This project replicates Google NotebookLM functionality locally, enabling users to process PDF documents and generate engaging audio content such as podcasts, summaries, and interviews. It supports multiple LLM providers including OpenAI, Anthropic Claude, Groq, LMStudio, Ollama, and Azure for content generation, along with text-to-speech engines for audio output. The system provides a FastAPI server for web access and a flexible pipeline allowing customization of content style, voices, and audio length.