Gemini

Verified against Gemini · 2026-08-01

Translate and culturally localize the text inside a photo, not just the words

A multimodal prompt for translating a photographed menu, sign, or label that asks for cultural and practical localization alongside the literal translation, instead of a flat word-for-word swap that produces something technically accurate but meaningless to the reader.

Gemini (Gemini 3 Pro)Gemini app4 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

Here's a photo of a restaurant menu board, originally in Japanese. Translate it into English for a first-time visitor from the US with no prior knowledge of the local cuisine.

For each item or line in the photo:
1. Give the literal translation first.
2. Then give a localized version if the literal translation would be confusing, misleading, or just odd to a English reader — explain in one line why you changed it (an idiom, a measurement unit, a culturally specific dish or reference the literal words don't convey).
3. Flag anything you can't read clearly in the photo as [unclear] rather than guessing at text that isn't actually legible — a confidently invented word based on a blurry photo is worse than an honest gap.
4. Convert any units, currency, or sizes to what's standard for a first-time visitor from the US with no prior knowledge of the local cuisine, noting the original figure alongside the conversion so nothing is silently lost.

If something in the source has no real equivalent in English or for a first-time visitor from the US with no prior knowledge of the local cuisine — a specific dish, an idiom, a cultural reference — say so explicitly instead of forcing an approximate translation that changes the actual meaning while looking fluent.

ALLERGENS AND DIETARY FLAGS
If the source text or common knowledge about the named dish suggests a common allergen or dietary consideration (shellfish, dairy, a specific nut, a meat that may not be expected in a dish's usual name), flag it explicitly even if the source text itself doesn't call it out — a menu written for local readers routinely omits information a first-time visitor would need, and staying silent because "the menu didn't say it" would miss the actual point of translating this for someone unfamiliar with the cuisine. Be clear this is a flag to ask about, not a guarantee, since ingredients can vary by kitchen.

REGIONAL VARIANTS
If a dish name is used differently across regions of Japanese's associated country or culture (the same name referring to a noticeably different dish elsewhere), note that ambiguity rather than picking one regional meaning silently — say which interpretation you went with and why, based on context in the photo if there is any.

SPICE LEVEL AND PREPARATION NOTES
If the photo or the item name implies a spice level, a raw or undercooked preparation, or an unusual texture that a first-time visitor might not expect from the translated name alone, mention it briefly — a literal name like "cold noodles" gives no signal about how spicy a dish actually is in practice, and that gap matters more to a diner than most other translation nuances.

OUTPUT FORMAT
One entry per line/item from the photo: literal translation, localized version if different (with the one-line reason), any allergen/dietary flag, and any unit/currency conversion. End with a short list of anything marked [unclear] and roughly where on the photo it appears, so the reader knows what to double-check in person if it matters.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

Reading the photo directly rather than routing through a separate OCR-then-translate step lets Gemini use surrounding visual context — menu section headers, price formatting, layout groupings — to disambiguate text that a plain OCR pipeline would misread in isolation, since OCR has no way to use the fact that an item sits under a 'Noodles' section header to disambiguate an otherwise ambiguous character. The request for a localized version alongside the literal one directly targets the most common failure of flat translation: an idiom, a dish name, or a unit gets translated word-for-word into something technically accurate but meaningless or actively misleading to the reader, and asking the model to explain why it changed something keeps that judgment call visible instead of hiding it inside a single unexplained 'translation.' The [unclear] flag matters specifically for real photos, which are often taken at an angle, partially glare-affected, or slightly out of focus — a model translating confidently from a misread character produces a wrong dish description or a wrong price with no signal to the reader that anything was uncertain, which is a materially worse outcome for a menu than an honest gap someone can ask a server about. Flagging likely allergens even when the source menu text doesn't mention them addresses a real gap in what a literal translation can provide: a menu written for local diners assumes shared cultural knowledge about what a dish typically contains, which is exactly the knowledge a first-time visitor from a different food culture doesn't have, so a translation that stays strictly literal reproduces the same invisible assumption for a reader who has no way to fill that gap themselves. Naming regional-variant ambiguity rather than silently picking one meaning matters because the same dish name can refer to genuinely different food depending on the region, and a traveler ordering based on a confidently wrong regional assumption gets a meal that doesn't match what they thought they were choosing, with no visible sign in the translation that a judgment call was even made.

What you get back

Line 3: 焼き餃子 (yakigyoza) Literal: "Fried gyoza" Localized: "Pan-fried pork dumplings" — kept "gyoza" since it's understood in English now, but added "pan-fried" since "fried" alone suggests deep-fried to most US readers, which this isn't. Line 7: [unclear] — price partially obscured by a sticker, showing only "¥8_0".

Verified against

Gemini Gemini 3 Pro · 2026-08-01

Changelog

  • 2026-08-01 Initial publish, verified against Gemini 3 Pro on a photographed Japanese restaurant menu.

Need this built into your business?

If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.

EXPLORE WHAT SCULT BUILDS
Turn a stack of scattered documents into one sourced decision memoA long-context synthesis prompt that loads every related document into the same context window as one connected evidence base and returns a single decision memo with inline citations and flagged disagreements, instead of a chain of disconnected per-document summaries that lose the connections between them.Gemini (Gemini 3 Pro)Gemini app2026-07-20Diff a redlined contract against the original and flag every substantive changeA long-context prompt that loads both the original and the redlined version of a contract into the same window and returns a change-by-change risk analysis, instead of a generic first read that misses a clause quietly weakened somewhere the visible tracked-changes markup doesn't draw the eye.Gemini (Gemini 3 Pro)Gemini app2026-07-21Compare competing sources side by side without smoothing over where they disagreeA long-context prompt that loads several full reports, reviews, or papers at once and produces a structured comparison table instead of a blended, opinion-free summary that quietly hides where the sources actually disagree.Gemini (Gemini 3 Pro)Gemini app2026-07-22Turn an entire small-to-mid codebase into an onboarding doc a new engineer can trustA long-context prompt that reads a whole repository — every file pasted or uploaded, not a handful of representative snippets — and produces an onboarding document that names actual file paths and real architectural seams, instead of generic advice that could describe any Next.js or Python project.Gemini (Gemini 3 Pro)Gemini app2026-07-23
All Gemini prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY