Loco localise.biz

Can AI replace Loco?

The core of Loco is a keyed string store with a locale matrix on top, and that part is genuinely a one-sitting build: SQLite, a table view, an import and an export. What eats the weekend is the format layer, because gettext PO with plural headers, Apple .strings and .stringsdict, Android plurals XML, ICU messages and flat JSON all disagree about pluralization and escaping in ways that only show up in production. Machine translation fill-in is a single API call if you already have a DeepL or provider key. If you are the only translator, a local build is fine and arguably faster to work with. If you send links to freelance translators and rely on the hosted API in CI, you are rebuilding a service, not a tool.

Verdict: Half-bot · AI gets you partway; the hard part stays hardBuild time: a weekend
Half-bot

01What it costs

$5.95/moPro, monthly per account
$71.4per year at that price

Checked Aug 18, 2026 · source: localise.biz.

02Could AI build it for you?

The core job: A local web app that stores translation keys per project, shows a locale-by-key grid you can edit, imports and exports JSON, PO and Android XML, and optionally machine-translates empty cells.

What a working version needs:

  • Node 20 and a local folder to run in
  • Optional machine translation API key (DeepL or similar) in .env
  • Your existing locale files to import as a starting point

Fine to self-host if you are your own translator; the moment a human you do not employ needs edit access, the hosted version starts earning its keep.

03What you'd give up

  • Format breadth: Loco reads and writes a long tail of formats, including the awkward Apple and Qt ones, with plural rules per locale already correct
  • A shareable editor for non-technical translators, with roles, comments and progress tracking
  • A stable public API and CLI that CI pipelines can pull from at build time
  • Translation history, who changed what, and the ability to roll a string back
  • Glossary and translation memory suggestions that improve as the project grows

Because localization is a pile of edge cases someone else already ate. Plural categories vary by language, every platform escapes strings differently, and one bad export ships mangled text to users in a language nobody on the team reads. Paying also buys a link you can send to a contractor and an API your build can hit, which a folder on your laptop cannot do. Solo developers with two or three locales tend to outgrow the need for that rather than into it.

05The build prompt

Paste this into an AI coding tool (such as Claude, ChatGPT, Lovable or Replit) to build your own version.

prompt.txt
Build a local translation management app called Strings. No accounts, no cloud, no telemetry.

Stack, non negotiable:
- Node 20 with Express and TypeScript
- SQLite via better-sqlite3, file at ./data/strings.db
- Server rendered EJS templates plus a little vanilla JS, no React, no bundler
- Runs with `npm run dev` on localhost:4321

Data model:
- projects: id, name, source_locale
- locales: id, project_id, code (BCP 47)
- keys: id, project_id, name (dot notation allowed), context note, created_at
- translations: key_id, locale_id, plural_category (one of other, one, two, few, many, zero), value, updated_at
- history: translation_id, old_value, new_value, changed_at

UI:
- Project list, then a grid page per project: rows are keys, columns are locales, cells are inline editable textareas that save on blur via fetch
- Filters: untranslated only, search by key or value substring
- Per key detail drawer showing context note, plural forms, and history
- Progress bar per locale showing percent of keys with a non empty value

Import and export, implement exactly these three formats and be strict:
- Flat and nested JSON
- gettext PO, including Plural-Forms header parsing and msgid_plural
- Android strings.xml, including plurals blocks with quantity attributes
Use the CLDR plural categories for each locale code; hardcode a small lookup table for the twenty most common locales and fall back to other plus one.

Also ship a CLI: `npm run export -- --project=X --locale=fr --format=po --out=./out` so a build script can use it.

Optional machine translation: if DEEPL_API_KEY is set in .env, add a "fill empty cells" button per locale that batches untranslated source strings through DeepL and marks results as machine translated with a flag shown in the grid. If the key is missing, hide the button rather than erroring.

Out of scope: multi user auth, sharing links, webhooks, screenshots, glossary, TMX.

Include a README with setup, a `.env.example`, and seed data for one project with English, French and Polish so plural handling is exercised on day one.
Sponsor slot · openFeatured alternative to Loco. A labeled card for one relevant tool.
Book this spot →

App prices, verdicts, alternatives and build prompts are adapted from Can I Vibecode It? (MIT License, © 2026 Rob Hallam). Each price shows the date it was checked and its source. Prices change; confirm on the vendor's site before you decide.