---
title: "Generate audio"
method: POST
path: "/v1/speech"
---

# Generate audio

`POST /v1/speech`

## Headers

- `X-Data-Retention` boolean

## Request body

- SpeechRequest
  - `language` string — This is optional; an ISO 639 language code to be used for the generation.
  - `text` string, required — The text for which you want to generate audio.
  - `voice` 'sade' | 'segun' | 'femi' | 'funmi' | 'amina' | 'aliyu' | 'hasan' | 'zainab' | 'john' | 'jude' | 'lina' | 'lucy' | 'henry' | 'kani' | 'remi' | 'kingsley' | 'ngozi' | 'amara' | 'obinna' | 'ebuka' | 'hana' | 'haile' | 'tena' | 'tesfaye' | 'ufoma' | 'tega' | 'justice' | 'boma', required
  - `speed` number, float — The speed of the voice, defaults to `1.0`
  - `format` 'mp3' | 'wav' | 'ogg_opus' | 'webm_opus' | 'mulaw' | 'alaw' | 'flac' | 'pcm_s16le'

## Response `200`

Successful Response

---

[API](https://skmtc.net/spi-tch/apis/spitch-api.md) · [All operations](https://skmtc.net/spi-tch/apis/spitch-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/spi-tch/spitch-api/versions/345ddd9a88d1/schema)