Meta has released an open source equivalent of Google’s viral podcast tool, NotebookLM, called NotebookLlama. The project is built on Meta’s Llama models. Like NotebookLM, it generates conversational, podcast-style summaries from uploaded text files.
Check out the GitHub repository here.
While people believe the quality is more robotic and doesn’t sound as natural as NotebookLM, it provides insights into the techstack behind technologies like NotebookLM, giving developers the flexibility to work on it.
Another open source alternative of NotebookLM includes Open NotebookLM. It is built on Llama 3.1 405B along with Fireworks AI and Instructor.
Building a Podcast with NotebookLlama
As per details shared on Github, the process involves the following steps:
PDF Pre-processing: Using the Llama-3.2-1B-Instruct model, the workflow first processes any PDF document, removing extra characters to ensure a clean, accurate text file.
Transcript Writing: Next, the Llama-3.1-70B-Instruct model (or optionally the Llama-3.1-8B-Instruct) generates a podcast-friendly transcript from the processed text. This model adds creative touches to make the content more engaging.
Dramatic Rewrite: To amplify the narrative, the Llama-3.1-8B-Instruct model rephrases the transcript for added drama, infusing personality and depth to captivate listeners.
Text-to-Speech Conversion: Finally, using Parler-TTS Mini V1 and Bark’s Suno, the workflow brings the text to life with a realistic, conversational audio output, ideal for podcasts.
Meta’s Push for Open Source
Interestingly, Llama has reached 400 million downloads globally, with India one of the top markets. With Llama 4 expected next year, Meta’s Llama models are touted to be the global standard in AI — hailed by Mark Zuckerberg as AI’s “Linux moment.” Top leaders like Jensen Huang and Mukesh Ambani believe these models are already building the foundation for India.
The post Meta Launches NotebookLlama, an Open Source Alternative to Google’s NotebookLM appeared first on AIM.
