# breezedeus/Pix2Text

An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

Repository: https://github.com/breezedeus/Pix2Text
Canonical: https://ross.abutalabs.com/products/pix2text
Homepage: https://p2t.breezedeus.com
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: math-formula, ocr, latex, math-formula-recognition, mathpix, python, pytorch, layout-analysis, math-ocr, table-ocr, image-to-markdown, latex-pdf
Last push: 2026-08-23T09:24:13+00:00

## Health v2 (maintenance only)
Score: 99/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 100
- inputs: {"age_days": 1456, "days_push": 10, "days_rel": 10, "gap_med": 13.5, "n_releases_24m": 11}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3227, forks 284 (observed 2026-08-28T04:07:49.993091+00:00)

## What it is
Pix2Text is an open-source Python tool that recognizes layouts, tables, math formulas (LaTeX), and text in images and converts them into Markdown, supporting 80+ languages. It uses small PyTorch models and serves as a free alternative to Mathpix.

## Use cases
- convert math formula images to latex
- ocr scanned documents to markdown
- extract tables from images
- convert pdf pages with formulas to markdown
- free mathpix alternative
- recognize text in 80+ languages from images
- layout analysis of document images

## When to choose
- you need to convert images or PDFs containing math formulas into editable LaTeX or Markdown
- you want a free, self-hosted alternative to Mathpix
- you need multilingual OCR combined with layout and table recognition in one pipeline

## When to avoid
- you need production-grade OCR for plain text only with minimal dependencies
- you cannot run Python/PyTorch or lack GPU resources for the models
- you need a fully managed cloud OCR API with SLAs

## Facets
- artifact type: library
- maturity: active
- function: ocr, image-processing, nlp, pdf, parser
- domain: computer-vision, image-processing, pdf, developer-tools
- platform: python, cross-platform, cli
- tags: math-ocr, latex, image-to-markdown, layout-analysis, table-recognition, mathpix-alternative, pytorch, natural-language-processing

## Member repositories
- breezedeus/Pix2Text (main) score 99

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:49.993091+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:44:09.727887+00:00, confidence not recorded.
  - readme: https://github.com/breezedeus/Pix2Text (fetched 2026-08-28T04:07:49.993091+00:00, sha 1f4fe9190dda)
  - homepage: https://p2t.breezedeus.com (fetched 2026-08-29T09:37:49.641482+00:00, sha 3c5fe5de25af)
  - registry_pypi: https://pypi.org/pypi/pix2text/json (fetched 2026-08-29T09:37:49.650493+00:00, sha 1ba5d8ea0519)
- Data as of 2026-08-30T08:39:29.467469+00:00.