yt-text

README

yt-text

Download audio from YouTube and convert it to text using yt-dlp and OpenAI Whisper.

This tool operates as a web server that accepts a YouTube URL (or any other URL supported by yt-dlp) and returns the video's transcript. Alternatively, you can run transcribe.py directly to transcribe a video.

Features

• Download audio from YouTube and other supported platforms
• Convert audio to text using OpenAI Whisper
• Operates as a web server for easy URL submission
• Direct transcription via transcribe.py

Installation

1. Clone the repository:

   git clone https://github.com/yourusername/yt-text.git
   cd yt-text
   

2. (Optional) Create a virtual environment and activate it:

   python -m venv venv
   source venv/bin/activate  # On Windows use `venv\Scripts\activate`
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Run the web server:

   go run main.go
   

Usage

• To transcribe a video directly, run:

  python transcribe.py <youtube-url>
  

  You can also specify the model name to use for transcription:

  python transcribe.py <youtube-url> --model <model_name>
  

  The default model is base.en. You can choose from other models like tiny, small, medium, large, etc. For more models, visit available models and languages.

Examples

• Transcribe a video using the default model:

  python transcribe.py <youtube-url>
  

• Transcribe a video using the base model:

  python transcribe.py <youtube-url> --model base
  

License

This project is licensed under the GNU Affero General Public License (AGPL) version 3. See the LICENSE file for details.

Contributing

Contributions are welcome! Please open an issue or submit a pull request for any changes.

Acknowledgements

• yt-dlp for downloading audio
• OpenAI Whisper for transcription