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

cURL

cURL

curl -X POST "https://api.case.dev/voice/boost-list/extract" \ -H "Authorization: Bearer $CASEDEV_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "vault_id": "<string>", "object_ids": [ "<string>" ], "text": "<string>" }'

200

{
  "items": [
    {
      "word": "<string>",
      "category": "<string>"
    }
  ],
  "source_ids": [
    "<string>"
  ]
}

Authorizations

Authorization · string · header · required

API key starting with sk_case_

Body

application/json

Source documents or text for entity extraction

vault_id · string

Vault ID containing the source documents (use with object_ids)

object_ids · string[]

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

text · string

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

categories · enum<string>[]

Optional filter for entity categories to extract

Available options: person, organization, legal_term, medical, citation, email

Response

200

application/json

Boost list extracted successfully

items · object[]

Show child attributes

source · enum<string>

Available options: document, text

source_ids · string[]