Cookie Preferences
We use cookies to personalize content and analyze traffic. See our Cookie Policy.
No audio yet. Submit the form to generate audio.
Explore different use cases and parameter configurations
Transparent pricing with no hidden fees. Pay as you go.
| Rule & Modality | Channel | Credits | Price (USD) | Official / Reference Price | Daily Savings |
|---|---|---|---|---|---|
Music generation musicMiniMax | Starter | 0.7per audio | $0.003 | - | - |
Complete guide to using MiniMax Music 1.5
Create original music from lyrics and style descriptions with MiniMax Music 1.5. Support for structured lyrics with tags, flexible audio quality settings, and multiple output formats.
MiniMax Music 1.5 is an AI music generation model that creates complete songs from lyrics and musical style descriptions. The model supports structured lyrics with section tags like [intro], [verse], [chorus], [bridge], and [outro], allowing for sophisticated song composition. Users can control audio quality through sample rate and bitrate settings, and choose from multiple output formats including MP3, WAV, and PCM. The Music 1.5 API makes professional music generation accessible through a simple programmatic interface, enabling developers to integrate AI-powered music creation into applications, content platforms, and creative tools.
The Music 1.5 API supports four sample rate options: 16kHz, 24kHz, 32kHz, and 44.1kHz (CD quality). Higher sample rates provide better frequency response and audio fidelity, while lower rates produce smaller file sizes. The default 44.1kHz setting delivers professional-quality output suitable for most applications.
Choose from four bitrate levels: 32kbps, 64kbps, 128kbps, and 256kbps. Bitrate controls the amount of data used per second of audio, directly affecting file size and audio quality. The default 256kbps setting provides high-quality output with minimal compression artifacts.
The API outputs music in three formats: MP3 (compressed, widely compatible), WAV (uncompressed, highest quality), and PCM (raw audio data). MP3 is recommended for most use cases, balancing quality and file size, while WAV is ideal for professional audio production requiring lossless quality.
The Music 1.5 API recognizes standard song structure tags including [intro], [verse], [chorus], [bridge], and [outro]. This enables the model to generate music with proper song architecture, creating distinct sections with appropriate musical progression and dynamics.
Describe the musical style you want with a text prompt, and Music 1.5 generates audio that matches your description. From acoustic ballads to electronic dance music, the model understands diverse musical genres, instruments, moods, and production styles.
With support for CD-quality 44.1kHz sample rate and 256kbps bitrate, Music 1.5 produces professional-grade audio suitable for commercial use. The model generates clean, well-mixed audio with proper dynamics and frequency balance.
Choose between MP3, WAV, and PCM output formats based on your workflow requirements. MP3 for web distribution, WAV for professional production, or PCM for custom audio processing pipelines.
Get started with AI music generation in just a few simple steps...
Create an account on apipass.dev and obtain your MiniMax Music 1.5 API Key. This key authenticates your requests and enables access to the music generation endpoints.
Use the interactive playground to experiment with different lyrics, musical styles, and audio settings. Test structure tags, explore genre variations, and find optimal quality settings before implementing in production.
Implement the Music 1.5 API in your application, defining how lyrics and style prompts are submitted, and how generated audio files are retrieved and delivered to users. Configure quality settings based on your use case requirements.
Deploy to production with proper asynchronous task handling, status monitoring, and audio file management. Implement storage solutions for generated music and establish delivery mechanisms for end users.
Lyrics must be between 10 and 600 characters. This constraint ensures the model has enough content to create meaningful music while maintaining generation quality and reasonable processing time.
The musical style prompt must be 10-300 characters. Be descriptive but concise, mentioning genre, instruments, mood, and tempo. Examples: 'Upbeat pop with electronic synths', 'Slow jazz ballad with piano and saxophone'.
Leverage structure tags [intro][verse][chorus][bridge][outro] in your lyrics for more professional song composition. The model recognizes these tags and creates appropriate musical variations for each section.
Generate original background music for videos, podcasts, and social media content. Create unique soundtracks that match your content's mood and message without licensing concerns or copyright issues.
Enable songwriters and producers to quickly prototype musical ideas by generating full arrangements from lyrics and style descriptions. Iterate rapidly on concepts before investing in full production.
