librosa — Python Audio & Music Analysis Library

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.