You are here

Text to Speech Products

TripleTalk USB Mini DECtalk USB TripleTalk USB TripleTalk PCI
TripleTalk USB Mini Hardware DECtalk USB Hardware TripleTalk USB Hardware TripleTalk PCI Hardware

What is text to speech, or "TTS" as it is commonly referred to?

Simply stated, TTS is the transmission of text or words in electronic form to a device called a speech synthesizer, producing understandable human sounding speech.

The history of machine generated speech surprisingly goes back a long way. It is not just a product of our modern technical times! In 1779 the Danish scientist Christian Kratzenstein built mechanical models of the human vocal tract that could make vowel sounds: a e i o and u.

Later, other scientists added models of the lips and tongue and were able to produce consonants as well. The idea of modeling the vocal tract caught on, and breaking speech into its component parts or unique sounds (more correctly called "phonemes") is what our modern speech machines do.

Early attempts at creating electronic speech were limited by the technology of the time and were often nothing more than monotone, hard to understand noise! The first computer generated speech was demonstrated in 1961, using an IBM 704 computer. That first demonstration included the song "Daisy Bell" which most of us will recall from the movie 2001, when the HAL9000 computer was being put to sleep!

As technology has advanced so has TTS technology. Desktop computers are now powerful enough that speech can be generated with an easy to use program. Simply type the words and the program does the speaking! Text to speech is now also done with small computer chips as well, enabling the technology to be easily added to a product.

What we have today are computer and software models of the human vocal tract that combine the basic sounds or phonemes together smoothly, adding the right inflection at the beginning or end of a sentence, to produce pleasant sounding, easily understood speech.

And it all started over 300 years ago!

Access Solutions has been designing advanced multi-language voice synthesizers for over 10 years. We continue to use the latest technology as it becomes available, bringing ever improved speech and ease of use and value for our customers.

Our current product offerings include:

We can also develop custom text to speech solutions for you! Contact us for details!