Text To Speech API

Text To Speech API - CloudPronouncer (tts online or tts reader) is a cross browsers REST API supporting now 169 Standard and Premium Voices in 30 languages including variants (the list is growing in time) and it may be used by any device that can connect to Internet and send the POST requests to our API as instructed in this website: smartphones, tablets, laptops, PC Desktops, other smart devices. It uses cloud infrastructure and artificial intelligence to solve the requests.

Allthough this Text To Speech or text to voice utility is intended for software development and therefore developers, we have also here an online application that may be used to get audio files from the input text either plain text or text with SSML markup. The necessary steps are written below, basically for Text To Speech API you send an authorized POST request in JSON format to the API endpoint and you get as JSON response a base64 encoded string representing the audio file and a link to the saved audio file if you chose so. You have also the option to save the audio file encoded as Linear16 (uncompressed .wav file), .mp3 file or .ogg file. You own the commercial copyright of the resulted audio file(s) with no additional fee.

Text To Speech APP or API is useful for a large number of domains like: e-Learning, bots, smart devices, robots, messaging, call centers etc.

For using our API and/or APP you must create an account (free of charge, no card required), activate it from your received email, login and then start your TRIAL package with no fees as you can see at our pricing packages. After you have tested the text to speech readear API and/or APP and you are satisfied, you may buy a paid package. You will always see at your Admin Console page the real resources consumption in real time, your invoices, you may see/edit/delete your profile or export log consents as GDPR instructed, you may read our FAQs.

Text To Speech APP

This is a very simple to implement Text To Speech API and yet really powerfull based on cloud and artificial intelligence. It works on every device which can connect to internet and can send requests to the API.

Voice Name

Audio Encoding

Request Type

Device (*Beta)

1 Speed

0 Pitch

0 Volume

Save audio file locally

API Endpoint (method POST):

https://www.de-vis-software.ro/tts.aspx

Headers:

Authorization: Basic //Your username:password are base64 encoded string
Content-Type: application/json
Accept: application/json

JSON Request Body:

{
"inputtext":"This is a very simple to implement Text To Speech API and yet really powerfull based on cloud and artificial intelligence. It works on every device which can connect to internet and can send requests to the API.",
"ssml":"Text",
"voicename":"en-US-PREMIUM-C_FEMALE",
"voicetype":"HeadPhones",
"encoding":"Mp3",
"speed":1,
"pitch":0,
"volume":0,
"saveFileLocally":"Yes"
}

JSON Response From API (*the real response string is much longer than the displayed string):

{
"base64AudioString":"//NExAAAAANIAAAAAPd+IVAABET...VVVVVVVVVVVVVVVVVVVVVVVVV",
"audioFileURL":"https://ffpoazure.blob.core.windows.net/itrew-crsq.mp3"
}

JSON Response (Example) From API in case of ERROR:

{
"cd":1001,
"error":"The authorization header is either empty or isn't Basic."
}

Request Parameters Table

Parameter Name

Parameter Description

inputtext

This is the input typed plain text that will be converted to audio for the selected language and voice. For each request there is a limit of 700 characters of input text.

ssml

The value for this parameter could be Text or SSML. If SSML, the input text will be marked with SSML markup tags, if Text then the input text is just plain text.

voicename

There are several voices for different languages, for example en-US-PREMIUM-C_FEMALE is a premium female voice named C for English American language or another example would be en-US-Standard-D_MALE which is a Standard male voice named D for English American language. A complete list of voices is given below, just click here.

voicetype

This parameter defines on which type of device will be the voice heard. For example if the value of this parameter is HeadPhones then the audio file will be best heared on head phones. A complete list of values is written here: Car Audio System, HeadPhones, Home Audio System, Interactive Voice Response (IVR), Small Home Speaker, Smart Home Speaker, SmartPhone, SmartWatch. This parameter is still in Beta, that means is possible to not hear differences between devices.

encoding

This parameter defines how the output audio file will be encoded. The possible values are: Linear16 which is an uncompressed looseless format with .wav extension for the otput audio file, Mp3 which is a well known compressed lossy format with .mp3 extension for the output audio file and OggOpus which is also a compressed lossy format with .ogg extension for the output audio file.

speed

This is the speed of pronouncing words in the output audio file. Values must be within range of 0.3 to 4, normal value is 1.

pitch

This is the pitch of pronouncing words, i.e. as higher as it is so it will be the frequency. Values must be within range of -20 to 20, normal value is 0.

volume

This is the volume of the output audio file. Values must be within range of -10 to 10, normal value is 0.

saveFilelocally

This parameter can take Yes or NO value. If Yes then the output audio file will be saved locally, otherwise only JSON response string will be downloaded.

Response Parameter Table

Parameter Name

Parameter Description

base64AudioString

This is the base64 encoded string which may be put as source of an html5 audio control for example or decoded in an audio file. You may see an example above.

audioFileURL

This is the link to the cloud saved audio file which may be downloaded locally.

