CAcasemark
Voice

Extract boost list from documents

Extracts a categorized word boost list from vault documents or raw text using LLM entity extraction. The resulting words can be passed as keyterms_prompt (or the legacy word_boost alias) to the transcription endpoint for improved accuracy.

post/voice/boost-list/extract

Request

  • Base URL
    https://api.case.dev
  • URL
    https://api.case.dev/voice/boost-list/extract
  • Auth
    HTTP bearer

Request body

vault_idstring

Vault ID containing the source documents (use with object_ids)

object_idsstring[]

Object IDs of documents to extract entities from (PDFs, text files)

textstring

Raw text input for entity extraction (alternative to vault documents)

categoriesstring[]

Optional filter for entity categories to extract

Response

Boost list extracted successfully

source'document' | 'text'
source_idsstring[]

Changes

No recorded changes to this operation across all 54 revisions of this API.