How to extract text from an image
- Drop an image into the box, or press Ctrl+V (⌘V on Mac) to paste a screenshot.
- Wait a few seconds while the text is recognised. The first time, the recogniser (about 7 MB) is downloaded once.
- Edit the text if needed, then copy it or download it as a .txt file.
Tips for the best result
- Use a sharp, straight photo with good lighting.
- Screenshots work best: they are perfectly sharp.
- Crop away anything that isn't text.
- The recogniser is trained for English and works well for most languages that use the Latin alphabet; accents may need a quick check.
Private OCR
Most online OCR tools upload your image to a server. This one uses Tesseract, the open-source OCR engine, compiled to run inside your browser — ideal for invoices, letters and other private documents.
Frequently asked questions
Is my image uploaded?
No. Text recognition happens in your browser; your image never leaves your device.
Which languages are supported?
The English model is used. It also reads most text in other Latin-alphabet languages, but accented letters may need a check.
Can it read handwriting?
Neat print works reasonably; joined-up handwriting usually doesn't.
Can I convert a PDF?
Convert the PDF pages to images first with our PDF to JPG tool, then drop them here.