Response Error Codes Table

Parameter Name

Parameter Description

This is the error code which may be:

1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
2001

description

This is the description of the error code which may be:

1001 - The authorization header is either empty or isn't Basic.
1002 - Daily requests number exceeded in TRIAL mode!
1003 - Trial expired!
1004 - Characters number exceeded!
1005 - Package expired!
1006 - No invoice!
1007 - Reader is NULL for TRIAL!
1008 - Cannot Read if TRIAL exists!
1009 - Error connecting to database looking for TRIAL! (and a detailed description message of the encountered error)
1010 - Reader is NULL for Invoice!
1011 - Cannot Read if Invoice exists!
1012 - Error connecting to database! (and a detailed description message of the encountered error)
1013 - Input request string too long! Maximum 700 characters per request are allowed
1014 - Invalid request data! (and a detailed description message of the encountered error)
1015 - Cannot initialize BLOB permissions for saving audio file! (and a detailed description message of the encountered error)
1016 - Cannot create and save the audio file! (and a detailed description message of the encountered error)
2001 - Invalid request data after passing to the API (and a detailed description message of the encountered error)

Supported languages and voices

Language Code
ar-XA

Voice Name
ar-XA-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
ar-XA

Voice Name
ar-XA-PREMIUM-B_MALE

Gender
MALE

Language Code
ar-XA

Voice Name
ar-XA-PREMIUM-C_MALE

Gender
MALE

Language Code
ar-XA

Voice Name
ar-XA-Standard-A_FEMALE

Gender
FEMALE

Language Code
ar-XA

Voice Name
ar-XA-Standard-B_MALE

Gender
MALE

Language Code
ar-XA

Voice Name
ar-XA-Standard-C_MALE

Gender
MALE

Language Code
cs-CZ

Voice Name
cs-CZ-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
cs-CZ

Voice Name
cs-CZ-Standard-A_FEMALE

Gender
FEMALE

Language Code
da-DK

Voice Name
da-DK-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
da-DK

Voice Name
da-DK-Standard-A_FEMALE

Gender
FEMALE

Language Code
de-DE

Voice Name
de-DE-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
de-DE

Voice Name
de-DE-PREMIUM-B_MALE

Gender
MALE

Language Code
de-DE

Voice Name
de-DE-PREMIUM-C_FEMALE

Gender
FEMALE

Language Code
de-DE

Voice Name
de-DE-PREMIUM-D_MALE

Gender
MALE

Language Code
de-DE

Voice Name
de-DE-Standard-A_FEMALE

Gender
FEMALE

Language Code
de-DE

Voice Name
de-DE-Standard-B_MALE

Gender
MALE

Language Code
el-GR

Voice Name
el-GR-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
el-GR

Voice Name
el-GR-Standard-A_FEMALE

Gender
FEMALE

Language Code
en-AU

Voice Name
en-AU-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
en-AU

Voice Name
en-AU-PREMIUM-B_MALE

Gender
MALE

Language Code
en-AU

Voice Name
en-AU-PREMIUM-C_FEMALE

Gender
FEMALE

Language Code
en-AU

Voice Name
en-AU-PREMIUM-D_MALE

Gender
MALE

Language Code
en-AU

Voice Name
en-AU-Standard-A_FEMALE

Gender
FEMALE

Language Code
en-AU

Voice Name
en-AU-Standard-B_MALE

Gender
MALE

Language Code
en-AU

Voice Name
en-AU-Standard-C_FEMALE

Gender
FEMALE

Language Code
en-AU

Voice Name
en-AU-Standard-D_MALE

Gender
MALE

Language Code
en-GB

Voice Name
en-GB-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
en-GB

Voice Name
en-GB-PREMIUM-B_MALE

Gender
MALE

Language Code
en-GB

Voice Name
en-GB-PREMIUM-C_FEMALE

Gender
FEMALE

Language Code
en-GB

Voice Name
en-GB-PREMIUM-D_MALE

Gender
MALE

Language Code
en-GB

Voice Name
en-GB-Standard-A_FEMALE

Gender
FEMALE

Language Code
en-GB

Voice Name
en-GB-Standard-B_MALE

Gender
MALE

Language Code
en-GB

Voice Name
en-GB-Standard-C_FEMALE

Gender
FEMALE

Language Code
en-GB

Voice Name
en-GB-Standard-D_MALE

Gender
MALE

Language Code
en-IN

Voice Name
en-IN-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
en-IN

Voice Name
en-IN-PREMIUM-B_MALE

Gender
MALE

Language Code
en-IN

Voice Name
en-IN-PREMIUM-C_MALE

Gender
MALE

Language Code
en-IN

Voice Name
en-IN-Standard-A_FEMALE

Gender
FEMALE

Language Code
en-IN

Voice Name
en-IN-Standard-B_MALE

Gender
MALE

Language Code
en-IN

Voice Name
en-IN-Standard-C_MALE

Gender
MALE

Language Code
en-US

Voice Name
en-US-PREMIUM-A_MALE

Gender
MALE

Language Code
en-US

Voice Name
en-US-PREMIUM-B_MALE

Gender
MALE

Language Code
en-US

Voice Name
en-US-PREMIUM-C_FEMALE

Gender
FEMALE

Language Code
en-US

Voice Name
en-US-PREMIUM-D_MALE

