Create Your Own OpenAI Whisper Speech-To-Text Desktop App Using Python (PyQt6)

In this tutorial, you will learn how to create an audio to text Text-To-Speech desktop application (PyQt6) using Open Source OpenAI Whisper API in Python.
OpenAI has a paid version of Whisper API, in which they host the audio models and provide the computing resource. The drawback is the paid API has a 25MB file size limitation vs open source version doesn't.
📋 Download FFMpeg here: github.com/Btb...
💖 Show Support
☕ Paypal: www.paypal.me/...
☕ Venmo: @Jie-Jenn
🌳 Patreon: / jiejenn (early access to tutorial source code)
✉️ Business Inquiring: [e-mail]
#openai #desktopapplication #python #pyqt6

[@movkeykiku]

Although the paid api can only work with 25mb, but it also corrects and uses punctuation and stop marks , does this also work that way?

[@jiejenn]

I believe so.