librosa/librosa

Health v2 · maintenance only

Adoption not part of the score

8576 stars · 1070 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity stable

audio-processing machine-learning nlp machine-learning data-science python cross-platform music-information-retrieval dsp signal-processing spectrogram feature-extraction scipy-ecosystem audio

Member repositories

For agents

markdown · JSON · MCP: product_card(name="librosa/librosa")