



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-1.5',
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-1.5',
'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
Discover MiniMax Music 1.5 API: Advanced AI Music Generation
Unlock the power of AI music creation with MiniMax Music 1.5, an innovative API designed to generate complete, original songs up to 4 minutes long. This advanced model transforms your text prompts and optional reference audio into high-fidelity musical pieces, featuring natural vocals, authentic ethnic instruments, and live-style arrangements. It supports custom lyrics and generates music across diverse genres and multicultural styles, making it ideal for various applications, from soundtracks to advertising and professional music production.
✨ Technical Specifications
- • Maximum Output Length: Approximately 4 minutes per generation, delivering substantial musical content.
- • Flexible Input: Supports detailed text prompts for music style, mood, and optional custom lyrics, plus reference audio.
- • Model Architecture: Utilizes an advanced multimodal deep learning approach, combining text understanding with sophisticated audio generation pipelines.
- • Lyrical Language Support: Primarily English and Chinese, with potential for further multilingual extensions.
📈 Performance Benchmarks
- • Produces coherent, emotionally expressive songs with smooth transitions and rich instrumental layers.
- • Achieves high realism in vocal synthesis, delivering clear timbre and expressive nuances surpassing previous model versions.
- • Demonstrates exceptional versatility across multiple music genres with culturally authentic instrument sounds.
- • Generation time optimized to efficiently support interactive and production workflows.
- • Outperforms comparable models in maintaining style consistency when guided by reference audio.
💡 Key Features of MiniMax Music 1.5 API
- ✅ Natural Vocals: Synthesizes expressive, smooth, and natural singing voices, seamlessly integrated with instrumental accompaniment.
- 🎶 Multi-Genre Support: Comprehensive coverage including pop, rock, jazz, classical, electronic, R&B, and diverse ethnic music with authentic instrumentation.
- ✍️ Custom Lyrics Integration: Easily add your user-provided lyrics to generate matching melodies and vocal delivery.
- 🌍 Multilingual & Multicultural Styles: Supports lyrics in multiple languages (including English and Chinese) and accommodates various cultural music styles.
- 🔊 Reference Audio Guidance: Input existing tracks to influence style, tempo, and arrangement, ensuring consistent, personalized outputs.
- 🎛️ Fine-Grained Control: Text prompts allow precise control over style, mood, emotional expression, and segment-level song structure.
- 🏆 High Audio Quality: Delivers studio-grade audio, perfect for commercial use and professional productions.
MiniMax Music 1.5 API Pricing
💲 $0.0315 per music generation (up to 4 minutes)
🎯 Versatile Use Cases
- 🎬 Soundtrack Production: Create high-quality original compositions for film, TV, and gaming.
- 🎥 Video Content: Generate engaging background music for YouTube, social media, and corporate videos.
- 🎤 Music Creation: Support virtual idols, produce demo tracks, and assist professional songwriting.
- 📢 Advertising & Branding: Craft custom music for commercials, corporate identity, and events.
- 📚 Education & Training: Develop musical content for language learning, practice sessions, and creative workshops.
- 🎮 Interactive Media: Create dynamic game sound effects and real-time music generation experiences.
💻 API Code Samples
Generation Code Sample:
<snippet data-name="audio.create-generation-minimax-15" data-model="minimax/music-1.5"></snippet>
Output Code Sample:
<snippet data-name="audio.fetch-generation" data-model="minimax/music-1.5"></snippet>
MiniMax Music 1.5 vs. Leading AI Music Models
↔️ MiniMax Music 1.5 vs. Suno AI
MiniMax excels in delivering predictable, consistent full-length songs up to 4 minutes, with superior natural vocals guided by reference audio. It prioritizes strong genre fidelity and vocal clarity. Suno AI, while offering greater creative flexibility and dynamic style variation, tends to produce less predictable outcomes, supporting more experimental music generation styles.
↔️ MiniMax Music 1.5 vs. Google Lyria 2
MiniMax stands out with its vocal expressiveness and authentic ethnic instruments, coupled with a clear song structure (Intro, Verse, Chorus, Bridge, Outro). Google Lyria 2 is renowned for highly controllable, professional-grade instrumental music and nuanced creative controls like BPM and key signature, targeting producers focused on deep instrumental customization. MiniMax provides an end-to-end solution with robust vocal expressiveness and multi-genre coverage.
↔️ MiniMax Music 1.5 vs. OpenAI Jukebox
MiniMax generates polished, studio-quality songs with focused vocal and instrumental clarity within 4 minutes, supporting user lyrics input. OpenAI Jukebox produces diverse stylistic music samples but often struggles with long coherent song structures and natural vocal quality. MiniMax offers more refined and commercially usable audio, whereas Jukebox is better suited for creative explorations and genre experiments.
❓ Frequently Asked Questions (FAQ)
MiniMax Music 1.5 is an advanced AI model specialized in music generation, capable of creating both singing vocals and instrumental music through text prompts and optional reference audio.
The model can generate complete songs up to approximately 4 minutes per request, providing substantial content for various creative and commercial uses.
Yes, MiniMax Music 1.5 supports custom lyric integration. You can provide your own lyrics for the AI to generate matching melodies and vocal delivery, available primarily in English and Chinese.
MiniMax offers more predictable and consistent full-length songs with superior natural vocals and strong genre fidelity, especially when guided by reference audio. While Suno AI allows more experimental styles and Lyria 2 offers deep instrumental control, MiniMax provides an end-to-end solution with robust vocal expressiveness and clear song structures, ideal for commercial production.
It is highly versatile, ideal for soundtrack production (film, TV, games), video content creation (YouTube, social media), professional music creation (demos, virtual idols), advertising, education, and interactive media applications requiring high-quality original compositions.
Learn how you can transformyour company with AICC APIs



Log in