Extractor — Paper to Markdown

Step 1 — Choose outputs

Output formats

Select every format you want back. Formats that can't be produced from a document are reported honestly.

Markdown

.md

JSON

.json

DOCX

.docx

LaTeX

.latex

HTML

.html

Step 2 — Drop a document

Upload & extract

Drag & drop a single file, or click to browse. We handle the upload, conversion and downloads.

# * { } [ >

Drag & drop your document here

or click to browse — PDF, images, Word, Excel, PPT

PDFPNGJPG WebPTIFFDOCX PPTXXLSXMD

≤ 100MB per file · PPT ≤ 20MB · TIFF ≤ 15MB · up to 200 pages

document.pdf

0 KB— pagesFile ready to extract

— Queued

Sign Upload Convert Format Done

Original —

File preview will appear here

Recent Extractions

Extraction History

Your last 20 extractions saved locally. Persists across page reloads.

0 items

No extractions yet

What you get

Five structured perspectives

Every output is derived from the same full-layout parse, so they stay perfectly in sync.

Markdown

Clean, readable Markdown with tables, code fences and inline math — ideal for LLMs, docs and notes.

JSON

Structured middle JSON with blocks, spans and coordinates — perfect for RAG pipelines and programmatic access.

DOCX

Editable Word document with reconstructed headings, tables and formulas — ready for further editing.

LaTeX

Fully typeset LaTeX including formula environments — perfect for academic papers and journals.

HTML

Semantic HTML preserving structure and styling — ready to embed in any web page or email.

Secure & Private

Files are deleted immediately after processing. Your documents always belong to you.

Start extracting documents for free

Sign up for a free quota. Members unlock batch processing and large files. Data bound to your account, synced across devices.

See pricing