OpenAI Whisper and Python: Easy Speech to Text

Learn how to record, transcribe, and automate your journaling with Python, OpenAI Whisper, and the terminal! 📝
In this video, we'll show you how to:
- Record audio right in your terminal with ffmpeg
- Automatically transcribe it into text using OpenAI's groundbreaking Whisper AI ✍️
- Delete the audio file when done for privacy
- Push new entries to a private Github repo for backup 🚀
It's the perfect nerdy journaling workflow - all from the comfort of your terminal! This project uses Python for automation and requires:
ffmpeg for recording
OpenAI Whisper for transcription
Python 3.8+ and pip for installation
Whether you love journaling or just want to experiment with OpenAI Whisper and Python, this is a fun automation project!
Blog with full instructions 👉 dev.to/chris-pennington/how-i-use-ai-to-transcribe-in-my-terminal-4n0d
Try Warp now for FREE 👉 bit.ly/warpdotdev
Twitter 🐦
warpdotdev
TikTok 📱
www.tiktok.com/@warp.dev
TimeStamps
00:00:00 - Introduction
00:00:30 - Recording Audio in Terminal
00:02:30 - Transcribing Audio with Whisper AI
00:05:14 - Stitching Everything Together
00:06:09 - Pushing Files to GitHub
00:07:03 - Displaying Local Notification
00:07:15 - Final Workflow
00:07:36 - Conclusion

[@warpdotdev]

What tutorial would you like to see next?

[@jawadsrour8490]

Hello, Would be great to see more content on docker! Or tutorial on writing automation scripts that are great for every day workflows using Bash / Scripting.

[@StevenFenix]

Text to speech using OPEN AI tecnology too!

[@jacobgoldenart]

How about a tutorial using Warp to build a nice CLI Chatbot Assistant?

[@jacobgoldenart]

This was a great tutorial. Please consider making some more python/programing/terminal/ai tutorial videos!

[@Fomites]

This is so complicated to setup (unless one works with this a lot and is familiar with it) that it's faster and easier to just put headsets on and transcribe it oneself. I have no idea what you are talking about.

[@555chaithanyakrishna8]

Can I use openAI whisper with python 3.8.10 ??

[@yasirbugrara]

This was a solid tutorial. Got it working quickly.

[@mariodevelopersantos1102]

this tutorial is excellent

[@_emnljrz]

When in Windows?

[@PhilSmy]

Great tutorial but my god it is SLOWWWWWW. I am getting Whisper to transcribe an mp3 file of a podcast episode. 30 minutes later it has done 8 minutes (out of 50). Is this expected behavior? But, aside from that, great job with the tutorial. Very easy to follow.

[@ThiagoOliveira-fj9me]

They will be slow on standard CPUs. They need GPUs for acceptable performance.

[@luizg.zambrano]

What's the best computer setup for a optimal whisper functionality in a productive manner?

[@PhilSmy]

I ended up running this on an AWS instance that has a GPU and yes, it is blazing! Thanks again.

[@광동아재廣東大叔]

I'm still using a i7 4790 rig but replaced the old graphics card with a RTX4080super. No problems whatsoever and lightfast as well.

[@tomfox41]

Why don't the people in these videos have names?

[@warpdotdev]

Chris!

[@republicavictinera]

Could not enumerate video devices (or none found). [dshow @ 000002221282aac0] Could not enumerate audio only devices (or none found). [in#0 @ 000002221282a940] Error opening input: Immediate exit requested Error opening input file dummy.

[@harukatenoh1097]

Can you speak any faster? I can't really understand you due to you speaking way too fast....

[@edyth5630]

learn how to use youtube to adjust playback speed