🏠
Contact About Privacy Policy API

AudiofyText API - Text to Speech Service

Google Text To Speech

Introduction

The AudiofyText API offers all the functions that are available on our website but with more focus on application programming. It is free to use this API in the current and future development of applications as well. However, we would like to inform you that maintaining the API does not come for free on our end, so we would appreciate if you could use it with due respect. If you have any questions or encounter any problems, please do not hesitate to contact us via email or Twitter.

API Details

The AudiofyText API is available at api.audiofytext.com and supports two key operations:

Discover AudiofyText on GitHub

If you're interested in the source code for AudiofyText and want to explore how it works, check out the AudiofyText GitHub Repository. This repository contains the full code for the Text-to-Speech and Speech-to-Text features, allowing you to integrate them into your own projects or contribute to the development.

Feel free to explore, fork, or contribute to the project. Happy coding!

Voice Options

The AudiofyText API has a limited set of voices which have been selected from well know and reliable services including Google Translate. The list of voices might be expanded in the future as well as removed from the list in the future as well. To help prevent any potential issues, it is recommended that you always use the shortened voice/language codes instead of the full names when making a request to the API.

List of Supported Voices

Code Voice
af-ZAAfrikaans
sqAlbanian
ar-AEArabic
hyArmenian
bn-BDBengali (Bangladesh)
bn-INBengali (India)
bsBosnian
myBurmese (Myanmar)
ca-ESCatalan
cmn-Hant-TWChinese
hr-HRCroatian
cs-CZCzech
da-DKDanish
nl-NLDutch
en-AUEnglish (Australia)
en-GBEnglish (United Kingdom)
en-USEnglish (United States)
eoEsperanto
etEstonian
fil-PHFilipino
fi-FIFinnish
fr-FRFrench
fr-CAFrench (Canada)
de-DEGerman
el-GRGreek
guGujarati
hi-INHindi
hu-HUHungarian
is-ISIcelandic
id-IDIndonesian
it-ITItalian
ja-JPJapanese (Japan)
knKannada
kmKhmer
ko-KRKorean
laLatin
lvLatvian
mkMacedonian
mlMalayalam
mrMarathi
neNepali
nb-NONorwegian
pl-PLPolish
pt-BRPortuguese
ro-RORomanian
ru-RURussian
sr-RSSerbian
siSinhala
sk-SKSlovak
es-MXSpanish (Mexico)
es-ESSpanish (Spain)
swSwahili
sv-SESwedish
taTamil
teTelugu
th-THThai
tr-TRTurkish
uk-UAUkrainian
urUrdu
vi-VNVietnamese
cyWelsh

Operations Reference

Create Sound

Use the POST /sounds endpoint to create a new sound file. Currently, the engine parameter is not used, but it is included for potential future support for multiple engines. Both the voice and text are required parameters.

Request Example

Set the Content-Type header to application/json and structure your request body as follows:

		{
		  "engine": "Google",
		  "data": {
			"text": "Hello, world",
			"voice": "en-US"
		  }
		}
			

Response

On Success:

You will receive a status code of 200 with the following response body:

		{
		  "success": true,
		  "id": ""
		}
			

Example ID: 416eda90-552e-11e7-9a60-63d42f732a9c

On Failure:

If the request fails, you will receive a status code of 400 or 500 with the following response body:

		{
		  "success": false,
		  "message": "Request failed due to..."
		}
			

Retrieve Sound

Use the GET /sounds/:id endpoint to check the current status of a requested sound and retrieve the public URL for the MP3 file.

Response

On Success:

If the request is still being processed, the status will be Pending:

		{
		  "status": "Pending"
		}
			

Once the request has been fulfilled, you will receive a Done status and the public URL for the MP3 file:

		{
		  "status": "Done",
		  "location": "https://hostname/path/to/audio.mp3"
		}
			

If there was an issue fulfilling the request, you will receive an error status and a corresponding message:

		{
		  "status": "Error",
		  "message": "Failed to create sound due to..."
		}
			

Free Text To Speech
© 2024 AudiofyText. All Rights Reserved.