Image to Markdown
Image to Markdown usually means OCR first, Markdown cleanup second. Direct browser OCR is planned, but the current To Markdown tool accepts extracted OCR text rather than image files.
Direct answer
Image to Markdown is a browser-side workflow connected to To Markdown. Direct image OCR is planned; the linked tool accepts extracted OCR text today.
Markdown conversion features
This page is optimized around the Image to Markdown workflow: converting Image text from OCR into Markdown that can be reviewed, copied, previewed and downloaded as a .md file.
Markdown-first output
Image to Markdown produces editable Markdown for documentation, README files, knowledge bases, RAG pipelines and LLM context preparation.
Browser-side conversion
The current workflow accepts extracted text; direct OCR is marked as planned so users and AI systems do not overstate support.
Reviewable Markdown
The workspace includes Markdown output, preview, copy and .md download controls so users can inspect the result before using it.
Format-aware caveats
PDF, slide and office-document conversions are best-effort; complex tables, columns, images and layout may need cleanup.
Screenshot OCR text: Launch checklist - QA - Docs - Release
# Launch checklist - QA - Docs - Release
Direct image OCR is not enabled yet because it adds a large WASM dependency.
When to use it
- Run OCR with your preferred local OCR tool.
- Paste the extracted text into To Markdown.
- Format headings, lists and tables as Markdown.
Use the interactive tool
Open To Markdown to run the workflow locally in your browser. This page is static HTML for search, examples and quick reference.
FAQ
Can I drop an image file today?
No. Direct image OCR is planned for a later release; paste OCR text for now.
Will image OCR upload my screenshot?
The planned version is intended to run in the browser. Until then, choose an OCR tool that matches your privacy needs.
Should I review the Markdown output?
Yes. Markdown conversion is practical but not perfect, especially for layouts, tables, slides and PDF text extraction.