Skip to content

GareBear99/awesome-python-audio-science

Awesome Python Audio Science

A curated, public-facing list of Python audio science, scientific audio research, DSP, MIR, machine-learning audio, datasets, notebooks, plugin testing, creator-audio tooling, and citation-ready audio research resources.

Awesome GitHub stars GitHub forks Last commit License PRs Welcome

Quick answer

Use this list when you need Python tools for:

  • scientific audio research
  • audio DSP and spectral analysis
  • music information retrieval
  • speech analysis and alignment
  • source separation
  • audio machine learning
  • datasets and dataloaders
  • audio visualization and notebooks
  • plugin analysis and creator-audio automation
  • TizWildin / GareBear99 audio ecosystem routing, deconstructed loops, plugin hubs, and release-surface mapping

This repo is inspired by the scientific-audio awesome-list tradition, especially faroit/awesome-python-scientific-audio, but it is intentionally broader: it includes research tooling, production-facing audio engineering, independent-artist data surfaces, plugin/tool ecosystems, and the GareBear99 / TizWildin routing network.

Academic / Research SEO Positioning

This repository is the official research-facing audio science satellite inside the GareBear99 / TizWildin ecosystem. It is designed to bridge practical audio tools with scholarly search intent:

  • Python scientific audio libraries
  • DSP and spectral-analysis references
  • MIR / music information retrieval tooling
  • machine-learning audio resources
  • datasets and reproducible notebooks
  • citation-ready open-source audio software
  • DOI / Zenodo / BibTeX / CITATION.cff guidance
  • research bridges for FreeEQ8, FreeVox8, Instrudio, Voxel Audio, and the HUB router

Use this repo when a project needs to look credible to developers, researchers, students, DSP learners, and audio-ML users instead of only producers.

Citation-ready ecosystem anchors

Project Research / citation role
FreeEQ8 Open-source JUCE/C++ EQ plugin for DSP education, plugin testing, analyzer research, M/S processing examples, and citable audio-software packaging.
FreeVox8 Spectral vocoder / ghost-resynthesis R&D anchor for STFT, phase vocoder, formant, masking, and spectral-processing research direction.
Instrudio Single-source-of-truth virtual instrument runtime with physically informed Studio Violin, Web Audio synthesis, MIDI routing, and runtime metrics.
Voxel Audio Audio visualization, image binding, export routing, and creator-facing media tooling useful for audio-visual research workflows.
TizWildinEntertainmentHUB Public router for plugins, lists, deconstructed loops, sample packs, visualizers, and release surfaces.

GareBear99 / TizWildin Audio Discovery Network

This list is part of the public GareBear99 audio ecosystem.

Project Role
awesome-audio-lists Parent hub for audio directories, submission targets, plugin lists, and music-platform lists.
awesome-music-platforms Independent artist platform map: streaming, distribution, beat stores, sample packs, sync licensing, analytics, creator storefronts.
awesome-audio-plugins-dev Audio plugin development, JUCE, DSP, plugin directories, and open-source audio engineering resources.
TizWildinEntertainmentHUB Main public plugin/sample-pack dashboard and .io router surface for the TizWildin ecosystem.
TizWildin HUB public router .io/GitHub Pages public route for plugins, packs, lists, deconstructed loops, and release surfaces.
TizWildin Release Vault Release/catalog proof surface for distributed tracks, official releases, and monetized music assets.
FreeEQ8 Open-source 8-band EQ plugin and flagship public audio-plugin anchor.
FreeVox8 Spectral vocoder / ghost resynthesis plugin anchor.
Voxel Audio RGB waveform visualizer, audio-router, visual export, image-binding, vault, and creator loop/track presentation surface.
SoundCloud: TizWildin Original songs, WIPs, remixes, VIP mixes, and underground release surface.
YouTube: TizWildin Music videos, demos, visualizers, public release clips, and platform routing.

IO router / deconstructed loops anchor

The public router for TizWildin plugins, deconstructed loops, release packs, visualizers, and list routing lives through:

Use these as the canonical public-facing anchors for deconstructed loops, sample packs, plugin releases, and creator-routing pages unless superseded by a later dedicated router repo.

Contents

Core Python Audio Packages

  • librosa - Audio and music analysis library for Python, widely used for MIR and research workflows.
  • Essentia - C++/Python library for audio and music analysis, feature extraction, and large-scale research.
  • aubio - Audio feature extraction, onset detection, pitch detection, beat tracking, and segmentation.
  • madmom - MIR package focused on beat, downbeat, onset, tempo, and chord recognition.
  • audioFlux - Audio and music analysis library with spectral transforms and feature extraction.
  • torchaudio - PyTorch audio I/O, transforms, datasets, and deep-learning audio utilities.
  • JAX audio examples - Useful base for research pipelines that need accelerated differentiable audio experiments.

