Human Sounding Text to Speech Peripheral Targets Passenger Information Systems

For the first time, multi-lingual announcements in human quality voices can be generated from the digital signals feeding existing transit infrastructure. TextSpeak has released the TTS-EM-HD2, the smallest and most sophisticated voice synthesis paging and announcement product of its kind. The stand-alone package requires only one digital input signal and a speaker connection to produce spoken audio. The conversion of informational data to a clear, natural sounding voice is completely automatic.

Dynamic and real-time passenger information, alerts and security warnings can be spoken from message queues, streaming data or directly from typed text, locally or from distant distribution points. The TextSpeak integrated audio amplifiers deliver the synthesized sound to paging systems, radio and video channels, or directly to a single speaker.

Unattended bus stops and rail platforms that are silent can be upgraded to support arrival/departure announcements at extremely low costs. Safety is also enhanced when used to supplement existing public address systems. Mass notification and emergency messages can be sent and broadcast from information at remote command centers. In addition, passengers with disabilities, both blind or with limited sight can be accommodated with audio announcements.

Designed from the ground up to support transportation, the TTS-EM scales to meet the most demanding specifications.

• Speech can be created from existing sources, such as RS-232 feeds to scrolling LED digital signage, modem data and Ethernet broadcasts.  
• Informational alerts can be pre-programmed and started with the push of a button or launched remotely by automated systems.
• Moving vehicles can offer dynamic announcement information transmitted by radio, from stored data, or updated locally from a keyboard.
• Multi-lingual announcements can be easily generated, with precise accents, to speak directly to international travelers.
• Audio messaging can be queued for sequential delivery. Real time text can be supplemented with pre-recorded messages, tones or even music.
• Deployment is suited for parking, platforms, trams, buses, gates, rail, marine and roadway systems 

"The speech quality we digitally synthesize is nearly indistinguishable from a spoken human voice," said Nancy Wolfe, president of TextSpeak. "We have removed the requirement of a PC interface and created flexible deployment models with a suite of world languages. This will enable air, sea, rail and land transit systems a means to modernize audio delivery at a low cost that leverages their existing wiring and infrastructure."

TextSpeak speech systems are currently deployed with ITS in large mass transportation facilities, onboard buses and at transit platforms worldwide. TTS-EM-HD2 versions are priced below $300 in moderate quantities and single unit evaluation packages are available online.

TTS-EM-HD2 World Languages include: Arabic, Chinese, Czech, Danish, Dutch, English, Finnish, French, German, Greek, Japanese, Korean, Italian, Norwegian, Polish, Turkish, Portuguese, Russian, Spanish, and Swedish, among others.