Pull the text out of a photo or scan.
How to use Scanned Document Reader
Add a photo or scan. Drop an image of the document onto the page, or choose a file.
Pick the language. Choose English, Spanish, French or German.
Extract the text. Click Extract text and wait for the progress to finish.
Copy the result. Click Copy text. The tool also shows the word count and a confidence percentage.
Limits and privacy
- Text recognition runs in your browser. The image is not uploaded.
- The first run downloads a language model of a few megabytes, so it needs an internet connection and can take a moment.
- One image at a time, up to 20 MB.
- Languages: English, Spanish, French and German.
- Only image files are accepted. For a scanned PDF, use the OCR PDF tool.
- The confidence figure is the OCR engine's own estimate, not a measure of how correct the text is. Check the result against the original.
- Without an account you get 3 free actions on this tool every 24 hours; signing in removes the cap.
Frequently asked questions
Is my document uploaded?
No. The image is read by an OCR engine running in your browser. Only the language data is downloaded.
Why is the first run slow?
The engine fetches a language model the first time you use a language, then reads the image.
Can it read handwriting?
It is built for printed text. Handwriting is likely to come out wrong or empty.
What does the confidence percentage mean?
It is the OCR engine's own average confidence in the words it recognised. A low value suggests the image was unclear.
Can I read a scanned PDF?
This tool takes images only. Use the OCR PDF tool for PDFs.