minimax / music-01

Quickly generate up to 1 minute of music with lyrics and vocals in the style of a reference track

  • Public
  • 2K runs
  • License

Pricing

This model is priced by how many audio files are generated.

Check out our docs for more information about how per-audio pricing works on Replicate.

Readme

Music-01

https://minimaxi.com/en/news/music-01

An AI music generation model for synthesizing multi-style music with accompaniment and vocals.

Features

  • Simultaneous generation of accompaniment and vocals
  • Style learning from reference music uploads
  • Lyrics-to-music generation
  • Multiple genre support including classical, pop, rock, electronic, and others
  • Maximum output duration: 60 seconds (3 minutes planned for next release)

Usage

  1. Upload reference music for style analysis
  2. Input desired lyrics
  3. Generate new music piece with learned style characteristics

Applications

  • Film/TV soundtrack creation
  • AI singer compositions
  • Musical reinterpretations
  • General music production

Technical Details

The model uses deep learning to analyze and reproduce musical patterns, rhythms, and vocal styles from reference tracks.

Limitations

  • Current maximum output length: 60 seconds
  • Reference track required for style learning

Future Development

  • Planned support for 3-minute generation in next major release

Privacy policy

Data from this model is sent from Replicate to MiniMax.

Check their Privacy Policy for details:

https://intl.minimaxi.com/protocol/privacy-policy

Terms of Service

https://intl.minimaxi.com/protocol/terms-of-service