About Slurp MD
A free, privacy-first tool that turns messy real-world documents into clean Markdown for AI workflows.
Why Slurp MD exists
If you have ever tried to paste a PDF into ChatGPT or feed a QuickBooks export to Claude, you know the problem. Real-world documents are messy. Excel exports come with company names in row 0, blank columns, and "Unnamed: 4" headers. PDFs lose their tables. Word documents arrive with stray formatting.
AI assistants work best when given clean, structured Markdown. Slurp MD converts 25+ document formats into exactly that, with no signup, no cost, and (for PDFs) no file ever leaving your browser.
What it does
- 25+ formats supported: PDF, Word, Excel, PowerPoint, EPUB, HTML, CSV, JSON, image OCR, audio transcription, and more.
- Smart Clean Mode for spreadsheets: detects real headers when business software puts the company name in row 0; strips empty columns; preserves accounting acronyms (YTD, AP, AR) in title case.
- Privacy-first PDFs: PDFs are processed entirely in your browser. Other formats use a stateless server that deletes files immediately after conversion.
- Free for everyone: 256MB max file size, all clean modes, batch up to 50 files. No tier system, no signup wall.
The tech behind it
The site is built with Astro (static, fast). The conversion engine is server-side with a custom pipeline for spreadsheet cleanup, OCR for scanned PDFs, and lossless PDF compression. The API is hosted on Hetzner.
Who built it
How it stays free
The static site is on Netlify (free tier). The API runs on a small Hetzner box. Plausible Analytics (self-hosted, no cookies) costs near zero. There is no investor pressure, no growth-at-all-costs roadmap. Slurp MD stays free because it is cheap to run and useful.
If it saves you time and you want to support it, the most useful thing you can do is share it with someone who would benefit, or tell us what you wish it did better.