No. The PDF is parsed entirely in your browser using a WebAssembly-compiled PDF library. Your file never leaves your device. There is no upload, no server processing, and no copy of your document stored anywhere outside your tab.
Scanned PDFs are images, not text. The pages are pictures of text rather than actual text data, so there is nothing for the parser to extract. To convert a scanned PDF to Markdown you need OCR (optical character recognition) first. This tool does not perform OCR. If you have a scanned PDF, try running it through an OCR tool first and then converting the resulting text-based PDF here.
PDF does not store document structure — only character positions. The converter infers structure from the spatial layout: font size for headings, column alignment for tables, vertical gaps for paragraphs. This works well for standard single-column documents but struggles with multi-column layouts, academic papers, magazine-style content, and PDFs with complex overlapping elements. The raw text is still useful for AI ingestion even when the visual order is off.
There is no hard limit enforced by the tool, but very large PDFs (hundreds of pages or very high image density) may slow down or cause the browser tab to run out of memory. In practice, documents up to 50–100 pages convert reliably. For very large documents, consider splitting them first.
Large language models work with plain text. PDFs are binary files — models can't read them directly. Converting to Markdown gives you clean, structured text that you can paste into ChatGPT, Claude, Gemini, or a retrieval-augmented generation (RAG) pipeline. Markdown preserves headings and lists in a way that plain text extraction from copy-paste doesn't.
No. Password-protected PDFs require decryption before the text layer can be accessed. If you enter the correct password in a PDF viewer (like Preview or Acrobat) and then save a copy, that copy can be converted here. The tool cannot prompt for or bypass passwords.
Images are skipped. The converter extracts text data only. Charts, photos, diagrams, and embedded figures in the PDF are not included in the Markdown output. If the figures have captions, those captions appear as text. The images themselves do not.
Not in the current version — one PDF at a time. After conversion, copy the Markdown output before loading the next file, as loading a new file replaces the current output.