tyiannak/pyAudioAnalysis

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

6254 stars · 1211 forks observed · 2026-08-28

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

pyAudioAnalysis is a Python library for audio analysis covering feature extraction (MFCCs, spectrograms, chromagrams), supervised and unsupervised classification and segmentation, and regression. It also provides command-line tools for common audio analysis tasks like silence detection and speaker diarization.

Use cases

• extract mfcc and spectrogram features from audio files
• train a classifier to distinguish music from speech
• detect audio events and remove silence from long recordings
• perform speaker diarization on a conversation recording
• build an audio emotion recognition model
• visualize audio data with dimensionality reduction
• classify unknown sounds into trained categories

When to choose

• you need a broad toolkit of classical audio analysis features and ML pipelines in Python
• you want quick command-line tools for segmentation, silence removal, or diarization
• you are prototyping audio classification or regression with SVMs and similar models

When to avoid

• you need deep-learning-based audio models rather than classical feature-based methods
• you require real-time streaming audio analysis in production
• you need GPU-accelerated or highly optimized industrial-grade audio processing

Facets

library · maturity active

audio-processing machine-learning nlp machine-learning speech-processing python cli cross-platform audio-analysis feature-extraction mfcc speaker-diarization audio-classification signal-processing svm audio

Member repositories

For agents

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