Image to Text (OCR)
Extract text from photos, scans and screenshots in 7 languages — review, edit, copy or download as .txt. Recognition runs entirely in your browser.
Drop a file here or click to choose
This tool runs entirely in your browser. Your data never leaves your device — it is not uploaded to any server.
How to use
- 1Drop in one image (PNG, JPG or WebP) that contains text.
- 2Pick the language of the text — the matching model loads on first use.
- 3Run the recognition and edit the extracted text if needed.
- 4Copy it or download it as a .txt file.
Image to Text (OCR)
Point at any image that contains text — a photo of a page, a scan, a screenshot — and get the characters back as editable text. Recognition is powered by Tesseract, loaded on demand inside your browser tab; the image itself is never uploaded anywhere.
The output lands in an editable box, so you can fix the occasional misread before copying it or downloading it as a .txt file. Clean, evenly lit, straight-on shots give the best results.
Frequently asked questions
Does my image get uploaded to a server?
No. The image is read and recognized in your own browser. Be aware that the OCR engine and the language model are downloaded from a public CDN on first use (roughly 10–20 MB per language) — that download goes from the CDN to you, but the image itself never leaves your device.
Which languages are supported?
English, Simplified Chinese, Japanese, Spanish, Portuguese, German and French. Each language loads its own trained model the first time you select it; afterwards it is cached by the browser and recognition starts faster.
Why is some of the text wrong?
OCR accuracy depends heavily on the source: blurry photos, curved pages, small fonts and busy backgrounds cause misreads. Use the sharpest image you have, crop to just the text area, and expect to proofread — especially numbers and similar-looking characters.
Related tools
OCR PDF
Run OCR on scanned PDFs entirely in your browser — recognize English, Chinese, Japanese and more, then copy or save the text.
All tools →
PDF to Text
Pull plain text out of any PDF instantly — preview it, copy to clipboard or save as .txt, extracted page by page in your browser.
All tools →
Screenshot Tool
Capture a single frame of your screen, crop it precisely and save it as a PNG — one authorized snapshot, nothing recorded or uploaded.
All tools →
Image Metadata Viewer
Inspect image dimensions, file type, size and EXIF details — camera, lens, exposure, date and GPS — without uploading anything.
All tools →
Image Converter
Convert images between PNG, JPG and WebP with adjustable quality — drop a whole folder and download every result in one click.
All tools →
Embed this tool
Put this tool on your own site with one line — it runs entirely in the visitor's browser.
<iframe src="https://zoyku.com/en/tools/ocr-image?embed=1" width="100%" height="640" style="border:0;border-radius:16px" title="Zoyku — ocr-image" loading="lazy"></iframe>