This project is inspired by the NotebookLM tool, and implements it with open-source LLMs and text-to-speech models. This tool processes the content of a PDF, generates a natural dialogue suitable for an audio podcast, and outputs it as an MP3 file.

Built with:

• Llama 3.1 405B 🦙 via Fireworks AI 🎆 and Instructor 📐
• MeloTTS 🐚
• Bark 🐶
• Jina Reader 🔍

• Convert PDF to Podcast: Upload a PDF and convert its content into a podcast dialogue.
• Engaging Dialogue: The generated dialogue is designed to be informative and entertaining.
• User-friendly Interface: Simple interface using Gradio for easy interaction.

To set up the project, follow these steps:

1. Clone the repository:

   git clone https://github.com/gabrielchua/open-notebooklm.git
   cd open-notebooklm

2. Create a virtual environment and activate it:

   python -m venv .venv
   source .venv/bin/activate

3. Install the required packages:

   pip install -r requirements.txt

1. Set up API Key(s): For this project, I am using LLama 3.1 405B hosted on Fireworks API as its JSON Mode supports passing a pydantic object. So, please set the API key as the FIREWORKS_API_KEY environment variable

2. Run the application:

   python app.py

   This will launch a Gradio interface in your web browser.

3. Upload a PDF: Upload the PDF document you want to convert into a podcast.

4. Generate Audio: Click the button to start the conversion process. The output will be an MP3 file containing the podcast dialogue.

This project is forked from knowsuchagency/pdf-to-podcast

This project is licensed under the Apache 2.0 License. See the LICENSE file for more information.