Gender
MALE

Language Code
en-US

Voice Name
en-US-PREMIUM-E_FEMALE

Gender
FEMALE

Language Code
en-US

Voice Name
en-US-PREMIUM-F_FEMALE

Gender
FEMALE

Language Code
en-US

Voice Name
en-US-Standard-B_MALE

Gender
MALE

Language Code
en-US

Voice Name
en-US-Standard-C_FEMALE

Gender
FEMALE

Language Code
en-US

Voice Name
en-US-Standard-D_MALE

Gender
MALE

Language Code
en-US

Voice Name
en-US-Standard-E_FEMALE

Gender
FEMALE

Language Code
es-ES

Voice Name
es-ES-Standard-A_FEMALE

Gender
FEMALE

Language Code
fi-FI

Voice Name
fi-FI-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
fi-FI

Voice Name
fi-FI-Standard-A_FEMALE

Gender
FEMALE

Language Code
fil-PH

Voice Name
fil-PH-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
fil-PH

Voice Name
fil-PH-Standard-A_FEMALE

Gender
FEMALE

Language Code
fr-CA

Voice Name
fr-CA-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
fr-CA

Voice Name
fr-CA-PREMIUM-B_MALE

Gender
MALE

Language Code
fr-CA

Voice Name
fr-CA-PREMIUM-C_FEMALE

Gender
FEMALE

Language Code
fr-CA

Voice Name
fr-CA-PREMIUM-D_MALE

Gender
MALE

Language Code
fr-CA

Voice Name
fr-CA-Standard-A_FEMALE

Gender
FEMALE

Language Code
fr-CA

Voice Name
fr-CA-Standard-B_MALE

Gender
MALE

Language Code
fr-CA

Voice Name
fr-CA-Standard-C_FEMALE

Gender
FEMALE

Language Code
fr-CA

Voice Name
fr-CA-Standard-D_MALE

Gender
MALE

Language Code
fr-FR

Voice Name
fr-FR-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
fr-FR

Voice Name
fr-FR-PREMIUM-B_MALE

Gender
MALE

Language Code
fr-FR

Voice Name
fr-FR-PREMIUM-C_FEMALE

Gender
FEMALE

Language Code
fr-FR

Voice Name
fr-FR-PREMIUM-D_MALE

Gender
MALE

Language Code
fr-FR

Voice Name
fr-FR-Standard-A_FEMALE

Gender
FEMALE

Language Code
fr-FR

Voice Name
fr-FR-Standard-B_MALE

Gender
MALE

Language Code
fr-FR

Voice Name
fr-FR-Standard-C_FEMALE

Gender
FEMALE

Language Code
fr-FR

Voice Name
fr-FR-Standard-D_MALE

Gender
MALE

Language Code
hu-HU

Voice Name
hu-HU-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
hu-HU

Voice Name
hu-HU-Standard-A_FEMALE

Gender
FEMALE

Language Code
id-ID

Voice Name
id-ID-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
id-ID

Voice Name
id-ID-PREMIUM-B_MALE

Gender
MALE

Language Code
id-ID

Voice Name
id-ID-PREMIUM-C_MALE

Gender
MALE

Language Code
id-ID

Voice Name
id-ID-Standard-A_FEMALE

Gender
FEMALE

Language Code
id-ID

Voice Name
id-ID-Standard-B_MALE

Gender
MALE

Language Code
id-ID

Voice Name
id-ID-Standard-C_MALE

Gender
MALE

Language Code
it-IT

Voice Name
it-IT-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
it-IT

Voice Name
it-IT-Standard-A_FEMALE

Gender
FEMALE

Language Code
ja-JP

Voice Name
ja-JP-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
ja-JP

Voice Name
ja-JP-PREMIUM-B_FEMALE

Gender
FEMALE

Language Code
ja-JP

Voice Name
ja-JP-PREMIUM-C_MALE

Gender
MALE

Language Code
ja-JP

Voice Name
ja-JP-PREMIUM-D_MALE

Gender
MALE

Language Code
ja-JP

Voice Name
ja-JP-Standard-A_FEMALE

Gender
FEMALE

Language Code
ja-JP

Voice Name
ja-JP-Standard-B_FEMALE

Gender
FEMALE

Language Code
ja-JP

Voice Name
ja-JP-Standard-C_MALE

Gender
MALE

Language Code
ja-JP

Voice Name
ja-JP-Standard-D_MALE

Gender
MALE

Language Code
ko-KR

Voice Name
ko-KR-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
ko-KR

Voice Name
ko-KR-PREMIUM-B_FEMALE

Gender
FEMALE

Language Code
ko-KR

Voice Name
ko-KR-PREMIUM-C_MALE

Gender
MALE

Language Code
ko-KR

Voice Name
ko-KR-PREMIUM-D_MALE

Gender
MALE

Language Code
ko-KR

Voice Name
ko-KR-Standard-A_FEMALE

Gender
FEMALE

Language Code
ko-KR

Voice Name
ko-KR-Standard-B_FEMALE

Gender
FEMALE

Language Code
ko-KR

Voice Name
ko-KR-Standard-C_MALE

Gender
MALE

Language Code
ko-KR

Voice Name
ko-KR-Standard-D_MALE

Gender
MALE

Language Code
nb-NO

Voice Name
nb-NO-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
nb-NO

Voice Name
nb-NO-PREMIUM-B_MALE

Gender
MALE

Language Code
nb-NO

Voice Name
nb-NO-PREMIUM-C_FEMALE

Gender
FEMALE

Language Code
nb-NO

Voice Name
nb-NO-PREMIUM-D_MALE

Gender
MALE

Language Code
nb-NO

Voice Name
nb-no-PREMIUM-E_FEMALE

Gender
FEMALE

Language Code
nb-NO

Voice Name
nb-NO-Standard-A_FEMALE

Gender
FEMALE

Language Code
nb-NO

Voice Name
nb-NO-Standard-B_MALE

Gender
MALE

Language Code
nb-NO

Voice Name
nb-NO-Standard-C_FEMALE

Gender
FEMALE

Language Code
nb-NO

Voice Name
nb-NO-Standard-D_MALE

Gender
MALE

Language Code
nb-NO

Voice Name
nb-no-Standard-E_FEMALE

