Image to Text (OCR)
Extract text from photos and screenshots – recognition runs in your browser.
Drop an image here
Or paste it from the clipboard (Ctrl+V)
The first time you use a language, its data (about 2–3 MB) is downloaded. It is kept in your browser afterwards.
How to use it
- Choose an image, drag it into the box, or paste it from the clipboard (Ctrl+V).
- Select the language of the text. If the text mixes two languages, add a second one, for example Lithuanian and English.
- Click Recognize text and wait for the progress bar to fill.
- Correct the result in the editable box, then copy it or download it as a .txt file.
Getting more accurate results
Accuracy depends mostly on the image. Sharp, straight-on photos of printed text on a light background work best.
- Shoot from directly above, without shadows or flash glare.
- Letters should be roughly 20–30 pixels tall or more; very small images recognise poorly.
- Pick the right language, since it affects accented letters such as ą, č, ę, š and ž.
- Handwriting, tables and complex layouts may contain errors, so always review the result.
Privacy and first use
Text is recognised on your device and the image is never uploaded. The first time you use a language, its data (about 2–3 MB each) is downloaded from this site and then kept in your browser cache, so the first run can take longer.