OCR · აბგ · ABC
Image to text: OCR for photos and scanned PDFs
Turn a photo of a document, a screenshot or a scanned PDF into text you can copy, edit and search. Toola runs the Tesseract OCR engine inside your browser and reads Georgian, English and Russian — even mixed on one page. Your files are never uploaded, so it’s safe for IDs, contracts and other private papers.
Private: your files never leave your device.
Best results: sharp, evenly lit, straight-on photos or scans of printed text.
How to use Image to text (OCR)
Step 1: Add photos, screenshots or a scanned PDF.
Step 2: Tick the languages in the text (Georgian and English are on by default) and press “Extract text”.
Step 3: Copy the text or download it as a .txt file.
Frequently asked questions
Does it recognise Georgian?
Yes. It uses Tesseract’s Georgian model, which reads printed Mkhedruli text. Handwriting and decorative fonts are much harder for any OCR.
Are my files uploaded?
No. The OCR engine and the language models are downloaded to your browser the first time (5–10 MB, then cached) and the recognition runs on your device.
How do I get the best results?
Use sharp photos taken straight on, with even light and no shadows across the text. A scan at 300 DPI works best. Tick only the languages that are really in the text.
Can it read a scanned PDF?
Yes, up to 50 pages at a time. Each page is turned into an image and read; the text is labelled by page.