A simple, lightweight, Python tool that transcribes audio into a text file and prints on command line using the nvidia/parakeet-tdt-0.6b-v2 model, very battery and hardware efficient

Very handy for Meetings and Lectures on a laptop or a pi

• Offline Conversion: Works entirely offline, no internet connection needed other then to download the model
• Playback Control: Pause and resume the Transcription at any time.
• Cross-Platform: Tested with Linux and windows 10
• Lightweight: Minimal dependencies, a small footprint and easy to run
• User Input You can add text along side the transcription with a different line header to differentiate
• Append or new file Asks if want to create a new or add on to a existing file

Follow these instructions to get a copy of the project up and running on your local machine.

I use python 12 but versions within reason should work

1. Clone the repository:

   git clone [https://github.com/jethrothelion/SimpleTextToSpeech.git](https://github.com/jethrothelion/SimpleTextToSpeech.git) cd SimpleTextToSpeech

2. Install the required packages: The project relies on the Nemo, Numpy and other libraries. Install them using pip:

   pip install -r requirements.txt

Using the SimpleTextToSpeech script is straightforward. Just run the python file and it will ask all it needs to know

Feel free to build off of this very simple file