Skip to content
LocalASO

ASO glossary

Machine translation (App Store metadata)

Machine translation is the automatic conversion of text from one language into another by software. For an App Store listing it is a fast way to produce a first draft of each localization, but not a finished one.

Updated

Where it helps

  • The app description and What's New, where meaning matters more than exact wording.
  • A first pass at screenshots captions.
  • Reaching many languages quickly, then asking a native reader to review the most important ones.

Where it fails for metadata

  1. Length. The name and subtitle are 30 characters each. A German or Finnish translation is often longer than the English and gets cut.
  2. Bytes. The keyword field counts bytes, so a translation that fits in characters may not fit in bytes. See byte limit.
  3. Search terms. A correct translation may not be what people type. This is why keyword localization and transcreation exist.
  4. Minimum length. Each keyword must be longer than two characters, which short translated words may not meet.

Review checklist

  1. Count the name, subtitle and keywords with a checker.
  2. Check each key term against local search results.
  3. Remove translated competitor or trademark names.
  4. Ask a native speaker to read the name, subtitle and first lines of the description.

Example

A hypothetical English subtitle "Daily routines that stick" (25 characters) is machine-translated into German as a longer phrase over 30 characters. The team shortens it to a punchier phrase of 28, which is rewriting, not translating.

In LocalASO

LocalASO uses the AI you bring (Claude Code, an Anthropic API key, Ollama, Codex or Gemini CLI) to draft localized text. You review it and keep the result inside Apple's limits.

Next step

Follow the localization guide and check lengths with the character counter.

Sources

Do this for every country, in minutes

LocalASO checks your rank, volume and difficulty for every keyword in 50+ App Store countries, in each local language. It runs on your Mac. $29 once, no subscription.