Text-to-speech is a program that converts typed or stored text to spoken language. A pregenerated voice speaks the text. Microsoft provides a default voice, called Microsoft Sam, with installation by the operating system (OS). Additional voices may be purchased from independent speech engine manufacturers and loaded during the installation of an application using speech recognition.
Each voice is characterized by a specific language, for example, English, Japanese, Chinese; sub-language, for example American English, British English, Australian English; gender, for example, male, female; and age, for example, child under 13 years old, adult. Proprietary features may provide additional characteristics from the manufacturer’s engine.
Other than selecting a language from a list of available languages, no additional configuration can be performed on languages. Characteristics of individual languages are inherent to the language from the design and may not be altered after the fact.
To set SAPI voice
For more information about speech features, see this Microsoft Web site