What Image to Text does
This tool pulls the words out of a picture and gives them back as text you can actually edit. Drop in a screenshot, a photo of a document, a scan or a receipt, choose the language, and it runs OCR — optical character recognition — to read the characters and hand you plain text to copy or download. It is built for the everyday moments when the words you need are trapped inside an image: a slide you photographed, a screenshot of a message, a scanned form, a book page or a receipt you want to retype.
Everything runs in your browser. Your image is read on your own device and never uploaded, so even a photo of a private document stays private.
How to extract text from an image
- Drag your image onto the drop zone, or click to pick it from your device.
- Choose the document language so the recognizer knows what alphabet to expect.
- Press Extract text. The first run downloads the language model once, then reads the image.
- Copy the text or download it as a .txt file.
Pick the language that matches the text — it reads accented letters (ç, ğ, ı, ñ, é) correctly when the right language is selected.
Key facts
| Attribute | Value |
|---|---|
| Input | PNG, JPG, WebP, BMP, GIF |
| Output | Editable text (copy or .txt) |
| Languages | 10, including Turkish, Spanish, French and Arabic |
| Privacy | Image read in your browser, never uploaded |
| Runs in browser | Yes — no upload, no sign-up, no watermark |
Why extract text here
There is no account, no watermark and no cost. Because the recognition happens on your own machine, a photo of a contract, an ID or a private note never leaves your computer. It works on a laptop, tablet or phone, and the extracted text drops straight into an email, a document or a search box.
For clean screenshots and scans this is all you need. Browse the rest of the free image tools to resize, convert or crop your pictures.
Frequently asked questions
- How does image to text work?
- Drop in a photo, screenshot or scan, pick the language of the text and press Extract. The tool runs OCR (optical character recognition) and returns the words as editable text you can copy or download.
- Is my image uploaded to a server?
- The image itself stays on your device and is read in your browser. The first time you use a language, its recognition model is downloaded once from a public CDN, but your picture is never uploaded anywhere.
- Which languages can it read?
- English, Turkish, Spanish, French, Italian, Portuguese, German, Dutch, Russian and Arabic. Pick the language that matches the text in the image for the best accuracy — it handles accented letters like ç, ğ, ñ and é.
- What kind of images work best?
- Clear, straight, high-contrast text works best — a screenshot, a scanned page or a well-lit photo. Blurry, skewed, handwritten or very low-resolution images give weaker results.
- Can it read a scanned PDF?
- This tool reads images (PNG, JPG, WebP, and similar). For a PDF, convert the page to an image first, or open the page as a screenshot, then run it through here.
Related image tools
Last updated: July 6, 2026