---
title: "Transcribe audio (speech-to-text + diarization)"
method: POST
path: "/v1/transcribe"
tags: ["audio"]
---

# Transcribe audio (speech-to-text + diarization)

`POST /v1/transcribe`

## Request

- Base URL: `https://varosity.ai/api`
- URL: `https://varosity.ai/api/v1/transcribe`
- Auth: HTTP bearer

ElevenLabs Scribe. Returns the transcript, word timestamps, and contiguous speaker segments. The caller decides which segments to use. Scope: transcribe:audio.

## Request body

- object
  - `audioUrl` string, uri, required
  - `diarize` boolean
  - `languageCode` string

## Response `201`

Success

- object
  - `ok` boolean, required
  - `languageCode` string, nullable, required
  - `durationSec` number, required
  - `text` string, required
  - `speakers` string[], required
  - `segments` object[], required
    - `speakerId` string, nullable, required
    - `start` number, required
    - `end` number, required
    - `text` string, required
  - `words` object[], required
    - `text` string, required
    - `start` number, required
    - `end` number, required
    - `speakerId` string, nullable, required

## Other responses

- `401`: Unauthorized
- `422`: Validation error

---

[API](https://skmtc.dev/varosity/apis/varosity-ai-api.md) · [All operations](https://skmtc.dev/varosity/apis/varosity-ai-api/llms.txt) · [OpenAPI document](https://skmtc.dev/varosity/apis/varosity-ai-api/revisions/049ca5f80d22?raw)