Extracts a categorized word boost list from vault documents or raw text using LLM entity extraction. The resulting list can be passed as word_boost to the transcription endpoint for improved accuracy.
API key starting with sk_case_
Source documents or text for entity extraction
Vault ID containing the source documents (use with object_ids)
Object IDs of documents to extract entities from (PDFs, text files)
Raw text input for entity extraction (alternative to vault documents)
Optional filter for entity categories to extract
person, organization, legal_term, medical, citation, email