The first read downloads the OCR engine and the language data (about 2–4 MB, one time only). After that it is much faster.
Image to text: frequently asked questions
Is my image uploaded to a server?
No. The recognition runs in your browser. Only the OCR engine and the language data are downloaded, the image stays on your device.
Why is the first image slow?
The first time, the browser downloads the OCR engine and the language data (about 2–4 MB). They are cached afterwards, so the next images are read much faster.
Which languages are supported?
English, Portuguese, Spanish, French, German, Italian, Dutch, Polish, Turkish, Russian, Ukrainian, Arabic, Hindi, Bengali, Chinese (simplified and traditional), Japanese, Korean, Vietnamese and Indonesian.
Can it read handwriting or scanned PDFs?
Handwriting is not reliable with this engine, and PDFs are not supported yet. Export a PDF page as an image and drop it here.
How the image to text tool works
OCR (optical character recognition) turns the letters in a picture into text you can edit, search and copy. This tool runs the open-source Tesseract engine inside your browser, so your screenshot, photo or document is never uploaded.
Results are best with sharp, well-lit images and printed text. Handwriting and very small or blurry text are recognised poorly.
- 1 Paste a screenshot with Ctrl+V, drop an image or choose a file.
- 2 Pick the language of the text if it is not detected correctly.
- 3 Edit if needed, then copy the text or download it as a .txt file.