---
title: Convert Text to Speech API
slug: text-to-speech
url: https://apyverse.com/apyhub/service/text-to-speech
provider: ApyHub
categories: [Audio Processing, File Conversion, Smart Generation]
tags: [text-to-speech, speech-synthesis, mp3-generation, audio-conversion, document-to-audio]
auth: api_key
---

# Convert Text to Speech API

Convert text or document content into MP3 downloads or signed links using male or female voices. Useful for accessibility, narration, and content playback.

## Endpoints

| Method | Path | Description | Atoms |
| --- | --- | --- | --- |
| POST | `tts/url` | What it does This endpoint takes a document URL and a voice gender, then returns a JSON object cont… | 750 |
| POST | `tts/text/file` | What it does Converts the supplied JSON text into an MP3 file for download. You send the text to sy… | 750 |
| POST | `tts/text/url` | What it does Converts the submitted JSON text into speech and returns a signed MP3 link. The reques… | 750 |
| POST | `tts/file` | What it does This endpoint accepts an uploaded document file and a gender choice, then returns the… | 750 |
| POST | `tts/file/url` | What it does Uploads a document file and a selected voice gender, then returns a signed MP3 link as… | 750 |
| POST | `tts/url/file` | What it does Downloads a document from the provided URL, extracts its text, and returns the generat… | 750 |

## About

## What it does
Text to Speech converts plain text or document content into MP3 audio. Send text, a document URL, or an uploaded file together with a gender value, and get back either a binary MP3 download or a signed MP3 link depending on the endpoint you use.

Use the text endpoints when you already have content in your application. The request body accepts `text` or `url` plus `gender` set to `male` or `female`. For longer documents, you can point the API at a document URL or upload the file directly, then retrieve audio from the generated response. The text input supports up to 75,000 characters.

Text to Speech is useful for turning articles, PDFs, reports, and user-generated content into listenable audio for accessibility features, internal review, or content repurposing. If you need a direct file response, use the `/text/file`, `/file/file`, or `/url/file` endpoints. If you need a shareable result for downstream processing, use the matching `/text/link`, `/file/link`, or `/url/link` endpoints.

## Usage

Authenticate with an ApyHub API key in the `apy-token` header.
Full docs and a live playground: https://apyverse.com/apyhub/service/text-to-speech