---
title: "Transcribe Spoken Chat Audio"
method: POST
path: "/api/v1/stt/transcribe"
tags: ["speak-to-chat"]
---

# Transcribe Spoken Chat Audio

`POST /api/v1/stt/transcribe`

Transcribe a short browser-recorded clip with the voice-stack STT.

## Response `200`

Successful Response

- SpeakToChatTranscriptRead — Transcript of a short browser-recorded clip. ``text`` is empty when Deepgram heard no speech. The composer stays usable; the client shows a clear 'couldn't hear anything' error rather than sending an empty message.
  - `text` string, required

## Other responses

- `400` — Empty, oversized, or unsupported audio
- `422` — Validation Error
- `502` — Speech-to-text provider failed
- `503` — Speech-to-text is not configured

## Changes

> 18 revisions in range; 1 not diffed.

- **2026-09-03** `d65b8fefae34` — 1 breaking, 3 info
  - the `file` request property contentMediaType changed from `` to `application/octet-stream`
  - the `file` request property format was generalized from `binary` to no format
  - added the optional property `detail/items/ctx` to the response with the `422` status
  - added the optional property `detail/items/input` to the response with the `422` status

[Change history](https://skmtc.dev/getanana/apis/cleon-api/changes/api/v1/stt/transcribe/post.md)

---

[API](https://skmtc.dev/getanana/apis/cleon-api.md) · [All operations](https://skmtc.dev/getanana/apis/cleon-api/llms.txt) · [OpenAPI document](https://skmtc.dev/getanana/apis/cleon-api/revisions/202b7d85683e?raw)