MinerU2PPT
Converts PDF files and images into fully editable PowerPoint presentations using MinerU structural data.
Turn static design assets and documents into modifiable PowerPoint decks using structural data.
MinerU2PPT is a specialized utility that bridges structural extraction and presentation authoring by taking MinerU JSON output and rebuilding documents into true PowerPoint files. It targets professionals who routinely need to reverse-engineer static PDFs or images back into fully editable slide decks without rebuilding layouts manually.
What it is
The application reads structured data from the MinerU PDF Extractor along with source files to reconstruct text, images, and layouts into editable `.pptx` presentations. It provides both a user-friendly graphical interface with batch processing capabilities and a command-line interface with advanced OCR device configuration and font sensitivity controls.
Who it's for
It suits professionals, designers, and analysts who spend hours manually recreating slides from static PDFs or image exports. It does not suit users looking for an all-in-one PDF reader or those unwilling to process files through external extraction tools first.
Key features
GUI and Batch Mode
Offers a Windows graphical interface supporting single files and multi-task batch conversion queues.
Watermark Removal
Includes an optional setting to automatically erase footers and page number elements during assembly.
OCR Refinement Controls
Exposes command-line parameters for OCR device policy, model variants, and font distance thresholds.
High-Fidelity Reconstruction
Rebuilds text boxes, images, and layouts accurately rather than flattening pages into static screenshots.
Up and running in 3 steps
Our honest verdict
What's great
- Outputs native editable PowerPoint elements instead of static images.
- Provides packaged Windows installers for CPU and multiple CUDA versions.
- Supports batch processing to queue and convert multiple documents sequentially.
- Includes CLI options for fine-tuning OCR device policies and bounding box sensitivity.
Where it falls short
- Requires you to first process your files through the external MinerU extractor to obtain the required JSON data.
- Packaged GUI releases are currently limited to Windows environments.
- Running advanced GPU-accelerated OCR tasks demands compatible Nvidia hardware and specific CUDA runtimes.
Pricing & license
The tool is free to use under its repository setup, though the README does not state a formal open-source license. There are no paid hosted options mentioned, so the only cost is your own hardware and time running it.
Open remote AI-training roles
870 open remote AI-training roles, updated November 14, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
Alternatives
These reviewed AI tools do the same job instantly — from our scored directory.
Use it, or have us set it up
FAQ
Do I need to install Python to use this tool?
No, if you use the packaged Windows release variants, Python and dependencies are bundled for you.
Where do I get the JSON file required for conversion?
You must upload your PDF or image to the online MinerU extractor tool to generate and download the layout JSON.
Can I process multiple files at the same time?
Yes, the GUI features a Batch Mode where you can add multiple conversion tasks to a sequential processing queue.
