Media Refine tool

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

IDmedia-refine

SourceBuilt-in

Categorytext-processing

Requirescredentials

Tagsai-powered, vision

Parameters

Parameter	Type	Default	Description
apiKey	string		API key for the AI provider
model	string		Multimodal model name
provider	string	anthropic	Multimodal AI provider
threshold	number	0.85	Re-read extracted lines whose confidence is below this

Configure it live

Configuration

Loading form…

Configuration output

vs defaultsno changes

# (default configuration)

← Back to the Tool Reference