Gender
FEMALE

Language Code
nl-NL

Voice Name
nl-NL-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
nl-NL

Voice Name
nl-NL-PREMIUM-B_MALE

Gender
MALE

Language Code
nl-NL

Voice Name
nl-NL-PREMIUM-C_MALE

Gender
MALE

Language Code
nl-NL

Voice Name
nl-NL-PREMIUM-D_FEMALE

Gender
FEMALE

Language Code
nl-NL

Voice Name
nl-NL-PREMIUM-E_FEMALE

Gender
FEMALE

Language Code
nl-NL

Voice Name
nl-NL-Standard-A_FEMALE

Gender
FEMALE

Language Code
nl-NL

Voice Name
nl-NL-Standard-B_MALE

Gender
MALE

Language Code
nl-NL

Voice Name
nl-NL-Standard-C_MALE

Gender
MALE

Language Code
nl-NL

Voice Name
nl-NL-Standard-D_FEMALE

Gender
FEMALE

Language Code
nl-NL

Voice Name
nl-NL-Standard-E_FEMALE

Gender
FEMALE

Language Code
pl-PL

Voice Name
pl-PL-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
pl-PL

Voice Name
pl-PL-PREMIUM-B_MALE

Gender
MALE

Language Code
pl-PL

Voice Name
pl-PL-PREMIUM-C_MALE

Gender
MALE

Language Code
pl-PL

Voice Name
pl-PL-PREMIUM-D_FEMALE

Gender
FEMALE

Language Code
pl-PL

Voice Name
pl-PL-PREMIUM-E_FEMALE

Gender
FEMALE

Language Code
pl-PL

Voice Name
pl-PL-Standard-A_FEMALE

Gender
FEMALE

Language Code
pl-PL

Voice Name
pl-PL-Standard-B_MALE

Gender
MALE

Language Code
pl-PL

Voice Name
pl-PL-Standard-C_MALE

Gender
MALE

Language Code
pl-PL

Voice Name
pl-PL-Standard-D_FEMALE

Gender
FEMALE

Language Code
pl-PL

Voice Name
pl-PL-Standard-E_FEMALE

Gender
FEMALE

Language Code
pt-BR

Voice Name
pt-BR-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
pt-BR

Voice Name
pt-BR-Standard-A_FEMALE

Gender
FEMALE

Language Code
pt-PT

Voice Name
pt-PT-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
pt-PT

Voice Name
pt-PT-PREMIUM-B_MALE

Gender
MALE

Language Code
pt-PT

Voice Name
pt-PT-PREMIUM-C_MALE

Gender
MALE

Language Code
pt-PT

Voice Name
pt-PT-PREMIUM-D_FEMALE

Gender
FEMALE

Language Code
pt-PT

Voice Name
pt-PT-Standard-A_FEMALE

Gender
FEMALE

Language Code
pt-PT

Voice Name
pt-PT-Standard-B_MALE

Gender
MALE

Language Code
pt-PT

Voice Name
pt-PT-Standard-C_MALE

Gender
MALE

Language Code
pt-PT

Voice Name
pt-PT-Standard-D_FEMALE

Gender
FEMALE

Language Code
ru-RU

Voice Name
ru-RU-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
ru-RU

Voice Name
ru-RU-PREMIUM-B_MALE

Gender
MALE

Language Code
ru-RU

Voice Name
ru-RU-PREMIUM-C_FEMALE

Gender
FEMALE

Language Code
ru-RU

Voice Name
ru-RU-PREMIUM-D_MALE

Gender
MALE

Language Code
ru-RU

Voice Name
ru-RU-Standard-A_FEMALE

Gender
FEMALE

Language Code
ru-RU

Voice Name
ru-RU-Standard-B_MALE

Gender
MALE

Language Code
ru-RU

Voice Name
ru-RU-Standard-C_FEMALE

Gender
FEMALE

Language Code
ru-RU

Voice Name
ru-RU-Standard-D_MALE

Gender
MALE

Language Code
sk-SK

Voice Name
sk-SK-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
sk-SK

Voice Name
sk-SK-Standard-A_FEMALE

Gender
FEMALE

Language Code
sv-SE

Voice Name
sv-SE-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
sv-SE

Voice Name
sv-SE-Standard-A_FEMALE

Gender
FEMALE

Language Code
tr-TR

Voice Name
tr-TR-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
tr-TR

Voice Name
tr-TR-PREMIUM-B_MALE

Gender
MALE

Language Code
tr-TR

Voice Name
tr-TR-PREMIUM-C_FEMALE

Gender
FEMALE

Language Code
tr-TR

Voice Name
tr-TR-PREMIUM-D_FEMALE

Gender
FEMALE

Language Code
tr-TR

Voice Name
tr-TR-PREMIUM-E_MALE

Gender
MALE

Language Code
tr-TR

Voice Name
tr-TR-Standard-A_FEMALE

Gender
FEMALE

Language Code
tr-TR

Voice Name
tr-TR-Standard-B_MALE

Gender
MALE

Language Code
tr-TR

Voice Name
tr-TR-Standard-C_FEMALE

Gender
FEMALE

Language Code
tr-TR

Voice Name
tr-TR-Standard-D_FEMALE

Gender
FEMALE

Language Code
tr-TR

Voice Name
tr-TR-Standard-E_MALE

Gender
MALE

Language Code
uk-UA

Voice Name
uk-UA-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
uk-UA

Voice Name
uk-UA-Standard-A_FEMALE

Gender
FEMALE

Language Code
vi-VN

Voice Name
vi-VN-PREMIUM-A_FEMALE

Gender
FEMALE

Language Code
vi-VN

Voice Name
vi-VN-PREMIUM-B_MALE

Gender
MALE

Language Code
vi-VN

Voice Name
vi-VN-PREMIUM-C_FEMALE

Gender
FEMALE

Language Code
vi-VN

Voice Name
vi-VN-PREMIUM-D_MALE

Gender
MALE

Language Code
vi-VN

Voice Name
vi-VN-Standard-A_FEMALE

Gender
FEMALE

Language Code
vi-VN

Voice Name
vi-VN-Standard-B_MALE

Gender
MALE

Language Code
vi-VN

Voice Name
vi-VN-Standard-C_FEMALE

Gender
FEMALE

Language Code
vi-VN

Voice Name
vi-VN-Standard-D_MALE

Gender
MALE

Speech Synthesis Markup Language (SSML) - Examples

