Screenshot to Text
Extract editable text from photos, scans and screenshots in 28 languages.
- Add images by dropping, choosing or pasting them.
- Adjust the options — everything previews on your device.
- Run, compare before and after, then download or share.
Image to Text (OCR)
Drop a photo of a document, a scan or a screenshot and the text is recognised on your device with the open-source Tesseract engine; nothing is uploaded. Correct the text in place, then copy it or download it as a TXT file, a Word document or a searchable PDF. Pick the language of the text for the best accuracy, and add a second language for pages that mix two, such as Hindi and English. Crop to the text area and use a sharp, well-lit photo for the cleanest result.
How it works
- Add images by dropping, choosing or pasting them.
- Adjust the options — everything previews on your device.
- Run, compare before and after, then download or share.
Frequently asked questions
Which languages can it read?
All 28 languages of this site, including English, Hindi, Arabic, Russian, Indonesian and every EU language. Choose the language of the text; for mixed pages add a second language. Each language model downloads once (1 to 4 MB) and is then cached.
Can I edit the text and save it as Word?
Yes. The recognised text appears in an editable box. Fix any mistakes, then copy it, or download it as TXT or as a Word document (.docx) that opens in Word, Google Docs and LibreOffice.
How do I get the best accuracy?
Use a sharp, evenly lit photo taken straight on, crop to the text, and pick the right language. Printed text works best; handwriting is recognised only roughly.