Transcribing recorded audio and video to text using Whisper AI on a Mac

Late last year, OpenAI announced Whisper, a new speech-to-text language model that is extremely accurate in translating many spoken languages into text. The whisper repository contains instructions for installation and use.


# Install whisper and its dependencies.
pip3 install git+ 

# (When needed) Update whisper.
pip3 install --upgrade --no-deps --force-reinstall git+

# Make sure ffmpeg is installed.
brew install ffmpeg

# Translate speech into text.
whisper my_audio_file.mp3 --language English

One thing I do quite regularly for my YouTube channel is extract the audio track, convert it to text using an online tool (I used to use Welder until they were bought out by Veed), and then hand-edit the file to fix references to product names, people, etc.

The Revised Translation of the Roman Missal

In case you've been living under a rock for a while, here's the best explanation to date as to why the Church will be implementing a new translation of the Roman Missal (basically, the words spoken by the Priest and/or the laity during the Holy Mass):

So far I've seen very little that really hits hard from official lines of communication from the Church (a lot of info for liturgists, priests, and Catholic addicts, but not so much for the Catholic everyman). Maybe some Catholic parishes could distribute this video to their parishioners?

A tip 'o the hat to my little Sister, who reminded me of this video, and got me to finally watch it!