Speech Synthesis Markup Language (SSML) is a very simple to understand language similar with HTML, containing HTML like tags with specific meaning in order to rich the experience of pronouncing words, phrases, numbers, dates etc. and making the audio to sound more human like, more natural. Our Text To Speech translator API - ClodPronouncer may be used with SSML, so below are written some simple examples of using SSML language. Of course you may construct more complex SSML text according to your needs. A more complex and detailed approach of SSML language you can find here at W3C.

<speak> is the first tag to begin any ssml markup text and also it has the corresponding closing tag </speak>
<break> means a pause with some optional parameters like time in seconds or miliseconds and strength which may be weak, medium, strong, x-strong

<speak>
  We need to take a pause after the sentence.<break time="2s"/>
  Now we are talking again.
  And also another pause. <break strength="medium"/>
  Finally done.
</speak>

<say-as> means a pronounciation in a certain way as interpret-as attribute is set. Its closing tag is </say-as> Below we set the number 153 as cardinal so one hundred and fifty three.

<speak>
  <say-as interpret-as="cardinal">153</say-as>
</speak>

Below we set the number 48 as ordinal so fourty eighth

<speak>
  <say-as interpret-as="ordinal">48</say-as>
</speak>

Below we set the interpret-as attribute as characters, so it will spell each character of the word write.

<speak>
  <say-as interpret-as="characters">write</say-as>
</speak>

Below we set the interpret-as attribute as fraction, so it will spell seven and a half.

<speak>
  <say-as interpret-as="fraction">7+1/2</say-as>
</speak>

Below we set the interpret-as attribute as expletive so all the words will be censored by a beep.

<speak>
  <say-as interpret-as="expletive">these words are banned</say-as>
</speak>

Below we set the interpret-as attribute as unit, so it means unit of measure and even if we wrote at singular it will spell correctly i.e. twelve feets.

<speak>
  <say-as interpret-as="unit">12 foot</say-as>
</speak>

Below we set the interpret-as attribute as verbatim, similar with characters, so it will spell each character of the word plrder.

<speak>
  <say-as interpret-as="verbatim">plrder</say-as>
</speak>

Below we set the interpret-as attribute as date wth specific format (ddmmyyyy - day, month, year) and detail. Detail may be 1 (day and month or year are required) or 2 (day, month and year are required).

<speak>
  <say-as interpret-as="date" format="ddmmyyyy" detail="1">
    09-10-1960
  </say-as>
</speak>

Below we set the interpret-as attribute as date wth specific format (md - month, day) and detail.

<speak>
  <say-as interpret-as="date" format="md">10-29</say-as>
</speak>

Below we set the interpret-as attribute as date wth specific format (dmy - day, month, year) and detail. Detail may be 1 (day and month or year are required) or 2 (day, month and year are required).

<speak>
  <say-as interpret-as="date" format="dmy" detail="2">
    20-11-1962
  </say-as>
</speak>

Below we set the interpret-as attribute as time wth specific format (hms12 - 12 hours format, hour, minute, second).

<speak>
  <say-as interpret-as="time" format="hms12">7:30pm</say-as>
</speak>

means a paragraph and it has its corresponding closing tag . <s> means a sentence and it also has its corresponding tag </s>.

<speak>
  <p><s>This word is unknown.</s>     <s>This is an important sentence.</s></p>
</speak>

is useful for defining aliases which means that the text will be pronounced as defined in alias attribute. It has its closing tag Below, the acronyme ONU is pronounced as United Nations Organization.

<speak>

   <sub alias="United Nations Organization">ONU</sub>

</speak>

is useful for defining aliases which means that the text will be pronounced as defined in alias attribute. It has its closing tag Below we have an example of some difficult to pronounce words (calcium carbonate) so they are pronounced more simple as chalk.

<speak>

    <sub alias="chalk">calcium carbonate</sub>

</speak>

<prosody> element will define together with its attributes how the words will be pronounced and it has its closing tag </prosody>. The attribute rate may be slow, medium, high and the attribute pitch is expressed in semitones which may be pozitive or negative values. Below is an example with voice lowered with 2 semitones than normal.

