librosa — Python Audio & Music Analysis Library
Python library for audio and music analysis: spectrograms, MFCCs, beat tracking, pitch detection, and feature extraction.
librosa
librosa is the de-facto Python library for audio and music analysis. It provides building blocks for feature extraction, spectral analysis, rhythm analysis, and audio effects — used in ML pipelines, music information retrieval, and audio preprocessing for deep learning models.
Key Features
- Spectral features: MFCCs, mel spectrogram, chroma, spectral contrast, tonnetz
- Rhythm: beat tracking, tempo estimation, onset detection
- Pitch: fundamental frequency (F0) estimation, harmonic/percussive separation
- Effects: time stretching, pitch shifting, harmonic-percussive separation
- I/O: load/save any audio format via soundfile and audioread
- Tight integration with NumPy, SciPy, and matplotlib for visualisation
Quick Start
import librosa
import librosa.display
import matplotlib.pyplot as plt
y, sr = librosa.load("audio.mp3", sr=22050)
# Extract 13 MFCCs
mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=13)
# Visualise mel spectrogram
S = librosa.feature.melspectrogram(y=y, sr=sr)
librosa.display.specshow(librosa.power_to_db(S, ref=max), sr=sr)
plt.colorbar(format="%+2.0f dB")
plt.show()
Install via ai-supply
npx ai-supply add librosa-audio-music-analysis
Curated mirror of the open-source librosa (ISC). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/librosa-audio-music-analysis/check). Click a policy:
Consume librosa — Python Audio & Music Analysis Library programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/librosa-audio-music-analysis
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/librosa-audio-music-analysis/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add librosa-audio-music-analysis
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/librosa-audio-music-analysis/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "librosa-audio-music-analysis" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.