---
title: "Create speech audio"
method: POST
path: "/v1/audio/speech"
tags: ["Text to speech processing"]
---

# Create speech audio

`POST /v1/audio/speech`

## Request

- Base URL: `/` (relative, and the document was published on a file host, not at the API’s origin)
- URL: `/v1/audio/speech`
- Auth: HTTP bearer
- TypeScript: <https://skmtc.dev/tenstorrent/apis/tt-media-server-api-c-drogon/docs/v1/audio/speech/post.ts> (a function with typed inputs; its response is checked against the schema)

Generates speech audio from text. Registered only when MODEL_SERVICE=tts. The initial C++ implementation streams audio/wav.

## Request body

- TtsSpeechRequest
  - `text` string, required: Text to synthesize into speech.
  - `description` string: Optional natural-language voice description.

## Response `200`

Streaming WAV audio

## Other responses

- `400`: Invalid request
- `401`: Missing or invalid authentication token
- `429`: TTS request queue is full
- `503`: TTS backend is not ready

## Changes

- **2026-08-05** `66618e53cba6`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/tenstorrent/apis/tt-media-server-api-c-drogon/changes/v1/audio/speech/post.md)

---

[API](https://skmtc.dev/tenstorrent/apis/tt-media-server-api-c-drogon.md) - [All operations](https://skmtc.dev/tenstorrent/apis/tt-media-server-api-c-drogon/llms.txt) - [OpenAPI document](https://skmtc.dev/tenstorrent/apis/tt-media-server-api-c-drogon/revisions/f1176db3fd15?raw)