---
title: "Text-to-Speech"
method: POST
path: "/v1/audio/speech"
---

# Text-to-Speech

`POST /v1/audio/speech`

## Request

- Base URL: `https://tts.freyavoice.ai`
- URL: `https://tts.freyavoice.ai/v1/audio/speech`
- Auth: HTTP bearer

Converts text into natural-sounding speech using Freya's TTS model. Returns a binary audio file. Supports the following emotion tags: [pause], [eee], [throat clearing], [mm-hmm], [laughter], [deep breath], [hmm], [cough], [breath]

## Request body

- object
  - `input` string, required: The text to synthesize audio for.
  - `voice` 'leyla' | 'zeynep' | 'alev' | 'ali' | 'alper' | 'mustafa', required: The voice ID to use.
  - `response_format` 'mp3' | 'opus' | 'aac' | 'flac' | 'wav' | 'pcm': Response format for the API request.
  - `model` 'tts-1' | 'tts-1-hd': Quality preset. `tts-1` is faster; `tts-1-hd` is higher quality.

## Response `200`

Audio file generated successfully.

## Other responses

- `400`: Bad request — missing or invalid parameters.

---

[API](https://skmtc.dev/freyavoice/apis/freya-model-apis.md) - [All operations](https://skmtc.dev/freyavoice/apis/freya-model-apis/llms.txt) - [OpenAPI document](https://skmtc.dev/freyavoice/apis/freya-model-apis/revisions/9618fd80fb1f?raw)