|
|
 |
Text-to-Speech
Play back dynamic texts or database entries
CreaVoice®Text-to-Speech
Die schnelle und zuverlässige automatische Telefonzentrale
Highlights
- multilingual
- multi-channel
- supports SAPI and VoiceXML
- user definable pronounciation lexica
- Corporate Voices possible
- variable synthesis parameters
CreaVoice®
Implement Voice Portals, access E-mail, Web pages, News, Traffic information or other regularly updated information by phone, realize intelligent and personal assistants, enable voice controlled Unified Messaging (UMS) by phone. All is in your hand.
Speech synthesis, also named Text- to-Speech (TTS), is usually used, where huge information volumes have to be read out aloud or where information is frequently updated. With TTS any written text can be converted into sound.
Exact knowledge of a language allows for an outstanding pronunciation; many years of development by various manufacturers now leads to a TTS quality of highest degrees an is as close as possible to the human voice.
The existing text is broken down by the system, using different algorithms, into ever smaller units (sentence, word, syllables...) until the lowest level of dismantling is reached. Then the pronunciation of the words is determined and an analysis of the linguistic structure will be performed.
According to this analysis speech melody, speech rhythm and pauses are determined. Through diphones recorded by a "real" speaker and using specific exception lists the synthesized text is then read out aloud. Soon, verbal communication with machines through voice input and output will be taken for granted. Driven by the automobile and telephony industry even today, high level speech synthesis software is a our disposal.
Inquiry of plane or train schedules, takeoff or of arrival times and event dates is substantially facilitated through the use of automated systems with TTS. CreaLog always offers you state of the art technology from different manufacturers, adapted to your special needs.
Technology partners:
  
|
|
|
|