<speak>

   <prosody rate="slow" pitch="-2st">May I help you?</prosody>

</speak>

<emphasis> is a similar element with <prosody> but it has only level attribute which may be strong, moderate, none, reduced. It has ist closing tag </emphasis>.

<speak>

   <emphasis level="moderate">I'm very happy to do this</emphasis>

</speak>

Source Code Examples for Using Our Text To Speech API

Imports System.IO
Imports System.Net
Imports System.Web.Script.Serialization

Public Class text_to_speech_api
    Inherits System.Web.UI.Page 
Public Structure RequestFields
        Dim inputtext As String
        Dim ssml As String
        Dim voicename As String
        Dim voicetype As String
        Dim encoding As String
        Dim speed As Single
        Dim pitch As Single
        Dim volume As Single
        Dim saveFileLocally As String
    End Structure
    
    Public Structure ResponseField
        Dim base64AudioString As String
        Dim audioFileURL As String
    End Structure

    Public Structure ErrorFields
        Dim cd As String
        Dim description As String
    End Structure
    
Protected Sub SendRequest()
        Dim Client As WebClient = New WebClient()
        Dim credentials As String = Convert.ToBase64String(Encoding.ASCII.GetBytes("your_username:your_password"))
        Client.Headers(HttpRequestHeader.Authorization) = String.Format("Basic {0}", credentials)
        Client.Headers(HttpRequestHeader.Accept) = "application/json"
        Client.Headers(HttpRequestHeader.ContentType) = "application/json"
        Client.BaseAddress = "https://www.de-vis-software.ro/tts.aspx"
        Dim j As RequestFields = New RequestFields()
        j.inputtext = "Hello World!" 
        j.ssml="Text" 
        j.voicename = "en-US-PREMIUM-C_FEMALE"
        j.voicetype = "HeadPhones"      
        j.encoding = "Mp3"
        j.speed = 1
        j.pitch = 0
        j.volume = 0
        j.saveFileLocally = "Yes"
        Try
            Dim js As String = (New JavaScriptSerializer()).Serialize(j)
            Dim reqString As Byte() = Encoding.[Default].GetBytes(js)
            Dim url As Uri = New Uri(Client.BaseAddress)
            Dim resByte As Byte() = Client.UploadData(url, "post", reqString)
            'The resString below is your needed JSON output
            'similar with {"base64AudioString":"//NETgDffgjjskkj===...HgYtyfFFFTTTFVVVV"}
            Dim resString As String = Encoding.[Default].GetString(resByte)
            If Instr(resString,"base64AudioString:") >0 Then 'In case we got it right without errors
               Dim r as ResponseField = New ResponseField()
               Dim j1 As JavaScriptSerializer = New JavaScriptSerializer()
               'Below we find in r.base64AudioString the string value base64 encoded which may be
               'used as source for html5 Audio control for example and play the file.
               r = j1.Deserialize(Of ResponseField)(resString)
            Else 'So in case of error occurence
               Dim e as ErrorField = New ErrorField()
               Dim j2 As JavaScriptSerializer = New JavaScriptSerializer()
               'Below we find in e.cd (error code) and e.description (error description)
               e = j1.Deserialize(Of ErrorField)(resString)
            End If
            Client.Dispose()
        Catch exception As System.Exception
            Dim ex As System.Exception = exception
            Console.Writeline("ERROR: " & ex.Message)
        End Try
    End Sub
End Class

using System;
using System.Collections.Generic;
using System.Diagnostics;
using System.Globalization;
using System.IO;
using System.Linq;
using System.Reflection;
using System.Runtime.CompilerServices;
using System.Security;
using System.Text;
using System.Threading.Tasks;
using Microsoft.VisualBasic;
using System.Net;
using System.Web.Script.Serialization;

public class text_to_speech_api : System.Web.UI.Page
{
    public struct RequestFields
    {
        public string inputtext;
        public string ssml;
        public string voicename;
        public string voicetype;
        public string encoding;
        public float speed;
        public float pitch;
        public float volume;
        public string saveFileLocally;
    }

    public struct ResponseField
    {
        public string base64AudioString;
        public string audioFileURL;
    }

    public struct ErrorFields
    {
        public string cd;
        public string description;
    }

    protected void SendRequest()
    {
        WebClient Client = new WebClient();
        string credentials = Convert.ToBase64String(Encoding.ASCII.GetBytes("your_username:your_password"));
        Client.Headers[HttpRequestHeader.Authorization] = string.Format("Basic {0}", credentials);
        Client.Headers[HttpRequestHeader.Accept] = "application/json";
        Client.Headers[HttpRequestHeader.ContentType] = "application/json";
        Client.BaseAddress = "https://www.de-vis-software.ro/tts.aspx";
        RequestFields j = new RequestFields();
        j.inputtext = "Hello World!";
        j.ssml = "Text";
        j.voicename = "en-US-PREMIUM-C_FEMALE";
        j.voicetype = "HeadPhones";
        j.encoding = "Mp3";
        j.speed = 1;
        j.pitch = 0;
        j.volume = 0;
        j.saveFileLocally = "Yes";
        try
        {
            string js = (new JavaScriptSerializer()).Serialize(j);
            byte[] reqString = Encoding.Default.GetBytes(js);
            Uri url = new Uri(Client.BaseAddress);
            byte[] resByte = Client.UploadData(url, "post", reqString);
            // The resString below is your needed JSON output
            // similar with {"base64AudioString":"//NETgDffgjjskkj===...HgYtyfFFFTTTFVVVV"}
            string resString = Encoding.Default.GetString(resByte);
            if (Instr(resString, "base64AudioString:") > 0)
            {
                ResponseField r = new ResponseField();
                JavaScriptSerializer j1 = new JavaScriptSerializer();
                // Below we find in r.base64AudioString the string value base64 encoded which may be
                // used as source for html5 Audio control for example and play the file.
                r = j1.Deserialize<ResponseField>(resString);
            }
            else
            {
                ErrorField e = new ErrorField();
                JavaScriptSerializer j2 = new JavaScriptSerializer();
                // Below we find in e.cd (error code) and e.description (error description)
                e = j1.Deserialize<ErrorField>(resString);
            }
            Client.Dispose();
        }
        catch (Exception exception)
        {
            System.Exception ex = exception;
            Console.Writeline("ERROR: " + ex.Message);
        }
    }
}

