Pick the integration that fits your toolchain. Every channel below is an official release (crates.io / npm / PyPI) — safe to use.

Prefer not to install? Convert in your browser

No setup needed — drop a document in, get Markdown out instantly. Everything runs locally.

Convert a Document

R

Rust

Native library

cargo add anydoc, then anydoc::to_markdown("report.docx")? — results in milliseconds.

Install from crates.io

JS

Node.js

npm package

npm install @firecrawl/anydoc — TypeScript types included, runs on the libuv thread pool without blocking the event loop.

Install from npm

Py

Python

PyPI package

pip install firecrawl-anydoc — releases the GIL during conversion, plays well with asyncio and threads.

Install from PyPI

W

Browser

WebAssembly

npm install @firecrawl/anydoc-wasm — converts locally in the browser; files never leave the device.

Install from npm

>_

CLI

No setup required

npx @firecrawl/anydoc report.docx prints Markdown directly, and it can read from stdin.

See CLI usage

AI

Agent Skill

Plug into AI agents

npx skills add firecrawl/anydoc — lets Claude Code / Codex / Cursor read your office documents directly.

Install from skills.sh

Before you install

• Only use official releases (crates.io / npm / PyPI / skills.sh). Avoid unofficial mirrors or third-party downloads.
• Node.js needs Node ^18 or newer; the Rust crate works on stable toolchains; the WASM package needs no server at all.
• For the Agent Skill, your AI coding tool must support the skills protocol (Claude Code, Codex, Cursor, etc.).

Hit a snag? Check these common questions.

How do I convert my first document?

The CLI is the fastest path: npx @firecrawl/anydoc report.docx prints to stdout, npx @firecrawl/anydoc slides.pptx -o slides.md writes to a file, and npx @firecrawl/anydoc - --format csv < data.csv reads from stdin. Full walkthrough in the getting started guide.

How do I use it in Node.js?

import { toMarkdown } from '@firecrawl/anydoc'
const markdown = await toMarkdown('report.docx')

The complete API is in the API quick reference.

How do I use it in Python?

import anydoc
markdown = anydoc.to_markdown("report.docx")

The complete API is in the API quick reference.

How do I use the WASM build in the browser?

import init, { toMarkdownBytes } from '@firecrawl/anydoc-wasm'
await init()
const markdown = toMarkdownBytes(bytes)

The converter on this very site is built with this package. See convert online.

Which formats can it convert?

14 formats: Word (.doc/.docx/.docm), PowerPoint (.ppt/.pptx/.pptm/.pps/.ppsx/.ppsm/.pot), Excel (.xls/.xlsx/.xlsm/.xlsb), OpenDocument (.odt/.ods/.odp), RTF, EPUB, CSV, and PDF. Scanned PDFs are not supported (they need OCR) and return an Unsupported error.

How fast is conversion?

Official benchmark: 4.4ms median conversion time, full coverage of 100 real documents across 14 formats, and an overall score of 81. See the benchmark.

Contributors: souvc