Products

Text-to-Speech

Text-to-Speech

Text-to-Speech (TTS) allows for the automated conversion of text to speech. Our products enable automated composition and announcement of vocal messages in public or private areas.

Advertisers use a variety of techniques for promoting their products to potential customers, many times utilizing audio and/or visual means. Vocal announcements are also commonly used for informational purposes. A typical case is the announcement of arrivals, departures, delays or other issues arisen on transportation stations such as airports, train or bus stations. This imposes an employee (or more) being dedicated to this task or switching between tasks when an announcement should be made; often announcing the same message more than once. Voice messages used for advertisement purposes are often recorded in studios with special equipment by actors, which imply a time-consuming and expensive process.

Automatic conversion of written text to voice messages could assist the promotion of products in such cases by creating and announcing promotions or special offers instantaneously in places such as malls, supermarkets, exhibitions, and suchlike. Similarly, announcements could be made by utilizing any conventional PC while having the potential of scheduling their repeating frequency when necessary. It is worth noting that vocal announcements can be created dynamically based on information from predefined sources and the whole process can be completely automated. Such an approach has a great potential for applications targeted to assist blind people and people with impaired vision.

The conversion of text to speech is achieved through a technique known as voice synthesis, currently supporting more than 20 languages. There is a set of predefined voices which are utilized for the composition of the message and there are some other features as well including adjustment of the speaker's volume and pitch as well as preset actions like laughing.