stretch as I walk alone
An old coat wraps my silent sorrow
Wandering, longing, where should I go
[Chorus]
Pushing the wooden door, the aroma spreads
In a familiar corner, a stranger gazes back
Warm lights flicker, memories awaken
In this small cafe, I find my way
[Verse]
Raindrops tap on the windowpane
A melody plays, soft and low
The clink of cups, the murmur of dreams
In this haven, I find my home
[Chorus]
Pushing the wooden door, the aroma spreads
In a familiar corner, a stranger gazes back
Warm lights flicker, memories awaken
In this small cafe, I find my way''',
}).json()
print('Generation:', response)
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
✨ Unlock creativity with the MiniMax Music 2.0 API, a revolutionary tool that transforms text prompts and lyrics into studio-quality music tracks up to 5 minutes long. This advanced model seamlessly integrates neural audio synthesis with sophisticated language understanding to produce natural vocals, rich instrumentals, and professional arrangements.
🎵 Technical Specifications
- • Model Architecture: Large-scale autoregressive Transformer, meticulously optimized for superior music and audio generation.
- • Multimodal Support: Effortlessly processes both text (lyrics, style prompts) and diverse audio elements for comprehensive music creation.
- • Audio Output Quality: Delivers CD-quality stereo audio at a 44.1 kHz sample rate, with configurable bitrate up to 256 kbps MP3.
- • Track Length: Generate up to 5 minutes of continuous music in a single, seamless generation.
- • Instrument Control: Enjoy independent control over multiple instrument tracks, including guitar, drums, synthesizers, and more.
- • Vocal Styles: Supports a wide array of singing styles and intricate emotional expressions.
🚀 Performance Benchmarks
- • Extended Track Duration: Outperforms competitors by generating significantly longer tracks, up to 5 minutes, rather than short clips.
- • Superior Audio Fidelity: Delivers high-quality stereo output at a standard CD sample rate, ensuring rich and immersive sound.
- • Efficient Processing: Optimized for fast generation while meticulously maintaining complex musical detail.
⭐ Key Features
- • Human-like Vocals: Experience clear, natural-sounding singing with remarkable emotional nuance.
- • Instrument Separation: Individual instrument track manipulation allows for detailed arrangement control.
- • Full Song Structure: Capability to generate complex song sections like intros, verses, choruses, bridges, and outros with consistent musical motifs.
- • Style and Mood Control: Users can easily specify musical style, mood, tempo, and other creative attributes using plain language prompts.
- • Hybrid Inputs: Combine text prompts with optional audio references for tailored sound and arrangement.
💰 MiniMax Music 2.0 API Pricing
$0.0315 per track for up to 5 minutes of generated music.
💼 Use Cases
- • Music Producers: Rapid prototyping and production of full songs with minimal manual sequencing.
- • Content Creators: Generate custom music for videos, games, podcasts, and streaming platforms.
- • App Developers: Seamlessly embed dynamic music generation capabilities into your applications and services.
- • Advertising & Media: Create tailored soundtracks perfectly aligned with campaign moods and themes.
- • Educational Tools: Enhance music composition and arrangement learning with AI-assisted workflows.
⚙️ Code Samples
Generation Code Sample
<snippet data-name="audio.create-generation-minimax-15" data-model="minimax/music-2.0"></snippet>
Output Code Sample
<snippet data-name="audio.fetch-generation" data-model="minimax/music-2.0"></snippet>
⚖️ Comparison with Other Models
MiniMax Music 2.0 vs. Suno Music: While Suno focuses on faster generation of shorter, radio-ready pop tracks with highly accessible vocal synthesis, MiniMax Music 2.0 stands out with its ability to generate longer tracks up to 5 minutes and offers more detailed instrument separation.
MiniMax Music 2.0 vs. Stable Audio 2.0: Stable Audio utilizes diffusion-based methods primarily for experimental sound design and precise sonic control. In contrast, MiniMax Music 2.0 is geared towards more conventional song structures and delivers emotional vocals, making it a stronger choice for commercial music production.
MiniMax Music 2.0 vs. Soundverse: Soundverse is recognized for its extensive toolset, including stem separation and auto-complete features, appealing to both hobbyists and professionals. MiniMax Music 2.0 matches Soundverse in audio quality but distinguishes itself with its patented vocal synthesis and capability for longer track generation, up to 5 minutes.
❓ Frequently Asked Questions
Q: What is the maximum length of music MiniMax Music 2.0 can generate?
A: MiniMax Music 2.0 can generate continuous music tracks up to 5 minutes long in a single generation.
Q: Does the API support various vocal styles and emotions?
A: Yes, the API supports a wide range of singing styles and emotional expressions, producing clear and natural-sounding vocals.
Q: Can I control individual instruments in the generated music?
A: Absolutely. MiniMax Music 2.0 offers independent control over multiple instrument tracks, allowing for detailed arrangement and customization.
Q: What is the audio output quality of MiniMax Music 2.0?
A: The API generates CD-quality stereo audio at a 44.1 kHz sample rate, with configurable bitrate up to 256 kbps MP3.
Q: How does MiniMax Music 2.0 compare in price?
A: It is priced at $0.0315 for generating up to 5 minutes of music per track.
Learn how you can transformyour company with AICC APIs



Log in