PDF to Markdown with Layout
turn scanned PDFs and document screenshots into structured Markdown with page blocks, tables, formulas, and source review.
Use formatted OCR for reports, statements, manuals, papers, and multi-page PDFs.
PDF to Markdown with Layout Tool
Drag and drop your file here, or click to select
Supports JPEG, PNG, GIF, WebP, BMP, TIFF, HEIC, PDF
Maximum file size: 20MB
Batch upload: up to 20 files
Paste an image or image URL from clipboard
Markdown output that keeps document structure visible
This page focuses on the gap between raw PDF text extraction and usable Markdown. It is for PDFs where headings, tables, formulas, and page boundaries matter.
Page-aware results
Multi-page PDF recognition is grouped by page so review and export stay predictable.
Markdown structure
Formatted OCR keeps headings, paragraphs, lists, tables, and formula markers where possible.
Editable blocks
Correct text blocks before copying or downloading the final Markdown.
Batch and API
Use batch OCR for multiple PDFs or the OCR API for automated ingestion.
Layout Markdown vs basic extraction
Basic extractors can miss document structure. Formatted OCR is designed for reviewable Markdown.
| Output need | Formatted OCR Markdown + JSON | Simple OCR Plain text | PDF text layer If available |
|---|---|---|---|
| Structure | |||
| Headings and paragraphs | Flat text | Depends | |
| Tables | Formatted blocks | Often broken | |
| Formula preservation | Best effort | ||
| Workflow | |||
| Page grouping | Depends | ||
| Editable OCR result | |||
| API automation | Custom | ||
Example output
A scanned PDF can become structured content that is easier to review and reuse.
Markdown heading
# Product Requirements | ## Acceptance Criteria | - OCR result is editable
Table Markdown
| Metric | Current | Target | converts into a copyable table when recognition finds rows and columns.
Page JSON
Each page can include blocks with type, text, confidence, bbox, and page index.
PDF to Markdown FAQ
Notes on scanned PDFs and layout preservation.
Convert a PDF into usable Markdown
Upload a sample PDF, inspect page-level output, and export Markdown or JSON.