The Spanish National Library just added online text to speech to its online documents. This follows the speech-enabling of its website last October. This is the latest example of how content owners are increasingly looking to customize how they want speech to interact with online text.

The first step is usually for content owners to add speech to their  websites. This can be customized in different ways like:

• What part(s) of a web page should be read
• Adding multiple listen buttons to a web page
• Adding multiple audio versions in terms of languages and voices
• Setting the default speed and pitch of the voice
• Specific pronunciation of certain words
• Design and placement of the audio player
• Rules for how images, tables, links should be read

This is customization at the web page level. Then content owners, like the Spanish National Library, also want to go deeper and provide their users with an audio access to online documents. Document formats like PDF have their own structure and we provide a specific reading and viewing solution to that effect.

Another aspect of customization involves the speech-enabling of forms. This provides end users with a voice service helping them to fill out online forms.

Customers can now adapt how they want online speech services to be integrated to their content.

It’s amazing how much text content gets created every day on the web. Think about all the blog posts, news articles and updates which generate billions of new text each day. Dynamic content brings about enormous volumes of text each second.

Now combine that with how much of this text content gets increasingly accessed from mobile devices. According to Comscore’s report, half of the total U.S. mobile population uses mobile media. The mobile media user population (those who browse the mobile web, access applications, or download content) grew 19 percent in the past year to more than 116 million people at the end of August 2011.

The problems with reading text from mobile devices for users are that:

• They can’t engage in other activities or tasks while reading
• They might have reading disabilities that keep them from accessing the written content
• The level of comfort offered by smaller screens is not always adequate

Having an online text to speech feature solves those problems and enables content owners to distribute their text on the fly into audio. The speech-enabling of the content that is displayed on mobile devices also increases the value of the text since it has both a written and audio output.

Contact us if you want to find out more about how you can unmute your online text content.

Amongst the number of customization possibilities offered by ReadSpeaker online text to speech solutions, the ability to switch languages and/or voices can be useful in a number of situations:

• Some websites mix different languages within a same page.
• In some cases, you might want to distinguish a quote from the rest of the text in your web page by allocating a different voice to speech-enable the quote.
• You have a web page where both genders are quoted and therefore need to have female and male voices.
• A combination of the above points.

You can test our automatic language switch demo and our automatic voice switch demo to see how this works.

Contact us if you want a free online text to speech demo of how these automatic voice and language switches work on your own web site.

Although text-to-speech technology has made a lot of progress, it can sometimes stumble on certain terms such as acronyms, abbreviations, date formats or number representations to name a few. We have some customers where the pronunciation needs fine-tuning such as in the pharmaceutical sector for example where it is even more important that each term is perfectly well read.

Every account that we open comes with a specific dictionary for the customer. We provide a service to each of our customers that helps them with pronunciation issues when they exist. Some of the pronunciation corrections will only be relevant to the dictionary of a particular customer, but in some instances the corrections can also be used for the default dictionary and benefit our entire customer base. We have a very knowledgeable network of linguists that can help our customers in many parts of the world when they encounter pronunciation difficulties.

We have prepared a few online text to speech demos that show the before and after effect of our work on some types of words that can get mispronounced by speech synthesis.

Photo Credit: Jim Linwood

This might sound like a shampoo & conditioner ad but it describes the “ReadSpeaker effect”. By adding a text-to-speech layer to your online content you are effectively providing an audio channel on top of your text content. Once you have ReadSpeaker on your web site, then you have an automatic and on-the-fly talking web site.

What are the advantages of providing an audio version of your online text content:

• Choice – you are providing a greater choice to your visitors on how they can consume your content.
• Equal access – you are reducing the digital divide by allowing users with different reading disabilities to access your  written content.
• Convenience – visitors to your web site or mobile app can listen while they are on the go, for example commuting to work, thereby making your content more convenient to access.
• Learning – if you propose content for learning purposes, having it in audio format reinforces the learning experience by enabling users to listen to your educational content on-the-fly or by saving the mp3 file for later consumption.
• Availability – an audio version of your web site or mobile app is always there for your visitors to use with the simple click & listen feature of our web based solutions.

Photo credit : takot

photo credit: Jamiesrabbits

One of the key elements in text to speech online is to have the web site or mobile app render the reading out of the text to a near faultless experience. We work with default dictionaries as well as dictionaries that are customer specific. In some cases, industry jargon (think the pharmaceutical industry here) can have very specific words that the default dictionary will not always correctly read out. That is where we provide a service which helps our customers enrich their own dictionaries with the corrected pronunciations. If the term is generic, the corrections then also get added to the default dictionary. Here is how the process typically works.

The customer reports mispronounced words/phrases using our pronunciation sheet, where they:

• fill in how and what it is that is mispronounced;
• a description of how it should be pronounced;
• the context where the mispronunciation occurs;
• and an URL to where the mispronunciation occurs (quite often the mispronunciation are due to the context or the HTML code).

We then use the information we get to make corrections to the HTML code or to a specific word. If it is indeed a word itself that is mispronounced we make phonetic transcriptions using different phonetic notations that represent the International Phonetic Alphabet. The notations can for example be X-SAMPA or Kirschenbaum. The corrections are made in our default or customer specific dictionaries were we make search and replace patterns using regular expressions.

Customers sometimes ask us if our text to speech online solutions pre-record the audio version of the text that is speech-enabled. The answer is that our products don’t pre-record anything, the audio we generate is done on-the-fly. This enables ReadSpeaker to convert text into speech on any dynamic web site. We have different products, so I’ll discuss implementation of our most popular one, ReadSpeaker Embedded Highlighting. There are basically 3 steps:

1. Add a short JavaScript to your website code
2. Add our Listen button using the HTML code we provide. We include recommendations in our implementation instructions on how to place the listen button
3. Define the reading area of your web site by either specifying the content to be read out using the HTML ID attribute or by using HTML start and stop comments

Apart from these 3 basic steps, we also include in our instructions a ready-made template for each of our text to speech online solutions which you can use on your web site to explain to your users how to use the listen function. We also provide information on how to name the mp3 file for users who want to save the mp3 file (for example if they don’t have flash) and other recommendations to customize the reading out loud of your web pages.

One you have implemented the above steps, the end-result is:

1. The user visits your site
2. He/she clicks on the listen button; ReadSpeaker detects the page/text
3. ReadSpeaker collects the text and produces the speech
4. …and sends the audio to the user

This process only takes a fraction of a second and doesn’t require the end user to download any software or plugin to be able to listen to your web site.