Open NotebookLM: Convert PDFs into Personalized Podcast Episodes
Summary
Open NotebookLM is an innovative open-source project that transforms any PDF document into an engaging podcast episode. Inspired by NotebookLM, it leverages powerful LLMs and text-to-speech models to generate natural dialogue from your documents. This tool provides a unique way to consume information, making learning and content absorption more accessible and enjoyable.
Repository Info
Tags
Click on any tag to explore related repositories
Introduction
Open NotebookLM is an open-source project inspired by Google's NotebookLM, designed to convert any PDF document into a personalized podcast episode. It processes PDF content, generates a natural dialogue suitable for an audio podcast, and outputs it as an MP3 file. This project utilizes advanced open-source LLMs and text-to-speech models to create an informative and entertaining listening experience, available in 13 languages.
Key technologies powering Open NotebookLM include:
Installation
To set up Open NotebookLM, follow these steps:
Clone the repository:
git clone https://github.com/gabrielchua/open-notebooklm.git cd open-notebooklmCreate a virtual environment and activate it:
python -m venv .venv source .venv/bin/activateInstall the required packages:
pip install -r requirements.txt
Examples
To use Open NotebookLM, first ensure your FIREWORKS_API_KEY is set as an environment variable, as the project uses Llama 3.3 70B via Fireworks AI. Run python app.py to launch the Gradio interface in your web browser. From there, you can easily upload any PDF document. The application will then process the PDF, generate an engaging podcast dialogue, and provide an MP3 file for download, allowing you to listen to your documents on the go.
Why Use It
Open NotebookLM offers a compelling way to interact with documents, moving beyond traditional reading. Its key benefits include:
- Accessibility: Convert written content into an audio format, making it accessible for listening during commutes, workouts, or for those who prefer auditory learning.
- Engagement: The generated dialogue is designed to be informative and entertaining, transforming dry documents into engaging narratives.
- Personalization: Create podcasts from your specific PDFs, tailoring the content directly to your interests and needs.
- Open Source Power: Built with leading open-source LLMs and TTS models, offering transparency and flexibility.
- User-Friendly Interface: The Gradio interface makes the process of uploading PDFs and generating podcasts straightforward and intuitive.
Links
- GitHub Repository: gabrielchua/open-notebooklm
- Llama 3.3 70B: Hugging Face
- Fireworks AI: fireworks.ai
- Instructor: GitHub
- MeloTTS: Hugging Face
- Bark: Hugging Face
- Jina Reader: jina.ai