What Is SSML and How Is It Used?

SSML stands for Speech Synthesis Markup Language. Speech Synthesis Markup Language (SSML) is an XML-based markup language for speech synthesis applications. SSML is often embedded in VoiceXML scripts to drive interactive telephony systems. However, it also may be used for creating text-to-speech audio books, chatbot voices, video, voice synthesis for podcasting, and numerous other text-to-speech projects.
Where ever audio applications can be used, SSML, along with an SSML processor, IPA processor, and Dictionary API, can be used to generate a human-like speech audio. In fact, there are some experts that say SSML may someday replace expensive voice-over services. Voice-over services may not be cost effective for your audio applications. SSML allows the speech developer to type text, add SSML tags, to produce high-quality audio files…with no re-recording required!

What is an SSML processor?

An SSML processor is a text-to-speech system (synthesis processor) that supports SSML, is responsible for rendering plain text into spoken (audio) output using tags and attributes. It uses the tagged information contained in a text editor to be rendered into audio, as intended by the author.
Our parent company, WP Global Syndicate LLC, is the developer of an outstanding SSML processor for personal or corporate training, as well as professional, commercial purposes. The processor is used as an editor, where SSML tags are added to plain text to produce an MP3 audio output. The combined text/SSML tagged file is sent to an Amazon audio services system (lambda) where the MP3 audio file is produced.
Our SSML processor and it’s features cannot be seen anywhere else in the world, especially when coupled with our exclusive International Phonetic Alphabet processor, and Dictionary API. No company in the world provides this type of comprehensive SSML training or products.

Why is an IPA Processor Necessary?

An International Phonetic Alphabet (IPA) processor does some pretty unique things when it comes to processing text-to-speech with an SSML editor. The processor takes a normal English word and translates it into an IPA spelling, so that people from different countries can speak the word in English.
To learn more about this process, click here to learn more about the IPA. To simplify things a bit. There are words in the English language that are spelled the same but have different meanings or parts of speech. They are called homographs. For example, the word bow has two different parts of speech (noun and verb), different audio pronunciations for each, and several definitions.
Bow, the noun (the device used for hunting with arrows), is pronounced one way, while bow, the verb (kneeling in respect to royalty), has a very different pronunciation. But how do we know which one to use? First we must identify whether we need the noun (bow and arrows) or the verb version (kneeling). The only way to determine which one we can select is to:
Know the part of speech for each or know how each is pronounced. When we know one of these, we can use the proper IPA spelling from the IPA processor. Most text-to-speech editors cannot distinguish which IPA spelling to use, without some kind of processor that identifies the parts of speech and the IPA spelling for each. This process hasn’t been developed yet, until now!
With our SSML editor, IPA processor, and dictionary API, we can identify both the IPA spelling and the part of speech for each spelling. With the dictionary API, you can also preview the IPA spelling, definitions for each part of speech, and several examples of how the word is used.

Want to Train Your Internal Staff or Provide SSML training to Customers?

SSML Processor- Commercial License -

When you sign up for our 14-Day Free Trial, it’s our way of introducing students, business owners, and corporate management to our commercially-licensed training product. Here’s what our commercially-licensed training and SSML processor do for your business and employees. You receive everything you see in our online SSML processor, which includes:

  • The same WordPress SSML processor plugin we use
  • Live training classes and videos
  • Low-cost annual updates to our training course and materials
  • Installation on any WordPress website
  • WordPress site integration for a one-time, setup fee (WooCommerce, WooCommerce Memberships, Subscriptions, Sensei, email, etc.), if required.
  • Free online S3 course and assistance with Amazon S3 account setup
  • Priority email technical support
  • A low-cost International Phonetic Alphabet (IPA) processor (Optional)
  • Low-cost Dictionary API that delivers tons of information about a word
  • Word spelling
  • Phonetic spelling
  • IPA spelling
  • Part(s) of speech
  • Definitions
  • Example uses of the word selected

Doing the right Thing, At the right time

SSML Training and Commercial Licensing Information

14-Day Free Trial

The 14-Day Free Trial gives you immediate access to our front-end SSML editor. You must sign up as a member to gain access to the editor. Once you have accessed the editor page, download the Amazon SSML tags PDF by clicking on PDF under the main title; Supported SSML Tags, at the top.

Once in the editor, type in a paragraph or two and start testing the editor by applying tags and attributes from the menu. To apply tags and attributes, highlight the word or place your mouse cursor in a sentence to add the tag. The Process button at the bottom will process the audio file of your paragraph(s). Download the audio file to hear the results.

Monthly Subscription

At this time, the 24/7 monthly video training subscription is not available and is under development. However, you can sign up for our live training classes on a first come, first served basis. We are accepting a maximum of six students per class and taking signups for live training, starting April 15th, 2022.

The live training classes are delivered on Microsoft Teams. They are two evenings a week, two hours per session for six weeks (a total of 24 hours). The classes are recorded for your benefit. For your convenience, you can download each recorded session and preview the classes on your own, personal time.

Live Training Classes
Starting April 18, 2022

Our live SSML training classes start on April 18, 2022. I will personally be conducting the classes. Prior to training, it is recommended that you download the Amazon SSML tag document and preview it before starting the class. This will help the entire class to quickly get started on tagging and understand how tags are used in an SSML editing environment. To download the SSML tag document, click on PDF under the Supported SSML Tags title at the top.

The SSML tags can also be found on the Home page, as well as in the FAQ, with short definitions. For more detailed examples and use, see the Amazon SSML tag document.

We will be explaining and testing tags from the most difficult to the easiest, as we go. You might ask, “Ken, why don’t we start with the easiest ones first?”

Commercial Licensing

We provide a commercial version of our SSML editor. Let’s assume you want to train members of your organization or other customers in SSML. This gives your business a deep discount on this one-of-a-kind application and allows you to train yourself, other end users, or even your customers. We also have the Rebrand version where you get a complete reproduction of our business and website, including eCommerce, training, website installation, and the entire SSML editing system.

One of the advantages of our SSML processing system is the inclusion of two more applications that support SSML tagging and text editing. The first is an International Phonetic Alphabet (IPA) processor. This processor converts English words into IPA spellings of words. The advantage is that the IPA spelling gives foreign and domestic users that ability to hear and repeat the spoken word. The second is a dictionary API. This application allows the SSML editor user to look up the part of speech of words, the IPA spelling, definitions of the word, and examples of the word’s usage.

Why are these applications important?
Both are absolutely necessary.

Let’s use a common example. The word bow in the English language has two parts of speech (noun and verb). The noun definition or example means a device to shoot arrows. The verb definition or example means to kneel in respect for royalty.

Each is pronounced differently, are different parts of speech, and have separate IPA spellings (noun / boʊ / and verb / baʊ /), and different definitions. Each is selected from a dictionary and processed from their respective IPA spellings to get the proper pronunciation in the context of your intended audio output.