Vamp Plugins

This page lists plugins made by research groups and developers around the world. It is generated automatically from RDF descriptions published by the plugin authors.

▶ Vamp Plugin Pack — Some of these plugins are also available in the Vamp Plugin Pack, a convenient bundle installer.

BBC Vamp Plugins
BBC
Available for selected platform
With source code
Included in Vamp Plugin Pack
Plugin homepage
Download
A collection of audio feature extraction algorithms from BBC Research and Development.
▼ Less
- Spectral Flux
  Low Level Features
  Calculates the spectral flux.
- Spectral Contrast
  Low Level Features
  Calculates the peak and valleys of the spectral contrast feature.
libxtract Vamp plugins
Chris Cannam and Jamie Bullock
Available for selected platform
With source code
Included in Vamp Plugin Pack
Plugin homepage
Download
Low-level feature extraction plugins using Jamie Bullock's libxtract library to provide around 50 spectral and other features.
▼ Less
- Spectral Slope
  Low Level Features
  Extract the spectral slope of an audio spectrum.
- Spectral Centroid
  Low Level Features
  Extract the spectral centroid of an audio spectrum.
- Spectral Spread
  Low Level Features
  Extract the spectral spread of an audio spectrum.
- Spectral Average Deviation
  Extract the average deviation of an audio spectrum.
- Spectral Variance
  Low Level Features
  Extract the variance of an audio spectrum.
- Spectral Sharpness
  Low Level Features
  Extract the spectral sharpness of an audio spectrum.
- Spectral Skewness
  Low Level Features
  Extract the skewness of an audio spectrum.
- Spectral Smoothness
  Low Level Features
  Extract the spectral smoothness of an audio spectrum.
- Spectral Crest Measure
  Low Level Features
  Extract the spectral crest measure of an audio spectrum.
- Spectral Standard Deviation
  Low Level Features
  Extract the standard deviation of an audio spectrum.
- Spectral Kurtosis
  Low Level Features
  Extract the kurtosis of an audio spectrum.
- Spectral Flatness
  Low Level Features
  Extract the spectral flatness of an audio spectrum.
- Spectral Rolloff
  Low Level Features
  Extract the rolloff point of an audio spectrum.
- Inharmonicity
  Low Level Features
  Extract the inharmonicity of an audio spectrum.
- Peak Spectrum
  Visualisation
  Extract the spectral peaks from an audio spectrum.
- Loudness
  Low Level Features
  Extract the loudness of an audio signal from its spectrum.
- Harmonic Spectrum
  Visualisation
  Extract the harmonics from an audio spectrum.
- Variance
  Low Level Features
  Extract the variance of a range of values.
- Lowest Value
  Low Level Features
  Extract the lowest value from a given range.
- Discrete Cosine Transform
  Visualisation
  Extract the DCT of an audio signal.
- Mean
  Low Level Features
  Extract the mean of a range of values.
- Fundamental Frequency (failsafe)
  Low Level Features
  Extract the fundamental frequency of an audio signal (failsafe).
- Noisiness
  Low Level Features
  Extract the noisiness of an audio spectrum.
- Average Magnitude Difference Function
  Low Level Features
  Extract the AMDF of an audio signal.
- Bark Coefficients
  Low Level Features
  Extract bark coefficients from an audio spectrum.
- Fundamental Frequency
  Low Level Features
  Extract the fundamental frequency of an audio signal.
- Tonality
  Low Level Features
  Extract the tonality an audio spectrum.
- Average Squared Difference Function
  Low Level Features
  Extract the ASDF of an audio signal.
- Tristimulus III
  Low Level Features
  Extract the tristimulus (type III) of an audio spectrum.
- Tristimulus II
  Low Level Features
  Extract the tristimulus (type II) of an audio spectrum.
- Irregularity I
  Low Level Features
  Extract the irregularity (type I) of an audio spectrum.
- Tristimulus I
  Low Level Features
  Extract the tristimulus (type I) of an audio spectrum.
- Irregularity II
  Low Level Features
  Extract the irregularity (type II) of an audio spectrum.
- Skewness
  Low Level Features
  Extract the skewness of a range of values.
- Spectrum
  Visualisation
  Extract the spectrum of an audio signal.
- Average Deviation
  Low Level Features
  Extract the average deviation of a range of values.
- RMS Amplitude
  Low Level Features
  Extract the RMS amplitude of an audio signal.
- Autocorrelation
  Low Level Features
  Extract the autocorrelation of an audio signal.
- Non-zero count
  Low Level Features
