Speakatoo - API Documentation

Text To Speech API Documentation

Getting Started

Speakatoo is a leading, trending & the most popular AI based Text to Speech transformation web based Application. This is the documentation for the Text To Speech API. You can integrate text to speech API with any custom apps. Using this API you convert your text into speech. The response is returned in JSON format.

HTTP Methods

HTTP defines a set of request methods that we use during Text to speech. Please check below for your reference:

• GET - This method requests a representation of the specified resource. It is used for only retrieving data
• POST - This method is used to transfer data securely using HTTP headers.
• PUT - This method replaces a representation of the target resource with the request. Used when you want to send an update request.
• DELETE - The DELETE request method deletes the specified resource.

HTTPS Status Codes

HTTP response status codes indicate whether a specific HTTP request has been successfully completed.

• Successful response (200)
• Client error responses (400-450)
• File synthesize response (600-620)
• Server error responses (500)

Some status codes are:

Setup

• Goto to your dashboard, if you do not have an account on Speakatoo please sign up.
• Goto My API option.
• You will get your unique API key (you can reset your API key).

Sign In

{
    "username":"YOUR USERNAME",
    "password":"YOUR PASSWORD"
}

{
    "status": true,
    "message": {
        "ids": "Created unique user id",
        "status": "1",
        "username ": "YOUR USERNAME",
        "balance": "{\"usd\":0}",
        "emailAddress": "youremail@gmail.com",
        "phone": "",
        "firstName": "name",
        "lastName": "lastname",
        "timezone": "Asia/Singapore",
        "dateFormat": "Y-m-d",
        "timeFormat": "H:i:s",
        "language": "English",
        "currency": "USD",
        "country": "",
        "addressLine1": "",
        "addressLine2": "",
        "city": "",
        "state": "",
        "zipCode": "",
        "createdTime": "2020-12-01 08:00:00",
        "updateTime": "2021-01-29 09:42:35"
    }
}

Sign Up

{
    "emailAddress": "Your email id",
    "firstName": "Your Name",
    "lastName": "Your Lastname",
    "password": "Your Password"
}

{
    "status": true,
    "message": "Signup complete! You may sign in..."
}

Forget

{
    "emailAddress": "Your registered email id"
}

{
    "status": true,
    "message": "A password reset link has been sent. Please check the email and follow..."
}

Synthesize File

Feature: First, it verifies the user, requests for synthesizing, and gives a response with synthesized file details with the URL.

Note: You need to pass API Key in the HTTP Authorization request header as 'X-API-KEY: YOUR-API-KEY'. Your Content-Type header should be 'Content-Type: application/json'.

Pass voice id with appropriate language text. For Ex. If you choose the Hindi language, you must pass the text in Hindi.

Request:

{
  "username":"YOUR USERNAME",
  "password":"YOUR PASSWORD",
  "tts_title":"YOUR FILENAME",
  "ssml_mode":"0",
  "tts_engine":"neural",
  "tts_format":"mp3",
  "tts_text":"Text for synthesize",
  "tts_resource_ids":"voice id",
  "synthesize_type":"save"
}

Response :

{
    "result": true,
    "message": "File synthesis successfully",
    "tts_uri": "https://www.speakatoo.com/tts_file/user/filename.mp3",
    "task_identifier": "Unique id",
    "title": "Your filename",
    "voice_name": "Voice name",
    "engine": "neural",
    "text": "Text of synthesized",
    "characters_count": Characters count,
    "created_time": "2022-10-15 11:56:54"
}

Note: At the time of synthesis, ssml mode should be 0.

Attributes	Request	Response
username	Your Username	Your Username
password	Your Password	Your Password
tts_title	Your Filename	Your Filename will be shown in the title field
ssml_mode	supports only ssml mode 0	For other values, it will throw an error.
tts_engine	supports only engine neural	neural
tts_format	supports only file format mp3
tts_text	Should be passed text according to the chosen language
tts_resource_ids	Mention proper resource id as per the given voice list
synthesize_type	supports only synthesize type 'save'
tts_uri		Gives the URL of the synthesized file
task_identifier		Gives unique code of the synthesized file
voice_name		Voice name as per the resource id you used
characters_count		Character count used in the text
created_time		File created at what date and time.

Voice Id list with different languages

Text to Speech API Demo Project