kapi exec translate

$ kapi translate [files...]

Translate content with an LLM or machine-translation provider (select an engine, then a provider)

Commandexec translate

Try it (demo)

Demo mode — illustrative output from a built-in stub, not a real model. Install the CLI to run with your own API key.

$ kapi translate messages.json --target-lang fr

Flags

Flag	Type	Default	Description
--api-key	string		API key for the AI provider
--batch-concurrency	int	1	Number of concurrent batch calls (0 or 1 = sequential)
--batching	string	auto	How many blocks share one LLM call (auto, single)
--concurrency, -j	int	0	max parallel files (0 = auto)
--context	string	key	What the model is told about a block besides the block itself (none, key, neighbours)
--context-window	int	2	Blocks either side to send as reference (with context: neighbours)
--credential	string		saved credential name to use (see 'kapi credentials list')
--encoding, -e	string	UTF-8	input file encoding
--engine	string	llm	Translation engine: an AI model or a machine-translation provider (AI (LLM), Machine translation)
--fail-on-unknown	bool	false	exit with error if any file cannot be processed (default: skip with warning)
--format, -f	string		override input format detection
--instruction	string		Extra guidance for the model while translating (e.g. 'informal register; keep product names in English')
--json	bool	false	output results as JSON
--map, -m	stringArray		map glob pattern to format (e.g. '*.docx=okf_openxml:test')
--model	string		AI model name
--no-warn	bool	false	suppress warnings for skipped files
--output, -o	string		output path template (variables: {dir}, {name}, {ext}, {lang})
--output-dir	string		write outputs under DIR/{lang}/ (default: beside the input, mirroring its locale layout)
--pack	bool	false	when transforming a .kpz, also eject the result to the .kpz (auto-pack)
--parallel-blocks	int	0	fan out block processing across N goroutines (0 = off)
--progress, -p	bool	false	show progress bar
--provider	string	anthropic	AI provider (Anthropic, OpenAI, Gemini, Azure OpenAI, Claude Code, Ollama, Demo (illustrative))
--skip-matched	bool	false	Skip blocks that already have a target translation
--source-lang	string	en	source language (e.g. en, en-US)
--strict	bool	false	alias for --fail-on-unknown
--target-lang	string		target language (e.g. fr, de-DE)
--trace	string		write flow trace JSON to file (for flow visualization)

More examples

$ kapi translate app.xliff --target-lang de --provider openai

$ kapi translate app.xliff --target-lang de -o app.de.xliff

← Back to the Command Reference