Image to Text (OCR)
betaThis free image-to-text OCR tool pulls the words out of a photo, screenshot or PDF using an AI model that runs entirely on your device. Drop, paste or snap a picture, run OCR, then copy or download the recognized text — nothing is ever uploaded.
How to use Image to Text (OCR)
- 1 Drop or paste an image or PDF, click to browse, or use your camera.
- 2 Optionally rotate 90° or tick 'Clean up image' and adjust the threshold to sharpen faint text before reading.
- 3 Click Run OCR — the first run downloads the recognition model once, then it reads on-device.
- 4 Copy the recognized text or download it as a .txt file; tick 'Parse as receipt' to pull out structured fields.
Frequently asked questions
Are my images or PDFs uploaded for OCR?
No. Text recognition runs on-device using an AI model in your browser, so your files never leave your device. That makes it safe for IDs, receipts and confidential documents.
Why does the first run take longer?
The OCR model is downloaded once on first use and then cached. After that, recognition is faster because the model is already on your device.
Can I read a specific page of a PDF?
Yes. Multi-page PDFs get Prev and Next controls so you can move to the page you want, then run OCR on just that page.
Can it pull fields out of a receipt?
Yes. After OCR, tick 'Parse as receipt' and the tool extracts structured fields like merchant, totals and line items from the recognized text.