public class text_to_speech_api extends System.Web.UI.Page
{
//C# TO JAVA CONVERTER WARNING: Java does not allow user-defined value types. The behavior of this class may differ from the original:
//ORIGINAL LINE: public struct RequestFields
	public final static class RequestFields
	{
		public String inputtext;
		public String ssml;
		public String voicename;
		public String voicetype;
		public String encoding;
		public float speed;
		public float pitch;
		public float volume;
		public String saveFileLocally;

		public RequestFields clone()
		{
			RequestFields varCopy = new RequestFields();

			varCopy.inputtext = this.inputtext;
			varCopy.ssml = this.ssml;
			varCopy.voicename = this.voicename;
			varCopy.voicetype = this.voicetype;
			varCopy.encoding = this.encoding;
			varCopy.speed = this.speed;
			varCopy.pitch = this.pitch;
			varCopy.volume = this.volume;
			varCopy.saveFileLocally = this.saveFileLocally;

			return varCopy;
		}
	}

//C# TO JAVA CONVERTER WARNING: Java does not allow user-defined value types. The behavior of this class may differ from the original:
//ORIGINAL LINE: public struct ResponseField
	public final static class ResponseField
	{
		public String base64AudioString;
                public String audioFileURL;
		public ResponseField clone()
		{
			ResponseField varCopy = new ResponseField();

			varCopy.base64AudioString = this.base64AudioString;
			varCopy.audioFileURL = this.audioFileURL;

			return varCopy;
		}
	}

//C# TO JAVA CONVERTER WARNING: Java does not allow user-defined value types. The behavior of this class may differ from the original:
//ORIGINAL LINE: public struct ErrorFields
	public final static class ErrorFields
	{
		public String cd;
		public String description;

		public ErrorFields clone()
		{
			ErrorFields varCopy = new ErrorFields();

			varCopy.cd = this.cd;
			varCopy.description = this.description;

			return varCopy;
		}
	}

	protected final void SendRequest()
	{
		WebClient Client = new WebClient();
		String credentials = Convert.ToBase64String(("your_username:your_password").getBytes(java.nio.charset.StandardCharsets.US_ASCII));
		Client.Headers[HttpRequestHeader.Authorization] = String.format("Basic %1$s", credentials);
		Client.Headers[HttpRequestHeader.Accept] = "application/json";
		Client.Headers[HttpRequestHeader.ContentType] = "application/json";
		Client.BaseAddress = "https://www.de-vis-software.ro/tts.aspx";
		RequestFields j = new RequestFields();
		j.inputtext = "Hello World!";
		j.ssml = "Text";
		j.voicename = "en-US-PREMIUM-C_FEMALE";
		j.voicetype = "HeadPhones";
		j.encoding = "Mp3";
		j.speed = 1;
		j.pitch = 0;
		j.volume = 0;
		j.saveFileLocally = "Yes";
		try
		{
			String js = (new JavaScriptSerializer()).Serialize(j.clone());
//C# TO JAVA CONVERTER WARNING: Unsigned integer types have no direct equivalent in Java:
//ORIGINAL LINE: byte[] reqString = Encoding.Default.GetBytes(js);
			byte[] reqString = Encoding.Default.GetBytes(js);
			Uri url = new Uri(Client.BaseAddress);
//C# TO JAVA CONVERTER WARNING: Unsigned integer types have no direct equivalent in Java:
//ORIGINAL LINE: byte[] resByte = Client.UploadData(url, "post", reqString);
			byte[] resByte = Client.UploadData(url, "post", reqString);
			// The resString below is your needed JSON output
			// similar with {"base64AudioString":"//NETgDffgjjskkj===...HgYtyfFFFTTTFVVVV"}
			String resString = Encoding.Default.GetString(resByte);
			if (Instr(resString, "base64AudioString:") > 0)
			{
				ResponseField r = new ResponseField();
				JavaScriptSerializer j1 = new JavaScriptSerializer();
				// Below we find in r.base64AudioString the string value base64 encoded which may be
				// used as source for html5 Audio control for example and play the file.
				r = j1.<ResponseField>Deserialize(resString).clone();
			}
			else
			{
				ErrorField e = new ErrorField();
				JavaScriptSerializer j2 = new JavaScriptSerializer();
				// Below we find in e.cd (error code) and e.description (error description)
				e = j1.<ErrorField>Deserialize(resString);
			}
			Client.Dispose();
		}
		catch (RuntimeException exception)
		{
			RuntimeException ex = exception;
			Console.Writeline("ERROR: " + ex.getMessage());
		}
	}
}

