---
title: "PDF to DOCX & Markdown Converter"
method: POST
path: "/v1/tools/convert_pdf_to_docx_markdown"
tags: ["PDF", "DOCX", "Markdown", "conversion", "document", "OOXML", "pdf.js", "text extraction"]
---

# PDF to DOCX & Markdown Converter

`POST /v1/tools/convert_pdf_to_docx_markdown`

## Request

- Base URL: `https://ainumbers.co`
- URL: `https://ainumbers.co/v1/tools/convert_pdf_to_docx_markdown`
- Auth: none declared

Converts the text layer of a PDF into a Markdown file and a DOCX file: column-aware reading order recovered by a band-first recursive XY-cut (full-width horizontal bands first, aligned table rows detected before any column split, then vertical gutters flanked by real text columns on both sides), font-size heading tiers plus all-caps section headings, paragraphs with end-of-line hyphens rejoined, bulleted and numbered lists, and best-effort tables. Detects and reports pages with no text layer, and flags pages whose text runs reach the right page boundary, instead of shipping silent clipping or empty output. Entirely client-side, zero network calls, pdf.js inlined workerless.

**Tool URL:** https://ainumbers.co/tools/643-pdf-to-docx-markdown-converter.html

## Request body

- object
  - `pdf_file` string, binary, required

## Response `200`

Successful tool execution result

- object
  - `markdown` string
  - `docx_base64` string
  - `scanned_pages` integer[]
  - `input_sha256` string
  - `output_sha256_md` string
  - `output_sha256_docx` string
  - `pdfjs_version` string

---

[API](https://skmtc.dev/ainumbers/apis/ainumbers-co-fintech-intelligence-suite.md) · [All operations](https://skmtc.dev/ainumbers/apis/ainumbers-co-fintech-intelligence-suite/llms.txt) · [OpenAPI document](https://skmtc.dev/ainumbers/apis/ainumbers-co-fintech-intelligence-suite/revisions/b462e4f5bb28?raw)