v44

latestOpenAPI 3.1.0Proprietaryraw.githubusercontent.com2026-05-192301780.0 KB

Voice

Extract boost list from documents

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.

post/voice/boost-list/extract

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[]