Read / Write / Metadata

  • soundfile - Read and write sound files using libsndfile through CFFI.
  • audioread - Decode audio using available backends such as GStreamer, Core Audio, MAD, FFmpeg, and others.
  • pydub - Simple high-level audio manipulation, conversion, slicing, and export.
  • mutagen - Audio metadata reading and writing for many formats.
  • tinytag - Lightweight metadata reader for MP3, OGG, FLAC, WAV, and more.
  • PyAV - Pythonic bindings for FFmpeg libraries.
  • stempeg - Read and write multi-stream audio, especially useful for stems and source-separation datasets.

DSP, Transforms & Spectral Analysis

  • NumPy - Array computation base for most audio analysis and DSP pipelines.
  • SciPy Signal - Filtering, transforms, windows, spectral analysis, and signal-processing utilities.
  • pyFFTW - Python wrapper around FFTW for faster FFT-heavy workflows.
  • STFT - Standalone short-time Fourier transform tools.
  • PyWavelets - Wavelet transforms and multi-resolution signal analysis.
  • resampy - Sample-rate conversion for audio and signal processing.
  • pyroomacoustics - Room acoustics simulation, beamforming, and sound-field experimentation.
  • acoustics - Acoustics calculations, room acoustics, decibels, filters, and standards-oriented utilities.
  • pyloudnorm - Loudness meter and normalization library based on ITU-R BS.1770.
  • matchering - Automated reference audio mastering in Python.

Feature Extraction & MIR

  • mir_eval - Standard evaluation tools for music information retrieval tasks.
  • mirdata - Common loaders for MIR datasets.
  • msaf - Music structure analysis framework.
  • pretty_midi - MIDI analysis and manipulation utilities.
  • music21 - Computer-aided musicology and symbolic music analysis.
  • mido - MIDI message, port, and file utilities.
  • partitura - Symbolic music processing for score-performance research.

Machine Learning Audio

  • PyTorch - Deep-learning framework commonly used for audio ML, MIR, source separation, and speech.
  • torchaudio - Audio-specific PyTorch transforms, datasets, models, and I/O.
  • TensorFlow Audio / Keras - Audio loading, preprocessing, and model training paths in the TensorFlow ecosystem.
  • Kapre - Keras audio preprocessing layers.
  • nnAudio - GPU-accelerated audio transforms using neural-network operations.
  • Hugging Face Audio - Models and datasets for classification, speech, separation, and generation tasks.
  • Asteroid - PyTorch-based audio source-separation toolkit.
  • SpeechBrain - Speech and audio toolkit for ASR, speaker recognition, separation, enhancement, and more.

Speech, Voice & Alignment

Source Separation

  • Demucs - Music source separation with deep learning.
  • Spleeter - Source-separation library by Deezer.
  • Open-Unmix - Music source separation toolkit and model family.
  • Asteroid - Source separation and speech enhancement toolkit.
  • nussl - Holistic source-separation framework.
  • musdb - MUSDB dataset tooling for source separation.

Loudness, Metering & Perceptual Audio

  • pyloudnorm - Program loudness and true-peak-oriented workflows based on BS.1770-style metering.
  • pystoi - Short-Time Objective Intelligibility measure.
  • pesq - PESQ speech quality metric wrapper.
  • cochlea - Inner-ear auditory models.
  • Brian2 - Spiking neural network simulator useful for auditory model research.

Realtime Audio & MIDI

  • sounddevice - Realtime audio I/O with PortAudio and NumPy.
  • pyo - Realtime DSP and synthesis engine for Python.
  • Jupylet - Python game/audio environment with synth and sample support.
  • mido - MIDI message and port handling.
  • python-rtmidi - Realtime MIDI I/O bindings.

Datasets & Dataloaders

  • mirdata - Standardized loaders for MIR datasets.
  • MUSDB18 - Music source-separation dataset.
  • MedleyDB - Multitrack dataset for MIR research.
  • FMA - Free Music Archive dataset for music analysis.
  • AudioSet - Large-scale audio event dataset.
  • Common Voice - Open speech dataset.
  • Magenta Datasets - Music and symbolic datasets for creative ML.

Visualization, Notebooks & Web Audio

  • matplotlib - Plot waveforms, spectrograms, features, and research figures.
  • plotly - Interactive audio-analysis plots and dashboards.
  • Jupyter - Notebook environment for audio experiments, MIR notebooks, and reproducible analysis.
  • Streamlit - Quick interactive audio analysis apps and dashboards.
  • Gradio - Simple ML/audio demos and web UIs.
  • TimeSide - Audio analysis, imaging, transcoding, streaming, and labelling tools.
  • Voxel Audio - TizWildin RGB waveform visualizer and audio export tool for creator routing and visual releases.

