Snip Snipping Tool Chrome Extension OCR API Files API Private Cloud OCR Secure Conversion Service
Make Documents Accessible Process Chemical Documents Collaborate on Documents OCR API for Developers Train Language Models Support Academic Research Artificial Intelligence Fintech Edtech Pharma & Chemical Universities & Schools
Handwriting Recognition Digital Ink On-prem PDF Cloud Mathpix Markdown All Supported Languages Image Conversion PDF Conversion Markdown Conversion Table OCR Mathpix CLI PDF Search PDF Reader PDF Data Extraction Chrome Extension View Conversion Gallery
Snip APIs Private Cloud OCR SCS
Mobile Desktop Web Chrome Extension
Mathpix Snip Apps Mathpix OCR API Mathpix Markdown Python SDK
Blog
About Careers Contact
Contact Get Started

Convert PDF to LaTeX

Mathpix Snip converts scientific PDFs to editable LaTeX files in minutes. Export as .zip or open directly in Overleaf.

  • Equations come back as LaTeX source, not as images
  • Theorems, lemmas and proofs keep their environments
  • Two-column journal layouts read in the right order
  • Easy exporting to Overleaf in seconds

LaTeX that compiles

Recognizing a research paper means recognizing its structure, not only its characters. Equations, theorem environments, algorithm blocks and figure captions each come back as themselves.

Equations come back as source

You get the LaTeX, not a screenshot. That is the difference between a paper you can build on and a PDF you can only read.

Theorem environments are preserved

Theorems, lemmas, corollaries and proofs are a documented Mathpix Markdown structure, so they export as environments rather than as bold paragraphs.

Algorithm blocks keep their shape

Pseudocode blocks are recognized as their own structure instead of being reflowed into prose and losing their line breaks.

What Mathpix recognizes in PDF files

Reading order on multi-column pages

The two-column layout most journals use is resolved during recognition, so the LaTeX is in reading order rather than column order.

Algorithms keep their line structure

The lines.json conversion format returns code and pseudocode line types, and algorithm and pseudocode diagram subtypes.

Per-line geometry and confidence

Every line carries a bounding box and a confidence score, so a long document can be spot-checked where the model was least sure.

Mathpix is ace. That’s the best results I got so far for scientific papers and reports. It understands the layout of complex documents very well, it’s quite impressive.

— kergonath Hacker News

How to convert PDF to LaTeX

1

Upload the paper

Drag the PDF into the Mathpix Snip web editor, or pick it from your files.

2

Choose which pages to convert

Enter a page range, or leave it blank for the whole document. Useful when you only need one section of a long paper.

3

Let the recognition run

Equations become LaTeX source, theorem environments stay environments, and two-column pages come back in reading order.

4

Export the LaTeX source

Export → LaTeX in the top right, as a .tex file or a zip carrying the figures with it.

What Mathpix accepts, and the limits that apply

Which files you can send

PDF, EPUB, Word (DOCX, DOC), PowerPoint (PPTX), OpenDocument Text (ODT), DjVu, WordPerfect (WPD), Mobipocket (MOBI) and Amazon Kindle (AZW3)

What you get back

A tex.zip archive carrying the LaTeX source and the extracted figures alongside it. The same conversion opens directly in Overleaf.

The size limits that apply

One PDF, uploaded: 1 GB

Files API, per file: 15 GB

Files API, files per job: 200,000

Our PDF to LaTeX conversion tools

Snip Web App

Snip Web App

Digitize PDFs, edit, and export to DOCX, LaTeX, Markdown, and HTML.

Go to Snip
On-premise PDF Cloud

On-premise PDF Cloud

Use all PDF processing features with a self-hosted, fully contained solution.

Learn more
Chrome Extension

Chrome Extension

Add and digitize PDFs directly from your browser.

Learn more

MPX CLI

Convert PDF files from the command line without uploading them online.

Learn more

Converting PDF to LaTeX: common questions

Do I get the LaTeX for the equations, or images of them?

The LaTeX. Equations are recognized as math and written as source, which is the whole point of converting a paper rather than reading it.

Are figures included?

Yes. Export as a zip and the extracted images come with the .tex, already referenced from it.

Will it compile without editing?

Usually, and where it does not the problem is almost always a package the original document assumed. The structure is there; the preamble is the part worth checking.

Can I send a whole book?

Up to 1 GB in one upload. Beyond that the Files API takes 15 GB per file and 200,000 files per job.

Other formats you can convert PDF to

PDF to Word

Convert PDFs to editable Word documents.

PDF to Overleaf

Open converted LaTeX directly in Overleaf.

Keep the reading order on journal pages

Two-column layouts, resolved during recognition.

PDF to Markdown

Convert PDFs to Mathpix Markdown.