notebookLM2PPT
Enables AI models to convert NotebookLM PDF exports into high-quality PowerPoint presentations with automatic watermark removal and vector graphics preservation. It provides automated tools for slide conversion, metadata management, and document processing via the Model Context Protocol.
README
notebookLM2PPT
Convert PDF Slides to PowerPoint Presentations with Vector Graphics (highest resolution).

✨ Features
- 🎯 Vector Graphics - Maintains highest resolution in generated PPT
- 📝 Metadata Conversion - Preserves title, author and other metadata
- 📐 Auto Detection - Automatically detects slide size and aspect ratio
- 🚀 Easy to Use - Simple command line interface with beautiful output
- 📄 Page Selection - Convert specific pages with
--pagesoption - ⚡ Parallel Processing - Speed up conversion with
--paralleloption - 🔍 Dependency Check - Automatically checks for required tools
- 🎨 Web UI - Modern web interface with drag-and-drop support
- 📡 REST API - FastAPI server with async processing
- 🔧 MCP Support - Model Context Protocol for AI integration
- 🐳 Docker Ready - All-in-one Docker image available
- 💎 Glassmorphism Design - Ultra modern frosted glass UI with neon effects
- 🌍 18 Languages - Full internationalization support
🌍 Supported Languages
| Language | Code | Language | Code |
|---|---|---|---|
| English | en | Italiano | it |
| 简体中文 | zh-CN | Русский | ru |
| 繁體中文 | zh-TW | العربية | ar |
| 日本語 | ja | हिन्दी | hi |
| 한국어 | ko | ไทย | th |
| Français | fr | Tiếng Việt | vi |
| Deutsch | de | Nederlands | nl |
| Español | es | Polski | pl |
| Português | pt | Türkçe | tr |
🎯 Motivation
- LaTeX users can easily convert
beamerslides from PDF to PPT - Typst users can easily convert
touyingslides from PDF to PPT
🚀 Quick Start
Option 1: Command Line (pipx)
# Install via pipx (recommended)
pipx install notebooklm2ppt
# Convert PDF to PPT
pdf2ppt input.pdf output.pptx
Option 2: Web UI (Docker)
For x86_64 / AMD64 (Linux servers, Intel Macs):
docker run -d -p 8100:8100 neosun/notebooklm2ppt:1.2.0-amd64
For ARM64 (Apple Silicon Macs, ARM servers):
docker run -d -p 8100:8100 neosun/notebooklm2ppt:1.2.0-arm64
Auto-detect architecture:
docker run -d -p 8100:8100 neosun/notebooklm2ppt:latest
Access at: http://localhost:8100
Option 3: API Server
# Install with server dependencies
pip install "notebooklm2ppt[server]"
# Start server
python -m uvicorn web.app:app --host 0.0.0.0 --port 8100
API Documentation: http://localhost:8100/docs
📦 Installation
Prerequisites
Install Dependencies
macOS:
brew install pdf2svg inkscape
Ubuntu/Debian:
sudo apt-get install pdf2svg inkscape
Windows:
Install notebookLM2PPT
# Recommended: Install with pipx (isolated environment)
pipx install notebooklm2ppt
# Or install with pip
pip install notebooklm2ppt
📖 Usage
Basic Usage
# Specify output file
pdf2ppt input.pdf output.pptx
# Auto-generate output filename (input.pptx)
pdf2ppt input.pdf
# Verbose mode
pdf2ppt input.pdf --verbose
Advanced Usage
# Convert specific pages
pdf2ppt input.pdf -p 1-5,7,9-11
# Parallel processing (4 workers)
pdf2ppt input.pdf -j 4
# Force overwrite existing file
pdf2ppt input.pdf output.pptx --force
# Keep temporary files for debugging
pdf2ppt input.pdf --no-clean
Command Line Options
usage: pdf2ppt [-h] [-v] [--verbose] [--no-clean] [--no-check] [--force]
[--pages PAGES] [--parallel PARALLEL]
[--pdf2svg-path PATH] [--inkscape-path PATH]
input [output]
positional arguments:
input Input PDF file
output Output PPTX file (default: input.pptx)
options:
-h, --help show this help message and exit
-v, --version show program's version number and exit
--verbose Verbose output
--no-clean Keep temporary files
--no-check Skip SVG filter check
--force, -f Overwrite output file if exists
--pages, -p PAGES Page range (e.g., "1-5,7,9-11")
--parallel, -j N Parallel workers (default: 1)
--pdf2svg-path PATH Path to pdf2svg executable
--inkscape-path PATH Path to inkscape executable
🔧 Technical Implementation
- Convert PDF to SVG using
pdf2svg - Convert SVG to EMF using
inkscape(due to python-pptx limitations) - Insert EMF into PPT using
python-pptx
🛠️ Tech Stack
| Component | Technology |
|---|---|
| Language | Python 3.9+ |
| PDF Processing | pypdf |
| PPT Generation | python-pptx |
| PDF to SVG | pdf2svg |
| SVG to EMF | Inkscape |
| CLI Output | rich |
⚠️ Known Issues
Transparent Background
Elements with transparency are not fully supported due to dependency limitations. You will receive a warning when such issues are detected. You can manually copy the generated SVG to fix the problem.
See #1 for more details.
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
Copyright © 2023-2024 Teddy van Jerry (Wuqiong Zhao)
⭐ Star History
📱 Follow Us

Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.