  Extract the number of non-zero elements in an input spectrum.
- Mel-Frequency Cepstral Coefficients
  Low Level Features
  Extract MFCC from an audio spectrum.
- Zero Crossing Rate
  Low Level Features
  Extract the zero crossing rate of an audio signal.
- Highest Value
  Low Level Features
  Extract the highest value from a given range.
- Sum of Values
  Low Level Features
  Extract the sum of the values in a given range.
- Kurtosis
  Low Level Features
  Extract the kurtosis of a range of values.
- Odd/even Harmonic Ratio
  Low Level Features
  Extract the odd-to-even harmonic ratio of an audio spectrum.
- Standard Deviation
  Low Level Features
  Extract the standard deviation of a range of values.
Vamp Aubio plugins
Paul Brossier
Available for selected platform
With source code
Included in Vamp Plugin Pack
Plugin homepage
Download
The Vamp Aubio Plugins provide methods from Paul Brossier's aubio annotation library, including beat and tempo tracking, onset detection, pitch detection, note tracking, silence detector, and Mel-frequency cepstral coefficients.
▼ Less
- Aubio Spectral Descriptor
  Low Level Features
  Compute spectral description function.
Vamp example plugins
Vamp SDK Example Plugins
Available for selected platform
With source code
Included in Vamp Plugin Pack
Plugin homepage
Download
A set of simple plugins as included with the Vamp developers kit. Amplitude tracker, simple percussion onset detector, tempo estimator, spectral centroid, power spectrum, and zero-crossing counter.
▼ Less
- Spectral Centroid
  Low Level Features
  Calculate the centroid frequency of the spectrum of the input signal.
  Documentation
- Amplitude Follower
  Low Level Features
  Track the amplitude of the audio signal.
  Documentation
- Simple Power Spectrum
  Visualisation
  Return the power spectrum of a signal.
  Documentation
- Zero Crossings
  Low Level Features
  Detect and count zero crossing points.
  Documentation
- Simple Percussion Onset Detector
  Time → Onsets
  Detect percussive note onsets by identifying broadband energy rises.
  Documentation
- Simple Fixed Tempo Estimator
  Time → Tempo
  Study a short section of audio and estimate its tempo, assuming the tempo is constant.
  Documentation
Expressive Means
Frithjof Vollmer and Chris Cannam
Available for selected platform
With source code
Included in Vamp Plugin Pack
Plugin homepage
Download
Plugins for analysis of articulation, vibrato, and portamento in audio recordings of musical performances, with a primary focus on bowed stringed instruments.
▼ Less
- Expressive Means (advanced)
  Time → Onsets
  Finds note onsets and durations in monophonic recordings based on changes in spectral content, power, and pitch.
- Expressive Means
  Time → Onsets
  Finds note onsets and durations in monophonic recordings based on changes in spectral content, power, and pitch.
Queen Mary plugin set
Queen Mary, University of London
Available for selected platform
With source code
Included in Vamp Plugin Pack
Plugin homepage
Download
Plugins from the Centre for Digital Music at Queen Mary, University of London.
▼ Less
- Bar and Beat Tracker
  Time → Tempo
  Estimate bar and beat locations.
  Documentation
- Tonal Change
  Key and Tonality
  Detect and return the positions of harmonic changes such as chord boundaries.
  Documentation
Silvet Note Transcription
Queen Mary, University of London
Available for selected platform
With source code
Included in Vamp Plugin Pack
Plugin homepage
Download
Silvet, or Shift-Invariant Latent Variable Transcription, is a Vamp plugin for polyphonic music transcription (from audio to note times and pitches).
▼ Less
- Silvet Note Transcription
  Notes
  Estimate the note onsets, pitches, and durations that make up a music recording.
MATCH Vamp Plugin
Simon Dixon and Chris Cannam
Available for selected platform
With source code
Included in Vamp Plugin Pack
Plugin homepage
Download
Vamp implementation of the MATCH audio alignment algorithm from Simon Dixon. Sonic Visualiser can use this for automatic time alignment among multiple audio files.
▼ Less
- Match Performance Aligner
  Time → Alignment
  Calculate alignment between two performances in separate channel inputs.
MIR.EDU
MIR.EDU by Justin Salamon
With source code
Plugin homepage
An open source Vamp plug-in library written in C++ which implements a basic set of descriptors useful for teaching MIR.
▼ Less
- MIR.EDU: Spectral Flux
