# Marker PDF-to-Markdown Converter

> Marker converts PDF, DOCX, PPTX, and image files to clean Markdown, JSON, and HTML with high accuracy. It handles tables, equations, code blocks, and multi-column layouts, with optional LLM-boosted extraction for maximum fidelity.

- Skill: `agentskillexchange/marker-pdf-to-markdown-converter` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/marker-pdf-to-markdown-converter`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/marker-pdf-to-markdown-converter/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Web & Frontend
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/marker-pdf-to-markdown-converter

---


# Marker PDF-to-Markdown Converter

Marker converts PDF, DOCX, PPTX, and image files to clean Markdown, JSON, and HTML with high accuracy. It handles tables, equations, code blocks, and multi-column layouts, with optional LLM-boosted extraction for maximum fidelity.

## Installation

Use the upstream install or setup path that matches your environment:
- pip install marker-pdf
- pip install marker-pdf[full]
- pip install streamlit streamlit-ace
- pip install -U uvicorn fastapi python-multipart

Requirements and caveats from upstream:
- Commercial self-hosting requires a license — see [Commercial usage](#commercial-usage). For on-prem licensing, [contact us](https://www.datalab.to/contact?utm_source=gh-marker-onprem).
- | [Think Python](https://greenteapress.com/thinkpython/thinkpython.pdf) | Textbook | [View](https://github.com/VikParuchuri/marker/blob/master/data/examples/markdown/thinkpython/thinkpython.md) | [View](https://github...
- You'll need python 3.10+ and [PyTorch](https://pytorch.org/get-started/locally/).

Basic usage or getting-started notes:
- See [below](#benchmarks) for detailed speed and accuracy benchmarks, and instructions on how to run your own benchmarks.
- # Commercial usage
- shell

- Source: https://github.com/datalab-to/marker
- Extracted from upstream docs: https://raw.githubusercontent.com/datalab-to/marker/HEAD/README.md

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/marker-pdf-to-markdown-converter/)