---
title: "Transcribe Audio"
method: POST
path: "/api/audio/transcribe"
tags: ["audio"]
---

# Transcribe Audio

`POST /api/audio/transcribe`

## Request

- Base URL: `https://app.thinqos.com` (the document declares no server; this is the origin it was published from)
- URL: `https://app.thinqos.com/api/audio/transcribe`
- Auth: none declared

Transcribe an audio file to text via ElevenLabs Scribe v2.

Same key cascade as /tts and /voices: caller's BYO ElevenLabs key via
TOS-199 → the stored platform ElevenLabs key. Returns 503 if neither is
configured.

Size cap (25 MB) is kept for parity with the previous OpenAI path -
ElevenLabs has a higher ceiling but the cap doubles as a sane
upload-size limit for the frontend's webm/opus recordings.

## Headers

- `x-impersonate-identity-id` string, nullable

## Response `200`

Successful Response

- object

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/thinqos/apis/thinqos-api.md) · [All operations](https://skmtc.dev/thinqos/apis/thinqos-api/llms.txt) · [OpenAPI document](https://skmtc.dev/thinqos/apis/thinqos-api/revisions/ce2c2ce318b1?raw)