  Compute the spectral flux between every two consecutive frames of the signal. The flux is defined as 1 minus the normalized correlation between successive magnitude spectra. The values returned range between 0 (no change) and 1 (maximum change). For the first frame the flux is always zero. If both frames are silent flux = 0, if only one is silent flux = 1.
- MIR.EDU: Spectral Kurtosis
  Compute the spectral kurtosis of the signal for each frame. The kurtosis is a measure of the peakedness of a distribution. For a gaussian distribution kurtosis = 3, for a flat distribution kurtosis < 3 and for a peakier distribution kurtosis > 3.If the frame is completely silent a value of 0 is returned.
- MIR.EDU: Spectral Spread
  Compute the spectral spread of the signal for each frame. The unit of the values returned is Hz. If the frame is completely silent a value of 0 is returned.
- MIR.EDU: Spectral Skewness
  Compute the spectral skewness of the signal for each frame. If the frame is completely silent a value of 0 is returned.
- MIR.EDU: Spectral Crest
  Compute the spectral crest of the signal for each frame. The crest is defined as the ratio between the maximum spectral magnitude in the frame and the arithmetical mean of the spectral magnitudes. The minimum possible value is 1 (flat spectrum) and it increases the peakier the spectrum is. If the frame is completely silent a value of 1 (flat spectrum) is returned.
- MIR.EDU: Spectral Roll-off
  Compute the spectral roll-off of the signal for each frame, defined as the frequency below which 95% of the signal energy is contained. The threshold (95%) is defined as a paramtere that can be changed by the user. The unit of the values returned is Hz. If the frame is completely silent a value of 0 is returned.
- MIR.EDU: Spectral Flatness
  Compute the spectral flatness of the signal for each frame. The flatness is defined as the ratio of the geometric and arithmetical means of the spectral magnitudes. The values returned range between 0 (peaky spectrum) and 1 (flat spectrum). If the frame is completely silent a value of 1 (flat spectrum) is returned.
- MIR.EDU: Spectral Centroid
  Compute the spectral centroid of the signal for each frame. The unit of the values returned is Hz. If the frame is completely silent a value of 0 is returned.
- MIR.EDU: MFCC
  Compute the Mel Frequency Cepstral Coefficients (MFCC) for each frame. MFCCs provide a concise representation of the spectral envelope of a sound, which in turn is related to the sound's timbre. Please refer to the code in MFCC.cpp and the reference provided in MFCC.h for a detailed explanation of how MFCCs are computed.
MARSYAS Vamp plugins
Marsyas Plugins
With source code
Included in Vamp Plugin Pack
Plugin homepage
Low-level feature extraction plugins containing functionality from the MARSYAS batch feature extractor.
▼ Less
- Marsyas - Batch Feature Extract - Spectral Flatness Measure
  Low Level Features
  Marsyas - Batch Feature Extract - Spectral Flatness Measure.
- Marsyas - Batch Feature Extract - Line Spectral Pairs
  Low Level Features
  Marsyas - Batch Feature Extract - Line Spectral Pairs.
- Marsyas - Batch Feature Extract - Spectral Rolloff
  Low Level Features
  Marsyas - Batch Feature Extract - Spectral Rolloff.
- Marsyas - Batch Feature Extract - Spectral Crest Factor
  Low Level Features
  Marsyas - Batch Feature Extract - Spectral Crest Factor.
Simple Cepstrum
Chris Cannam
With source code
Included in Vamp Plugin Pack
Plugin homepage
A simple Vamp plugin to calculate and return cepstrum values from DFT bins. Useful as a preliminary tool for looking at cepstral data for simple pitch or envelope methods.
▼ Less
- Simple Cepstrum
  Low Level Features
  Return simple cepstral data from DFT bins. This plugin is intended for casual inspection of cepstral data. It returns a lot of different sorts of data and is quite slow; it's not a good way to extract a single feature rapidly.
Mazurka Plugins
The Mazurka Project
Not available for selected platform
No source code
Plugin homepage
Download
Spectral visualisation and feature extraction plugins from the Mazurka project.
▼ Less
- Spectral Flux
  Low Level Features
  Spectral Flux.
- Spectral Reflux
  Low Level Features
  Spectral Reflux.
- Harmonic Spectrogram
  Visualisation
  Harmonic Spectrogram.
- Chronogram
  Visualisation
  Chronogram.
- Nevermore Spectrogram
  Visualisation
  Nevermore Spectrogram.
- Power Curve
  Low Level Features
  Power Curve.

