audiofeatures

A Python library for audio preprocessing and handcrafted feature extraction for machine learning, deep learning, and music information retrieval (MIR).

audiofeatures extracts temporal, spectral, cepstral, tonal, pitch, and rhythm features from audio files and returns a Pandas DataFrame.

Features

Audio Preprocessing

Mono conversion
Resampling
Normalization
Silence removal
Audio cropping

Temporal Features

RMS Energy
Zero Crossing Rate
Energy
Peak Amplitude
Crest Factor
Dynamic Range
Energy Variability
Amplitude Variability

Spectral Features

Spectral Centroid
Spectral Bandwidth
Spectral Rolloff
Spectral Contrast

Cepstral Features

MFCC
Delta MFCC
Delta-Delta MFCC

Tonal Features

Chroma
Tonnetz

Pitch Features

Pitch Mean
Pitch Standard Deviation
Pitch Minimum
Pitch Maximum

Rhythm Features

Onset Strength Mean
Onset Strength Standard Deviation
Onset Strength Maximum

Installation

pip install audiofeatures

Quick Start

from audiofeatures import extract_features

df = extract_features("song.wav")

print(df.head())

Default Parameters

Parameter	Default
Sample Rate	22050 Hz
Window Size	0.5 seconds

Returned Features

185 handcrafted audio features
Window-based extraction
Pandas DataFrame output

Requirements

Python 3.9+
NumPy
Pandas
Librosa
SoundFile

License

MIT License

Author

Dhyan Sudheer

Metadata

Release files for audiofeatures 2.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for audiofeatures 2.3.0
File	Size	Uploaded
audiofeatures-2.3.0.tar.gz	11.9 kB	Aug 3, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for audiofeatures 2.3.0
File	Interpreter	ABI	Platform	Reset
audiofeatures-2.3.0-py3-none-any.whl 24.1 kB Aug 3, 2026	Python 3	none	any	Details

Total release size: 36.0 kB

Release files / audiofeatures-2.3.0.tar.gz

Download URL	audiofeatures-2.3.0.tar.gz
Size	11.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`83268fe78a7f6cebda3ad80d6d130ea0349f4a9cd7c6f35b8e9eaf7ec69701ec`
BLAKE2b-256 checksum How to use checksums	`f7279a31dba8e226d6b22dade713fb6523616046d9945ffdb20a0ec6b1bc211e`
Upload date	Aug 3, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.11.5`

Release files / audiofeatures-2.3.0-py3-none-any.whl

Download URL	audiofeatures-2.3.0-py3-none-any.whl
Size	24.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`aed68d41b62a012a8c9aac3e57e4d7bfef37ab02a28bed06c647814df6321324`
BLAKE2b-256 checksum How to use checksums	`1a54b17577822d75cf39e56b2e1750f1cf52db0a80a898acb738b46349f8703b`
Upload date	Aug 3, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.11.5`