---
title: "Write down one of UXDuck's own recordings again"
method: POST
path: "/v1/speech/transcribe"
tags: ["Speech"]
---

# Write down one of UXDuck's own recordings again

`POST /v1/speech/transcribe`

## Request

- Base URL: `https://api.uxduck.com`
- URL: `https://api.uxduck.com/v1/speech/transcribe`
- Auth: none declared

The body is a WAV recording as UXDuck's dictation makes it (16 kHz mono 16-bit PCM), up to 5 minutes. Answers its words and its length in seconds.

## Response `200`

Its words

- object
  - `text` string, required
  - `seconds` number, required

## Other responses

- `400`: Not one of UXDuck's own recordings
- `413`: Longer than 5 minutes
- `429`: Too many at once, or the shared allowance is used up
- `502`: Cartesia could not write it down
- `503`: Transcription is switched off or not set up

---

[API](https://skmtc.dev/uxduck/apis/uxduck-api.md) - [All operations](https://skmtc.dev/uxduck/apis/uxduck-api/llms.txt) - [OpenAPI document](https://skmtc.dev/uxduck/apis/uxduck-api/revisions/d594d81b2806?raw)