How to Install

A Vamp plugin set consists of a single dynamic library file with .dll, .dylib, or .so extension (depending on your platform), plus optionally a category file with .cat extension and an RDF description file with .ttl or .n3 extension.

To install a plugin set, copy the plugin's library file and any supplied category or RDF files into your system or personal Vamp plugin location.

The plugin file extension and the location to copy into depend on which operating system you are using:

You can alternatively set the VAMP_PATH environment variable to override the search path for for Vamp plugins. VAMP_PATH should contain a semicolon-separated (on Windows) or colon-separated (macOS, Linux) list of directory locations. If it is set, it will completely override the standard locations listed above. (N.B. When using 32-bit plugins on 64-bit Windows, some hosts will check for the VAMP_PATH_32 environment variable instead of VAMP_PATH.)

Your operating system	File extension for plugins	Where to put the plugin files
macOS	`.dylib`	On a Mac: Put plugins for all users to use in `/Library/Audio/Plug-Ins/Vamp` Put plugins for only the current user in `$HOME/Library/Audio/Plug-Ins/Vamp` The `Library` folders are hidden by default; see here for details of how to show them
64-bit Windows	`.dll`	When using a 64-bit version of Windows: Put 32-bit plugins in `C:\Program Files (x86)\Vamp Plugins` Put 64-bit plugins in `C:\Program Files\Vamp Plugins` Both 32-bit and 64-bit plugins can be used, as long as you put them in the right places as above If a plugin package is not described as 64-bit, then it is a 32-bit plugin. Some older plugins were only published in 32-bit form.
32-bit Windows	`.dll`	When using a 32-bit version of Windows: Put 32-bit plugins in `C:\Program Files\Vamp Plugins` You cannot use 64-bit plugins at all on 32-bit Windows If a plugin package is not described as 64-bit, then it is a 32-bit plugin. Some older plugins were only published in 32-bit form.
Linux, other Unix	`.so`	On Linux, BSD systems, etc: Put plugins for all users to use in `/usr/local/lib/vamp` Put plugins for only the current user in `$HOME/vamp` Only plugins with the correct architecture can be used (32-bit plugins on 32-bit systems, and 64-bit on 64-bit).

Vamp Plugins

Find and Download Plugins

How to Install