Convert a picture to text

Snap a page, a sign or a whiteboard and get editable text back, without sending the picture anywhere.

Turn a picture into text you can copy. Works with phone photos, HEIC from iPhone, screenshots and scans. It is free, needs no account and adds no watermark, and your files are not uploaded: everything runs in your browser on your device. The first run downloads the text reader (about 4 MB) and the WebAssembly engine that runs it to your browser, and after that the tool works offline.

Drop pictures to turn into textor click to choose files. Batches welcome.
    Details

    Reads printed English text. The first run downloads the text reader and its WebAssembly engine (about 4 MB) from this site; after that it works offline.

    Working…

    Done

    Free, no ads. Support StayPut

    Your files are processed on this device and never sent to a server. Reload the page to clear everything from memory.

    A picture of a page is easy to take and hard to use: you cannot search it, paste it into an email or edit a sentence. This page turns the picture into real text. It reads iPhone HEIC photos as well as JPG, PNG and WebP, so you can use the picture straight from your camera roll.

    Pictures of paperwork tend to be personal: a letter from the bank, a prescription, a child’s homework, a recipe from a relative. The text is recognised in your browser, by an OCR engine that this page loads from its own server, so the picture itself is never uploaded or stored anywhere.

    For the best result, take the photo straight on in good light, fill the frame with the text and keep it in focus. Printed text reads very well. Handwriting mostly does not, so treat anything handwritten as a rough draft to correct.

    Photographing a book? Take one page per picture rather than the whole spread. With two pages in one shot the reader can run lines from the left page into the right, and the curve near the spine bends the lines it needs to follow. Press the page flat, hold the phone parallel to it and turn off the flash, which leaves a bright patch that wipes out the words under it.

    The reader is set up for English. Pictures of French, Spanish or German text are still read, but accented letters are often swapped for plain ones or dropped, and other alphabets, such as Greek, Arabic or Chinese, will not come out. For a sign or menu in another language, expect a rough draft at best. Numbers, prices and dates come through well in any language, since the digits are the same.

    How it works

    1. Drop the picture, or tap to pick it from your photos. Several at once is fine.
    2. Choose whether to keep the line breaks from the picture or join them into paragraphs.
    3. Read text, then tap Copy text or save the .txt file.

    In your browser, not on a server

    Your browser decodes the image (libheif or the Squoosh decoders step in for HEIC, AVIF and JPEG XL), enlarges small screenshots so letters are big enough to read, and hands the pixels to Tesseract, the open-source OCR engine first built at HP and later developed by Google, compiled to WebAssembly by tesseract.js (Apache-2.0). Its neural network model for English is served by this site and loaded the first time you run it. The text is recognised line by line inside a worker in your tab.

    Compared with upload-based tools: The pictures people want text from are often private: a letter, a receipt, a bank statement, a prescription, a screenshot of a conversation. Online OCR sites upload the image to their server to read it and keep it for hours, and several limit free use or ask for an account. Here the image never leaves your device, and after your first run the page keeps working with Wi-Fi off.

    Verify it yourself. Give the page a short while after your first run to save itself for offline use, then turn off Wi-Fi or switch to airplane mode and run the tool again. Or open your browser's developer tools (F12, or Cmd-Option-I on a Mac), pick the Network tab, and watch it while you convert. The panel above does the same count for you.

    Questions

    Can I get a Word document instead of text?

    Yes. Image to Word reads the same way and saves one .docx with each image on its own page. Only the text comes across, not the layout.

    Can I use it on my phone?

    Yes. On an iPhone or Android phone, tap the drop area and choose a photo or take one with the camera. The first run downloads the reader and its engine, about 4 MB in all, so start it on Wi-Fi if your data plan is tight.

    Does it read handwriting?

    Only neat block capitals, and not reliably. The engine is trained on printed text. For handwritten notes expect to fix a good share of the words.

    Can it read other languages?

    It reads English. Languages written in the same alphabet mostly come through, but letters with accents, like é or ü, may be misread, so check names and words carefully. Text in other scripts, such as Cyrillic, Arabic, Hindi or Chinese, is not recognised and comes out as noise or not at all.

    Why are lines from my photo mixed up?

    This usually happens with a picture of two pages, several columns or a poster with text in separate blocks. The reader tries to work out the reading order and sometimes joins lines that sit side by side. Take one page or one column per picture and the order comes out right.

    Does it work on a photo of a computer screen?

    Often, but a screenshot is far better. Photos of screens pick up a wavy moiré pattern, reflections and a slight tilt, all of which cost accuracy. If you can reach the device, take a screenshot and drop that instead.

    Is the file uploaded anywhere?

    No. There is no server in this process. The page is a static file and the work is done by code running inside your browser tab. Give the page a short while after your first run to save itself for offline use; then you can turn off Wi-Fi and it still works.

    More image tools

    Other conversions

    Guides