Essentia is an open-source C++ library for audio analysis and audio-based music information retrieval released under the Affero GPL license. It contains an extensive collection of reusable algorithms which implement audio input/output functionality, standard digital signal processing blocks, statistical characterization of data, and a large set of spectral, temporal, tonal and high-level music descriptors. The library is also wrapped in Python and includes a number of predefined executable extractors for the available music descriptors, which facilitates its use for fast prototyping and allows setting up research experiments very rapidly. Furthermore, it includes a Vamp plugin to be used with Sonic Visualiser for visualization purposes. Essentia is designed with a focus on the robustness of the provided music descriptors and is optimized in terms of the computational cost of the algorithms. The provided functionality, specifically the music descriptors included in-the-box and signal processing algorithms, is easily expandable and allows for both research experiments and development of large-scale industrial applications.

Documentation online: https://essentia.upf.edu

The library is cross-platform and currently supports Linux, Mac OS X, Windows, iOS and Android systems. Read installation instructions:

• https://essentia.upf.edu/documentation/installing.html
• doc/sphinxdoc/installing.rst

You can download and use prebuilt static binaries for a number of Essentia's command-line music extractors instead of installing the complete library

• doc/sphinxdoc/extractors_out_of_box.rst

Quick start using python:

• https://essentia.upf.edu/documentation/essentia_python_tutorial.html
• IPython Notebook Essentia tutorial

Command-line tools to compute common music descriptors:

• doc/sphinxdoc/extractors_out_of_box.rst

• Read frequently asked questions
• Create an issue on github if your question was not answered before

Official releases:

• https://github.com/MTG/essentia/releases

Github branches:

• master: the most updated version of Essentia (Ubuntu 14.10 or higher, OSX); if you got any problem - try it first.

If you use example extractors (located in src/examples), or your own code employing Essentia algorithms to compute descriptors, you should be aware of possible incompatibilities when using different versions of Essentia.

We are more than happy to collaborate and receive your contributions to Essentia. The best practice of submitting your code is by creating pull requests to our GitHub repository following our contribution policy. By submitting your code you authorize that it complies with the Developer's Certificate of Origin. For more details see: https://essentia.upf.edu/documentation/contribute.html

You are also more than welcome to suggest any improvements, including proposals for new algorithms, etc.