Convert PDF to Word with OCR
Convert scanned and image-only PDFs into editable text for Word. Today the result is Markdown you can paste into Word or convert with Pandoc.
Your Markdown or JSON shows up here.
3 free pages a day, no sign-up.
Word (.docx) download is coming soon. For now you get Markdown you can paste into Word or turn into .docx with Pandoc.
How it works
- Step 1Upload your PDF
- Step 2OCR reads every page, scans included
- Step 3Paste into Word or convert to .docx
Why use this PDF to Word (OCR) converter
Image-only pages are read with OCR, which is the part most PDF to Word converters skip or charge for.
Structure comes through as Markdown, which Pandoc turns into real Word headings and tables.
Columns and page headers are handled, so paragraphs are not cut up across lines.
What people use it for
- Editing a scanned contract or agreement
- Updating an old document when only a scanned PDF is left
- Getting a scanned form into Word to fill it in
- Translating a scanned document in Word
Models that do this well
The free tool picks one for you. With the API you choose, and can set fallbacks so a failed page is retried on the next model.
mistral/mistral-ocr6 credits / page2MarkerHosted version of the open-source Marker and Surya models. Strong on books and papers.datalab/marker14 credits / page3LlamaParseDocument parser built for RAG pipelines, with several quality tiers.llamaindex/llamaparse5 credits / page4Azure Document IntelligenceAzure layout model with tables, selection marks and prebuilt invoice and ID readers.azure/document-intelligence15 credits / pageDo it with the API
Converting more than a few files? The same conversion is one request. Pick any model, or let auto choose.
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "auto",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'