---
title: "Extract boost list from documents"
method: POST
path: "/voice/boost-list/extract"
tags: ["Voice"]
---

# Extract boost list from documents

`POST /voice/boost-list/extract`

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.

## Request body

- object
  - `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` string[] — Optional filter for entity categories to extract

## Response `200`

Boost list extracted successfully

- object
  - `items` object[]
    - `word` string
    - `category` string
    - `boost_param` 'low' | 'default' | 'high'
  - `source` 'document' | 'text'
  - `source_ids` string[]

## Other responses

- `400` — Bad request - missing required fields
- `401` — Unauthorized
- `403` — Forbidden - lacks voice service permissions
- `404` — Vault or objects not found

---

[API](https://skmtc.net/casemark/apis/case-dev-api.md) · [All operations](https://skmtc.net/casemark/apis/case-dev-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/casemark/case-dev-api/revisions/5b7e64e6d6f9/schema)