localekit translate
Translate missing localization keys
Solo planQuick Start
bash
localekit translate --engine deepl --api-key $DEEPL_API_KEYbash
localekit translate --engine openai --api-key $OPENAI_API_KEYbash
localekit translate --engine mlx --mlx-model mlx-community/Qwen3-4B-4bitSee Translation Engines for a detailed comparison and available MLX models.
Usage
bash
localekit translate [path] [options]Arguments
| Argument | Description | Default |
|---|---|---|
path | Path to localization file or directory (defaults to current directory) | . |
Options
| Option | Description | Default |
|---|---|---|
--config <config> | Path to configuration file (.localekitrc.yml) | — |
-l, --languages <languages> | Target languages to translate (comma-separated, e.g., 'de-DE,fr-FR') | — |
--engine <engine> | Translation engine: openai, deepl | deepl |
--api-key <api-key> | API key (or use LOCALEKIT_API_KEY, DEEPL_API_KEY, or OPENAI_API_KEY env var) | — |
--source-language <source-language> | Base/source language (e.g., en-US) | — |
--workspace-dir <workspace-dir> | Path to workspace XLIFF directory (uses workspace files instead of platform scan) | — |
--mlx-model <mlx-model> | MLX model ID from Hugging Face (e.g., mlx-community/Qwen3-4B-4bit) | — |
Flags
| Flag | Description |
|---|---|
--dry-run | Preview changes without writing files |
-v, --verbose | Show detailed output |
MLX (on-device)
6 models available — from Qwen3 4B (8 GB RAM) to Qwen3 32B (32 GB RAM). See all models and comparison.
TIP
After translating, a .localekit-snapshot.json file is saved. This is used by localekit diff to detect changes.