How to extract text from an image (OCR)
Turn the text in a photo, screenshot, or scanned document into editable text, right in your browser.
OCR (optical character recognition) reads the letters in an image and turns them into text you can copy. Instead of retyping a book page, an invoice, a sign, or a screenshot, you can have it as text in seconds.
Steps
1) Upload your image at /app/ocr. 2) Pick the language: Turkish, English, or both. 3) Hit 'Extract text'. 4) Edit the result, copy it to the clipboard, or download it as a .txt file.
Improving accuracy
Well-lit images where the text is flat and sharp give the best result. Crop and straighten documents photographed at an angle first. For very small text, enlarging the image 2× with the upscaler first improves recognition noticeably. Handwriting and decorative fonts have a higher error rate.
Recognition runs entirely in your browser with the Tesseract engine; your document is never sent to a server, which matters for sensitive files like invoices and IDs. Each recognition costs 1 credit.
Frequently asked questions
- Which languages are supported?
- English and Turkish, including Turkish-specific letters like ç, ğ, ı, ö, ş, and ü.
- Can I extract text from a PDF?
- Image files (JPG, PNG, WebP) are supported right now. You can save the pages of a scanned PDF as images and upload those.
- Is my document uploaded to a server?
- No. Recognition happens in your browser, and your file stays on your device.