Speech Synthesizer Text-to-Speech Engines
Information and Support for NCH Speech Software A number of NCH Software applications include speech synthesizers or text-to-speech features; including Verbose Text to Speech Software and WavePad Sound Editing Software.
Text to Speech Voices Our software will use the default text-to-speech voice on your computer for all text-to-speech synthesis. For Windows users this will typically be either Microsoft Sam or Microsoft Anna, which have come standard with every Windows operating system since Windows XP. Our software supports SAPI 4 and SAPI 5 compliant voices.
Note: Windows Vista and 7 will not support SAPI 4, only SAPI 5 compliant voices.
Alternative Text to Speech Voices If you don't like the sound of the default text-to-speech voice on your computer, or if do not have one, you can install a third-party voice. Once a new SAPI 5 voice is installed, restart the program for it to appear as an option.
|If you are looking for a new voice for your computer one place we recommend you look is Cepstral. Cepstral supplies many high quality, natural sounding SAPI 5 compliant voices you can choose from.|
Keyword Searching Many of our recording applications, such as the VRS Telephone and Voice Recording System, can process audio recordings, convert them to text, and search for keywords.
To use the search functionality, you need to have a speech recognition engine that supports SAPI 4 or SAPI 5 and context-free grammar installed on your computer.
Voice Commands Some NCH programs, like Express Dictate (Windows only) and Express Talk, can work with your computer's speech recognition engine for hands-free control of the software. To set up voice commands, first you need to configure your computer's speech recognition engine. Our software requires a SAPI 5 compatible speech engine.
A SAPI 5 compatible speech engine comes standard with Windows Vista and Windows 7 and can be configured by going to your system’s control panel under Ease of Access -> Speech Recognition Options -> Start Speech Recognition. You’ll go through guided steps that will teach your computer to recognize your voice and accent.
You should always thoroughly train a speech engine to ensure it correctly recognizes words and phrases.