Read any menu, sign or document in your language

Two engines work in series: OCR extracts the original text from the photo, then a large-language-model translator renders it into your target language with context awareness. Idioms, menu items, brand names and short signs translate cleanly. For long literary passages, expect the same quality as a top-tier consumer translator like DeepL or Google Translate.

Yes. English, Spanish, French, German, Italian, Portuguese, Dutch, Russian, Polish, Turkish, Arabic, Hebrew, Hindi, Bengali, Tamil, Chinese (Simplified and Traditional), Japanese, Korean, Vietnamese, Thai and Indonesian are supported in both directions. Translate French → English, Japanese → Spanish, Chinese → Hindi and any other pair across the supported set.

Clean block-letter handwriting and chalkboard menus work in most cases — the OCR is tuned for everyday signage and casual handwriting. For cursive, dense handwritten letters or doctor's prescriptions, use our Handwriting OCR tool first to extract the text, then paste it into a translator for higher accuracy.

Yes. One upload triggers OCR, language detection, translation and side-by-side display. You can also see the original text on the left and the translation on the right, making it useful for language learners who want to compare phrasings. Tap a word to hear its pronunciation in the target language.

Uploads are processed and auto-deleted within 24 hours — unless you explicitly share a result, which keeps it at a public link anyone who has it can open for up to 30 days. Translation history is not saved on the server — your last result is held only in your browser tab and clears when you close the page. That makes the tool safe for travel emergencies, medical leaflets and personal correspondence translations.

Yes. Copy buttons give you the original, translated, or both side-by-side in one click. Download buttons export plain .txt for notes, or a simple .docx for sharing with colleagues. Travelers paste it into WhatsApp; students paste it into Notion; agencies paste it into translation memory tools for cleanup.

It swaps the underlying text-recognition model used before translation. Default works well for most printed signs and menus; Engine 1 and Engine 2 are alternates that can read stylized fonts, low-contrast photos or scripts the default struggles with more accurately. If the detected text looks wrong before it's even translated, switching engines is the first thing to try.

Target-language changes re-translate automatically, but source language and engine changes require pressing the Re-run button — an amber notice appears telling you settings have changed. This is deliberate: OCR is a metered step, so the tool won't silently re-scan the image every time you touch a dropdown, only when you confirm a fresh read.

Yes. Once a translation is ready, a toggle button switches the result panel between the detected source text and the translated text, and each version has its own copy button. This helps language learners check how a phrase maps between languages, or verify the OCR read the sign correctly before trusting the translation.

Set the Source language dropdown to the actual language on the sign rather than leaving it on English, since OCR accuracy depends on matching the character set. Then try Engine 1 or Engine 2 if Default misreads stylized lettering — each engine has different strengths on decorative fonts and low-contrast photos. Getting the OCR text right matters more than the translation step, since a bad OCR read guarantees a bad translation regardless of target language.

Image language covers every script our OCR engines can read — around 30 languages depending on the OCR Engine you pick. Translate to draws from a shorter list of roughly 20 output languages that the translation backend supports. That means you can photograph text in almost any supported language, but the translated result can only come out in one of the languages shown under Translate to.

Yes — both the detected-text and translated-text boxes are editable, so you can type a correction directly into whichever one the toggle button is currently showing. Copy always grabs the text you're viewing at that moment, but Download .txt always saves the translated-text version specifically, even mid-edit on the original side — toggle to the translated view first if you want a source-text fix to carry into the downloaded file.

The upload accepts PNG, JPG, WEBP, GIF, TIFF, BMP, HEIC and HEIF, so an iPhone photo in its native HEIC format works without converting it to JPG first. Whichever format you use, set the Image language and OCR Engine to match the text in the photo before running OCR for the most accurate read.

Upload the picture, choose English and preview the translated text before signup. Copy it in the tool, or create a free account to download the standard .txt result.

Yes. Japanese is fully supported, so Japanese to English image translation works on menus, packaging, screenshots and manga pages with clear printed text. Dense stylised lettering and handwritten sound effects are harder — a sharp, well-lit photo of the page gives the OCR the best chance. Korean and Chinese (Simplified and Traditional) work the same way.