Drop an image and click Extract text. The OCR engine runs 100% on your device: your image is never uploaded. On first use the engine and models (about 25 MB) download once and are cached by your browser. English, Spanish and Urdu are supported — pick the text language below.
Best on printed Urdu (Naskh). Nastaliq script is best-effort.
Pull editable text out of photos, scans and screenshots — free, in your browser.
100% free · No sign-up · No daily limits · No watermarks · Processed in your browser — files never leave your device
Extract editable text from photos, scans and screenshots using OCR that runs entirely in your browser. No upload, no sign-up: drop an image, click Extract text, then copy or download the result as a text file.
A phone photo of a printed page usually extracts in a few seconds. A 2,000 × 1,500 screenshot of a settings screen produces clean, selectable text that can be pasted into notes, an email or a document.
OCR (optical character recognition) is performed by the PP-OCRv5 engine (open source, Apache-2.0) running locally in your browser via WebAssembly: a Latin-script model covers English and Spanish, and an Arabic-script model covers Urdu. Each image is read several complementary ways and the readings are combined line by line, which is why designed text — posters, banners, coloured headlines — reads far better than with a single pass. It analyses the shapes of letters in the image and reconstructs words and lines. The image is processed in device memory only — it is never sent to a server.
No. The OCR engine runs in your browser using WebAssembly. Your image never leaves your device, which makes this safe for documents, IDs and private screenshots.
The first use downloads the recognition engine and English language data (about 25 MB in total) and your browser caches them. Later extractions on this device skip that download.
Straight-on, well-lit images where the text is large and in focus. Crop away clutter, avoid photographing screens at an angle, and prefer scans or screenshots over camera photos where you can.
Handwriting is unreliable with this engine. For languages, use the Text language selector: English, Spanish (accents included) and Urdu are supported — Urdu reads best in printed Naskh, and Nastaliq is best-effort. Printed text — mixed case, numbers and common punctuation — works well.
Low resolution, blur, low contrast or text over busy backgrounds confuse character shapes. Try a larger, sharper version of the image, or crop it to just the text area and run it again.
What is missing, broken, or could be better on this tool? Tell us — we read every suggestion.
✅ Thanks — your suggestion has been received. Suggestions like yours shape what we build next.