OCR — Scanned Documents to Text

Recognize text in scanned PDFs and images — Georgian, English, and Russian — entirely in your browser.

Click or drag files here

Supports scanned PDFs and JPG/PNG images. Processed in your browser.

How it works

Select a file

Drag and drop a scanned PDF or a JPG/PNG image.

Pick the languages

Choose every language that appears in the document for accurate recognition.

Copy or download

Get the recognized text to copy or save as a .txt file.

Frequently Asked Questions

Does my document get uploaded for OCR?

No. Recognition runs in your browser via WebAssembly. The only thing fetched from the network is the OCR engine and language model, which download once and are cached — your document itself never leaves your device.

Which languages are supported?

Georgian, English, and Russian, individually or combined. Select all the languages present in the document so mixed-language pages are read correctly.

Why is OCR slower than the other tools?

OCR is computationally heavy — each page is analyzed pixel by pixel. Larger or multi-page documents take longer, and the first run also downloads the language model.