YT2Text: YouTube Transcriber

This tool allows you to transcribe YouTube videos. It uses OpenAI's Whisper model for transcription.

Features

• Download audio from YouTube videos
• Transcribe audio using OpenAI's Whisper model with:
  • 99% transcription accuracy
  • Support for 98+ languages with auto-detection
  • Robust handling of accents and background noise
  • High-quality speech recognition
• Save transcriptions to a text file
• Secure storage of OpenAI API key

Prerequisites

• Python 3.7 or higher
• pip (Python package installer)
• OpenAI API key (get it from https://platform.openai.com/api-keys)

See .env.example for environment variable setup. The actual environment file will be created automatically when you run the script.

Installation

Windows

1. Clone this repository:

   git clone https://github.com/PierrunoYT/YT2Text.git
   cd YT2Text

2. Create and activate a virtual environment:

   python -m venv venv
   venv\Scripts\activate

3. Install required packages:

   pip install -r requirements.txt

macOS

1. Clone this repository:

   git clone https://github.com/PierrunoYT/YT2Text.git
   cd YT2Text

2. Create and activate a virtual environment:

   python3 -m venv venv
   source venv/bin/activate

3. Install required packages:

   pip install -r requirements.txt

Linux

1. Clone this repository:

   git clone https://github.com/PierrunoYT/YT2Text.git
   cd YT2Text

2. Create and activate a virtual environment:

   python3 -m venv venv
   source venv/bin/activate

3. Install required packages:

   pip install -r requirements.txt

Usage

1. Run the script:

   python youtube_transcriber.py    # Windows
   python3 youtube_transcriber.py   # macOS/Linux

2. Follow the prompts to:

   • Enter your OpenAI API key (only required on first run)
   • Provide a YouTube video URL
   • Specify the output file name for the transcription

3. The script will download the audio, transcribe it, and save the transcription to a file.

Notes

• The OpenAI API key is stored securely in your home directory.
• Temporary audio files are automatically cleaned up after processing.
• On Linux and macOS, you might need to use python3 instead of python depending on your system configuration.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Copyright (c) 2025 PierrunoYT