<?php
ob_start();
  ini_set('display_errors', 1);
  ini_set('display_startup_errors', 1);
  error_reporting(E_ALL);
$data = array('inputtext' => 'Hello World!', 
              'ssml' => 'Text',
              'voicename' => 'en-US-PREMIUM-C_FEMALE',
              'voicetype' => 'HeadPhones',
              'encoding' => 'Mp3',
              'speed' => 1,'pitch' => 0,
              'volume' => 0,
              'saveFileLocally' => 'NO');
$data_string = json_encode($data);
$username = 'your_usernmae';
$password = 'your_password';
$hash = base64_encode($username . ':' . $password);
$headers = array(
'Authorization: Basic ' . $hash
);
?><!DOCTYPE html>
<html lang="en">
<head>
  <title>Test TTS API</title>
</head>
<body>
<?php
 $url = "https://www.de-vis-software.ro/tts.aspx"; // Where you want to post data
 try 
    {
  $ch = curl_init();
  if (FALSE === $ch)
     throw new Exception('failed to initialize');

    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_POST, true);  // Tell cURL you want to post something
    curl_setopt($ch, CURLOPT_POSTFIELDS, $data_string); 
   // Define what you want to post
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
    curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
    curl_setopt($ch, CURLOPT_HEADER, 0);
    curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
    
  //curl_setopt(/* ... */);
  $content = curl_exec($ch);
  
  $info = curl_getinfo($ch);
 
   if (FALSE === $content)
    throw new Exception(curl_error($ch), curl_errno($ch));

  } 
  catch(Exception $e) 
    {
     trigger_error(sprintf(
     'Curl failed with error #%d: %s',
     $e->getCode(), $e->getMessage()),
     E_USER_ERROR);
     }
  echo '<pre>'; print_r($data); echo '</pre>';
  echo '<br />';
  echo http_build_query(array('data' => $data));
  echo '<br /><br />';

 $json = json_encode($data);
echo "<b>JSON Request is:</b>" ."<br />" . $json . "<br />" . "<br />";
  $onlyjson = str_replace("\u0022", '"', $content);

echo "<br />" . "<br />" . "<b>JSON Response From API is:</b>" . "<br />" . $onlyjson . "<br />";?>
</body>
</html>

TTS Online Video Presentation

Text to speech online, CloudPronouncer, is in the video presentation below. Our text to speech reader or text to speech voices is a text to speech translator or tts or you may call it tts demo, text to voice converter. This tts online is for users and developers, so talk to speech, type to speech online, word to speech are just another various tags to name it. Tts generator or text to audio converter are both used in online searches. We do not neglect text to audio app, type to speech app or tts voices that also appeared for a number of searches. We intend to optimize for text to voice generator, text and speech and text to audio online. In fact text and speak, text to voice app, text to speech engine complete the number of the words to be looked for.

Pricing Packages

Please choose one of the below pricing packages for start using our Text To Speech API and online APP!

Start TRIAL
No catches

7 days TRIAL
Use our cloud REST API and online APP
Maximum 700 characters per each request
Maximum 50 requests per DAY in trial period
You do NOT own the commercial copyright of the resulted audio file(s) in trial period.
Get audio file uncompressed as Linear16 format (.wav)
Or get audio file compressed as .mp3 or .ogg file
Get base64 encoded string of audio file which can be source of audio control in HTML5
169 male and female voices Standard and Premium (more natural) in 30 languages including regional accents
Administration console
Support through online chat and/or tickets
We do NOT allow spam accounts for TRIAL

Monthly TIER
Popular

80 USD per month
Use our cloud REST API and online APP
Maximum 700 characters per each request
Maximum 50 requests per MINUTE
You own the commercial copyright of the resulted audio file(s) with NO additional fee.
Maximum 1.000.000 input characters per MONTH
Get audio file uncompressed as Linear16 format (.wav)
Or get audio file compressed as .mp3 or .ogg file
Get base64 encoded string of audio file which can be source of audio control in HTML5
169 male and female voices Standard and Premium (more natural) in 30 languages including regional accents
Administration console
Support through online chat and/or tickets

Yearly TIER
(15% Discount)

816 USD per year
Use our cloud REST API and online APP
Maximum 700 characters per each request
Maximum 50 requests per MINUTE
You own the commercial copyright of the resulted audio file(s) with NO additional fee.
Maximum 1.000.000 input characters per MONTH
Get audio file uncompressed as Linear16 format (.wav)
Or get audio file compressed as .mp3 or .ogg file
Get base64 encoded string of audio file which can be source of audio control in HTML5
169 male and female voices Standard and Premium (more natural) in 30 languages including regional accents
Administration console
Support through online chat and/or tickets

Note: VAT rate may be added or not, function to your country and/or if you are a taxable person or company.

Text To Speech API

Text To Speech APP

Request Parameters Table

Response Parameter Table

Response Error Codes Table

Supported languages and voices

Speech Synthesis Markup Language (SSML) - Examples

Source Code Examples for Using Our Text To Speech API

TTS Online Video Presentation

Pricing Packages

Start TRIAL No catches

Monthly TIER Popular

Yearly TIER (15% Discount)

Start TRIAL
No catches

Monthly TIER
Popular

Yearly TIER
(15% Discount)