How to use it
- Make sure you are logged in with a Pro account.
- Choose or drop a PNG, JPEG or WebP image.
- Select the language of the text. Tick “Also recognise English words” for mixed text.
- Click “Extract text” and wait for the progress bar. Correct any mistakes in the box, then copy or download the text.
How it works
Text recognition uses Tesseract, an open-source OCR engine, compiled to WebAssembly and running inside your browser. The first time you use a language, the engine and that language's data (a few megabytes) are downloaded from a public CDN; your browser may cache them for later.
Recognition works best on sharp, evenly lit images of printed text with good contrast, such as screenshots and scans. Handwriting, very small text, strong perspective, curved pages and decorative fonts give poor results. Choosing the correct language matters, especially for accents and non-Latin scripts.
The result box is editable so you can fix mistakes before copying. The confidence value is Tesseract's own average estimate and is only a rough guide. The maximum image size depends on your plan.
Examples
Copying text from a screenshot
Take a screenshot of an error message or a slide, drop it here with English selected and paste the text into an email or search box.
Digitising a printed page
Photograph a page of a Turkish book in good light, choose Turkish and get editable text with the correct ç, ğ, ı, ö, ş and ü characters.
Frequently asked questions
Is my image uploaded?
No. The image is processed in your browser. Only the OCR engine and language data are downloaded from a CDN; the image itself is never sent anywhere.
Can it read handwriting?
Only very neat block letters, and not reliably. Tesseract is designed for printed text.
Why is the first run slow?
The first time, your browser downloads the engine and the language data. Later runs can reuse the cached files and start faster.
Does it work with PDFs?
Not directly. Convert the PDF page to an image first (for example with a screenshot) and then upload the image.
Privacy
The image is processed locally in your browser and is not uploaded to TIG or anyone else. To run, the tool downloads the Tesseract OCR engine and the selected language data from a public CDN (jsDelivr), which can see that your browser requested these files. The recognised text is not stored or included in analytics.