Voicent's Multilingual Text To Speech (TTS) Plug-in is a cost-effective way to generate personalized voice messages by converting text to computer-generated voices in real time. The multilingual capability supports voices
including English (American or European), Spanish, Italian, Chinese, German,
Greek, Japanese, French and many more.
A TTS voice engine cannot be directly used by Voicent programs. To convert text to voice, you must have Voicent TTS Plug-In to:
Voicent TTS Plug-In does not include a specific voice. Microsoft Windows operating system provides free TTS voices. If these voices do not meet your quality expectation, there are many high quality TTS voices provided by AT&T, Nuance, Neospeech. For example, you can check out some voice demo at Cepstral Voice Demo. Voicent TTS Plug-in requires 8KHz, 16bit, mono output format. Some 16KHz voices, such as AT&T Crystal 16 voice, are able to produce 8KHz voice also.
Text-to-Speech (TTS) is also called Speech Synthesis. It is the computer-generated voice that simulates human language pronunciation. For telephony applications, especially for regular telephone systems that do not have text capabilities, speech synthesis converts text to voice and then plays it over the phone.
The two characteristics used to describe the quality of a speech synthesis system are naturalness and intelligibility. The naturalness of a speech synthesizer refers to how much the output sounds like the speech of a real person. The intelligibility of a speech synthesizer refers to how easily the output can be understood. The ideal speech synthesizer is both natural and intelligible, and each of the different synthesis technologies try to maximize both of these characteristics.
This is the opposite of speech synthesis. Spoken voices are converted to text by a speech recognition engine.