#197197th of 206 in ML frameworks and librariesFor voice, speech and music
audioflux
C library with Python bindings for audio time-frequency transforms and feature extraction
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 3.4k
- License
- MIT
- Last commit
- Mar 2026
- Last release
- May 2024
- Language
- C
Missed the latest GitHub check; these facts may be older.
Overview
audioFlux is a C library with a Python package that computes time-frequency transforms (BFT, NSGT, CWT, PWT, CQT, VQT, DWT and others) across Linear, Mel, Bark, Erb, Octave and Log scales. On top of these it provides spectral, cepstral (MFCC-style) and chroma features, plus MIR functions for pitch, onset detection and harmonic-percussive separation. Output is meant as input for training audio models for classification, separation or ASR.
Who it is for: Audio ML researchers and MIR developers needing fast feature extraction
Strengths
- Broad transform set: BFT, NSGT, CWT, PWT, CQT, VQT, ST, DWT, WPT, SWT
- Core in C; builds for Linux, macOS, Windows, iOS and Android
- Installs with pip or conda; MIT licensed
- Includes pitch (YIN and others), onset, HPSS, pitch shift and time stretch
Weaknesses
- Feature extraction only; no models, training loops or pretrained weights
- Last tagged release is 2024-05-24, while commits continue into 2026
- iOS, Android and source builds need manual steps from the docs
- Benchmark shown only on one CPU; GPU support is not documented
Also in ML frameworks and libraries
See all 206| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |