How can I convert a .wav file of spoken audio (from say, a handheld recorder) into a .txt file with fairly accurate speech recognition? A command that uses a free utility would be most helpful.

I understand there are ways of doing this using the Google Web Speech API and Google Chrome. I'm trying to achieve a way to do this that could be built into a shell script that converts pre-recorded audio of some of my notes into text.

1 Answer 1


A Python utility to cover your bases:


Installation pip install SpeechRecognition

Transcribing from WAV via command line: check https://github.com/Uberi/speech_recognition/blob/master/examples/wav_transcribe.py

Engines used: Sphinx (offline), and free online services (Google Speech Recognition, Wit.ai, IBM Speech to Text, and AT&T Speech to Text) - registration required.

  • 1
    I think this will work great. Thank you so much! Apr 1, 2016 at 13:36

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

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