Make a PDF searchable
Find out what text is in a scanned PDF. Today you get the recognised text; a searchable PDF download is coming soon.
Your Markdown or JSON shows up here.
3 free pages a day, no sign-up.
Searchable PDF download is coming soon. For now you get the recognised text of each page, which you can search and copy.
How it works
- Step 1Upload the scanned PDF
- Step 2OCR reads every page
- Step 3Search or copy the recognised text
Why use this Make PDF searchable converter
You get the text, page by page, which is what search needs. The PDF itself is not modified yet.
The output marks where each page starts, so a search hit tells you which page to open.
Through the API, you can store the text per page in your own search tool and link back to the PDF page.
What people use it for
- Checking what text is in a scanned archive before choosing a tool
- Building a full-text search over scanned PDFs through the API
- Finding which page of a long scan mentions a name or number
- Getting the text of scans for e-discovery or records work
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 / page2Amazon TextractAWS OCR with form key-value pairs, tables and per-word confidence scores.aws/textract6 credits / page3Azure Document IntelligenceAzure layout model with tables, selection marks and prebuilt invoice and ID readers.azure/document-intelligence15 credits / page4TesseractThe classic open-source OCR engine. Plain text from clean printed scans.tesseract/tesseractFreeDo 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"
}'