Build applications that generate custom songs for users based on their input. Create personalized birthday songs, greeting cards with music, or custom jingles for businesses and events.
Develop educational applications that teach music composition, song structure, and lyric writing by generating musical examples. Students can hear how different lyrical and stylistic choices affect the final composition.
apipass.dev provides cost-effective access to MiniMax Music 1.5 with transparent, predictable pricing. Generate professional music at a fraction of traditional production costs, making AI music creation accessible for all project sizes.
Comprehensive API documentation covers all parameters, structure tags, audio quality options, and output formats. Code examples and integration guides help developers implement music generation quickly and correctly.
Around-the-clock support ensures your music generation workflows remain operational. Expert assistance available for integration questions, quality optimization, and troubleshooting.
All APIs require authentication via Bearer Token.
Authorization: Bearer
Create a new Music 1.5 music generation task
The API accepts a JSON payload with the following structure:
1{
2 "model": "minimax/music-1-5",
3 "callBackUrl": "string (optional)",
4 "channel": "auto",
5 "input": {
6 "lyrics": "string (required, 10-600 characters)",
7 "prompt": "string (required, 10-300 characters)",
8 "sample_rate": 16000|24000|32000|44100 (optional, default: 44100),
9 "bitrate": 32000|64000|128000|256000 (optional, default: 256000),
10 "audio_format": "mp3"|"wav"|"pcm" (optional, default: "mp3")
11 }
12}modelRequiredstringThe model name to use for music generation
"minimax/music-1-5"
callBackUrlOptionalstringOptional callback URL for task completion notifications
"https://your-domain.com/api/callback"
channelOptionalstringYou may specify the corresponding provider within APIPASS via the channel parameter; these providers handle the actual image and video generation tasks. APIPASS currently offers three provider options:
The default value for the channel parameter is auto. When enabled, APIPASS automatically allocates tasks across available providers based on real-time pricing and stability metrics to balance minimal cost and reliable performance. Retain the default auto value unless you have custom routing requirements.
Available options:
auto
The input object contains the following parameters:
input.lyricsRequiredstringSong lyrics, 10-600 characters. Supports structure tags: [intro], [verse], [chorus], [bridge], [outro] for better song composition.
Required field, 10-600 characters, supports structure tags
"[verse]\nWalking down the street\nFeeling the beat\n[chorus]\nThis is my song\nCome sing along"
input.promptRequiredstringMusic style description, 10-300 characters. Describe the genre, instruments, mood, and tempo you want.
Required field, 10-300 characters
"Upbeat pop song with electronic beats and catchy melody"
input.sample_rateOptionalintegerAudio sampling rate in Hz. Higher values provide better audio quality. Default is 44100 (CD quality).
Optional, default: 44100
Available options:
44100
input.bitrateOptionalintegerAudio bitrate in bits per second. Higher values provide better audio quality but larger file sizes. Default is 256000.
Optional, default: 256000
Available options:
256000
input.audio_formatOptionalstringOutput audio file format. MP3 is compressed and widely compatible, WAV is uncompressed high quality, PCM is raw audio data. Default is 'mp3'.
Optional, default: 'mp3'
Available options:
"mp3"
1curl -X POST "https://api.apipass.dev/api/v1/jobs/createTask" \
2 -H "Content-Type: application/json" \
3 -H "Authorization: Bearer YOUR_API_KEY" \
4 -d '{
5 "model": "minimax/music-1-5",
6 "callBackUrl": "https://your-domain.com/api/callback",
7 "input": {
8 "lyrics": "[verse]\nWalking down the street\nFeeling the beat\n[chorus]\nThis is my song\nCome sing along",
9 "prompt": "Upbeat pop song with electronic beats and catchy melody",
10 "sample_rate": 44100,
11 "bitrate": 256000,
12 "audio_format": "mp3"
13 }
14 }'1{
2 "code": 200,
3 "message": "success",
4 "data": {
5 "taskId": "task_music_12345678"
6 }
7}codeStatus code, 200 for success, others for failure
messageResponse message, error description when failed
data.taskIdTask ID for querying task status and retrieving generated music
