refmatch 0.1.0

AI-powered reference track suggestions for music producers

RefMatch

AI-powered reference track suggestions for music producers.

Stop searching for reference tracks. Let RefMatch analyze your audio and suggest the best matches.

Install

pip install refmatch

Usage

Analyze a track

refmatch analyze my_track.wav

Shows BPM, key, loudness (LUFS), dynamic range, brightness, and spectral balance.

Find reference tracks

refmatch match my_track.wav

Returns the top 5 most similar tracks from the database with match scores and explanations.

Dimension-specific matching

refmatch match my_track.wav --dimension low-end
refmatch match my_track.wav --dimension loudness
refmatch match my_track.wav --dimension brightness
refmatch match my_track.wav --dimension rhythm
refmatch match my_track.wav --dimension harmony

Manage your library

# Add a track or folder
refmatch library add my_reference.wav
refmatch library add ~/Music/References/ --artist "Various" --genre "Hip-Hop"

# List your library
refmatch library list

# Match against your own library only
refmatch match my_track.wav --library

# Remove a track
refmatch library remove 42

How it works

RefMatch extracts a 43-dimensional audio feature vector from your track using:

• MFCCs (timbral characteristics)
• Spectral features (centroid, bandwidth, contrast, rolloff)
• Loudness (integrated LUFS, dynamic range)
• Rhythm (tempo detection)
• Harmony (chroma features, key estimation)

It then finds the most similar tracks using cosine similarity, with optional dimension-specific matching to focus on particular aspects of the mix.

Supported formats

WAV, MP3, FLAC, OGG, AIFF, M4A

License

MIT