kapi exec media-refine

$ kapi media-refine [files...]

Re-read low-confidence OCR/ASR lines with a configurable multimodal LLM

Commandexec media-refine

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 exec media-refine

Flags

Flag	Type	Default	Description
--api-key	string		API key for the AI provider
--concurrency, -j	int	0	max parallel files (0 = auto)
--credential	string		saved credential name to use (see 'kapi credentials list')
--encoding, -e	string		charset the input is read in; a byte-order mark in the file wins (default: the project's defaults.encoding, then UTF-8)
--engine	string		format engine for detected files: native or a plugin name (default: native, then plugins)
--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
--json	bool	false	output results as JSON
--map, -m	stringArray		map glob pattern to format (e.g. '*.docx=okf_openxml:test')
--model	string		Multimodal model name
--no-warn	bool	false	suppress warnings for skipped files
--output, -o	string		output path template (variables: {dir}, {name}, {ext})
--output-dir	string		write outputs under DIR (default: rewrite each input in place)
--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)
--print-ops	bool	false	write no file and print the change set the run would apply, for kapi apply
--progress	bool	false	show progress bar
--project, -p	string		path to a kapi.yaml project recipe or its directory (auto-discovered from cwd if omitted)
--provider	string	anthropic	Multimodal AI provider (Anthropic, OpenAI, Gemini, Azure OpenAI, Claude Code, Ollama, Demo (illustrative))
--source-lang	string		source language (e.g. en, en-US; defaults to the project's source_language, else en)
--strict	bool	false	alias for --fail-on-unknown
--threshold	float64	0.85	Re-read extracted lines whose confidence is below this
--trace	string		write flow trace JSON to file (for flow visualization)

← Back to the Command Reference