What graphs / visuals can be generated from audio files? Is there a command-line utility to generate said visual?

I found the following:

Waveform : ffmpeg is able to generate a waveform
Spectrogram : sox can make a spectrogram

Any CLI tool for audio analysis could be useful as well. Basically anything that'll give me more information than duration, bitrate, format, channels, sample rate, bit/sample.

My operating system is Windows 7. Solutions for other platforms are accepted. (just precise what os the solution is aimed at)

1 Answer 1


While I haven't tried it myself pyAudioAnalysis to quote the blurb:

pyAudioAnalysis is a Python library covering a wide range of audio analysis tasks. Through pyAudioAnalysis you can:

  • Extract audio features and representations (e.g. mfccs, spectrogram, chromagram)
  • Classify unknown sounds
  • Train, parameter tune and evaluate classifiers of audio segments
  • Detect audio events and exclude silence periods from long recordings
  • Perform supervised segmentation (joint segmentation - classification)
  • Perform unsupervised segmentation (e.g. speaker diarization)
  • Extract audio thumbnails
  • Train and use audio regression models (example application: emotion recognition)
  • Apply dimensionality reduction to visualize audio data and content similarities
  • Command Line Operation e.g.:
    • Chromagram extraction: python audioAnalysis.py fileChromagram -i data/doremi.wav. Example 1

Note that there are many, (446 at the time of writing), forks of this code on github some of which may include useful modifications.


  • git version control client, (several clients are readily available for just about every platform).
  • python (the original code is for python 2.7 but at least part of this fork run under python 3.3 or later).
  • Several python packages, running pip install numpy matplotlib scipy sklearn hmmlearn simplejson eyed3 pydub after installing python should do the job.

Examples and detailed tutorials can be found at the wiki.

This option is Free, (Gratis & Open Source), and cross platform.

  • Neat! I'll definitely be looking into it.
    – TheRowdy
    May 17, 2018 at 12:17

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.