a collection of tools for music analysis
aubio is a collection of tools for music and audio analysis.
This package integrates the aubio library with NumPy to provide a set of efficient tools to process and analyse audio signals, including:
- read audio from any media file, including videos and remote streams
- high quality phase vocoder, spectral filterbanks, and linear filters
- Mel-Frequency Cepstrum Coefficients and standard spectral descriptors
- detection of note attacks (onset)
- pitch tracking (fundamental frequency estimation)
- beat detection and tempo tracking
aubio works with both Python 2 and Python 3.
Some examples are available in the
python/demos folder. Each
script is a command line program which accepts one ore more argument.
Notes: installing additional modules is required to run some of the demos.
demo_source.pyuses aubio to read audio samples from media files
demo_onset_plot.pydetects attacks in a sound file and plots the results using matplotlib
demo_pitch.pylooks for fundamental frequency in a sound file and plots the results using matplotlib
demo_mfcc.pyfor spectral analysis.
demo_timestretch.pycan change the duration of an input file and write the new sound to disk,
demo_wav2midi.pydetects the notes in a file and uses mido to write the results into a MIDI file
demo_timestretch_online.py to slow down
loop.wav, write the results in
$ python demo_timestretch_online.py loop.wav stretched_loop.wav 0.92
The core of aubio is written in C for portability and speed. In addition to NumPy, aubio can be optionally built to use one or more of the following libraries:
media file reading:
- ffmpeg / avcodec to decode and read audio from almost any format,
- libsndfile to read audio from uncompressed sound files,
- libsamplerate to re-sample audio signals,
- CoreAudio to read all media formats supported by macOS, iOS, and tvOS.
- Atlas and Blas, for accelerated vector and matrix computations,
- fftw3, to compute fast Fourier Transforms of any size,
- Accelerate for accelerated FFT and matrix computations (macOS/iOS),
- Intel IPP, accelerated vector computation and FFT implementation.
Release history Release notifications | RSS feed
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.