# librosa/librosa

Python library for audio and music analysis

Repository: https://github.com/librosa/librosa
Canonical: https://ross.abutalabs.com/products/librosa
Homepage: https://librosa.org/
Language: Python
License: ISC
License Family: permissive
Topics: audio, python, music, dsp, librosa, scipy
Last push: 2026-08-22T13:06:58+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 65, longevity 100
- inputs: {"age_days": 5065, "days_push": 11, "days_rel": 22, "gap_med": 518, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8576, forks 1070 (observed 2026-08-28T04:10:23.625162+00:00)

## What it is
Librosa is a Python library for audio and music signal processing, providing foundational algorithms for building music information retrieval (MIR) systems. It offers feature extraction, spectral analysis, and DSP tools built on the scientific Python ecosystem.

## Use cases
- extract audio features like MFCCs and spectrograms
- analyze music for tempo, beat, and onset detection
- build a music genre classification model
- resample and load audio files in Python
- compute chroma features for chord recognition
- visualize audio waveforms and spectrograms

## When to choose
- you need well-established, documented audio feature extraction in Python
- you are building music information retrieval or audio ML pipelines
- you want a scipy/numpy-compatible signal processing toolkit

## When to avoid
- you need real-time low-latency audio streaming or playback
- you need audio synthesis or DAW-style editing rather than analysis
- you need GPU-accelerated large-scale audio processing

## Facets
- artifact type: library
- maturity: stable
- function: audio-processing, machine-learning, nlp
- domain: machine-learning, data-science
- platform: python, cross-platform
- tags: music-information-retrieval, dsp, signal-processing, spectrogram, feature-extraction, scipy-ecosystem, audio

## Member repositories
- librosa/librosa (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:23.625162+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 2026-08-29T17:26:16.205357+00:00, confidence not recorded.
  - readme: https://github.com/librosa/librosa (fetched 2026-08-28T04:10:23.625162+00:00, sha b1b5c41f1aa4)
  - homepage: https://librosa.org/ (fetched 2026-08-29T08:26:31.875354+00:00, sha 6a672a97afcc)
  - registry_pypi: https://pypi.org/pypi/librosa/json (fetched 2026-08-29T08:26:31.879895+00:00, sha 31e6fed74e08)
- Data as of 2026-08-30T08:39:29.467469+00:00.