# MTG/essentia

C++ library for audio and music analysis, description and synthesis, including Python bindings

Repository: https://github.com/MTG/essentia
Canonical: https://ross.abutalabs.com/products/essentia
Homepage: http://essentia.upf.edu
Language: C++
License: AGPL-3.0
License Family: copyleft
Topics: audio, music, dsp, essentia, python, c-plus-plus, music-information-retrieval, audio-analysis, sound-processing
Last push: 2026-07-22T07:45:39+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 8, longevity 100
- inputs: {"age_days": 4839, "days_push": 42, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3705, forks 631 (observed 2026-08-28T04:08:15.057881+00:00)

## What it is
Essentia is an open-source C++ library for audio analysis and music information retrieval, offering a large collection of reusable DSP algorithms and music descriptors, with Python bindings and prebuilt command-line extractors. It supports fast prototyping, research experiments, and large-scale industrial applications across Linux, macOS, Windows, iOS, and Android.

## Use cases
- extract music descriptors like tempo, key, and loudness from audio files
- compute spectral and tonal features for music information retrieval research
- run audio classification models with essentia-tensorflow in Python
- batch-analyze large music catalogs with command-line extractors
- prototype audio analysis pipelines in Python notebooks
- visualize audio features in Sonic Visualiser via the Vamp plugin

## When to choose
- you need robust, optimized audio/music feature extraction in C++ or Python
- you want out-of-the-box music descriptors without writing DSP code
- you are doing MIR research or building large-scale audio analysis services

## When to avoid
- you need a permissive license - Essentia is AGPLv3
- you need real-time low-latency audio synthesis rather than analysis
- you only need simple playback or recording functionality

## Facets
- artifact type: library
- maturity: stable
- function: audio-processing, machine-learning, nlp
- domain: machine-learning, data-science
- platform: windows, python, cpp, cross-platform
- tags: music-information-retrieval, dsp, audio-analysis, music-descriptors, tensorflow, vamp-plugin, feature-extraction, audio, linux, macos, ios, android

## Member repositories
- MTG/essentia (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:15.057881+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:30:58.927870+00:00, confidence not recorded.
  - readme: https://github.com/MTG/essentia (fetched 2026-08-28T04:08:15.057881+00:00, sha b035d4372d8a)
- Data as of 2026-08-30T08:39:29.467469+00:00.