Audio Plugin / Creator Tooling

  • pedalboard - Python audio effects and VST3/AU plugin hosting from Spotify.
  • DawDreamer - Python DAW-style rendering and plugin hosting.
  • Vamp plugins / VamPy host - Python interface for Vamp audio-analysis plugins.
  • JUCE - C++ plugin framework; relevant for Python-assisted testing, packaging, and analysis pipelines.
  • FreeEQ8 - TizWildin open-source EQ plugin anchor for analysis/testing examples.
  • FreeVox8 - TizWildin spectral vocoder / ghost-resynthesis plugin anchor.
  • TizWildinEntertainmentHUB - Public plugin router, release dashboard, list tab, and creator ecosystem hub.

GareBear99 / TizWildin Ecosystem

These entries are included as canonical creator/audio ecosystem anchors, especially for plugin-routing, deconstructed-loop routing, sample-pack routing, visualizer export surfaces, and audio-tool SEO discoverability.

Best Python Audio Stack by Use Case

Use Case Start With Add Next Notes
Quick audio analysis librosa matplotlib, soundfile Fastest path for spectrograms, features, tempo, and MIR experiments.
Production file conversion pydub PyAV, ffmpeg Good for creator pipelines, exports, and batch processing.
Deep-learning audio torchaudio PyTorch, nnAudio, SpeechBrain Best for GPU/ML pipelines.
Source separation Demucs Open-Unmix, Asteroid, MUSDB Best for stems, dataset work, and research comparisons.
Speech alignment Montreal Forced Aligner aeneas, Parselmouth Good for lyrics, voice, and phonetics workflows.
Realtime audio sounddevice pyo, mido Useful for prototypes, MIDI, and live control.
Plugin rendering/testing pedalboard DawDreamer, JUCE/pluginval Use for offline plugin tests and audio examples.
TizWildin creator routing Voxel Audio TizWildinEntertainmentHUB, Release Vault For deconstructed loops, public routing, visualizer export, packs, and music surfaces.

Research, Citations & DOI Guides

These pages turn the repo from a normal awesome list into an academic-facing research and citation hub:

Citation-Ready GareBear99 / TizWildin Audio Software

Software Suggested citation angle Next action
FreeEQ8 Open-source JUCE/C++ 8-band EQ plugin for DSP education, analyzer testing, M/S processing examples, and pluginval/DAW compatibility workflows. Add CITATION.cff, CITATIONS.md, Zenodo DOI, and release artifacts.
Instrudio SSOT Web Audio instrument runtime with physically informed Studio Violin, MIDI routing, plugin-bridge events, live metrics, and reproducible JSON definitions. Add formal paper-style README section, BibTeX, and Zenodo archive.
FreeVox8 Spectral vocoder / ghost-resynthesis R&D package for STFT, masking, phase-vocoder, and formant-processing direction. Add research spec, pluginval reports, and citation metadata after binary certification.
Voxel Audio Audio visualization/export/router surface for waveform visualizer research, cover-art binding, and creator-media pipeline experiments. Add reproducible export metrics and citation metadata.
TizWildinEntertainmentHUB Public router and ecosystem index for plugins, lists, deconstructed loops, sample packs, release surfaces, and audio-tool discovery. Keep it as the canonical public gateway and add crawlable links.

Long-Tail Guides

Related Awesome Lists

Recommended GitHub metadata

Recommended repo name:

awesome-python-audio-science

Recommended GitHub description:

A curated awesome list of Python audio science, scientific audio research, DSP, MIR, machine-learning audio, datasets, visualization, plugin testing, and creator-audio tooling.

Recommended topics:

awesome awesome-list python audio scientific-audio audio-dsp signal-processing music-information-retrieval mir speech-processing source-separation audio-machine-learning datasets audio-analysis audio-visualization music-technology independent-artists tizwildin garebear99 audio-research research-software citable-software zenodo doi bibtex citation-cff reproducible-research deep-learning-music neural-audio

Contributing

Contributions are welcome. Keep entries useful, neutral, public-facing, and directly relevant to Python audio science or creator-audio automation.

Submission format:

- [Project Name](https://example.com/) - Short neutral description.

See CONTRIBUTING.md and docs/SUBMISSION_GUIDE.md.

License

CC0-1.0 recommended for public awesome-list reuse.

About

A curated, public-facing list of Python audio science, scientific audio research, music information retrieval, DSP, machine learning audio, datasets, notebooks, and creator-audio tooling.

Resources

License

Code of conduct

Contributing

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages