Wizzard Software is shipping speaker-independent voice recognition software aimed at adding large-vocabulary, offline voice-recognition capabilities to server-based Linux applications. The company says WizzScribe SI can convert large volumes of audio data into searchable text, for data-mining, storage, analysis, and information archiving.

According to Wizzard, WizzScribe SI incorporates a “conversational model,” said to eliminate the need for user training. The product is easily integrated with server-based Linux applications, without an SDK (software development kit), according to the company.

Bruce Phifer, Wizzard's general manager of technology and services, stated, “We believe [this product] will address many large-scale opportunities. It is based on new technology that produces exceptional accuracy, even via telephony.”

Availability

WizzScribe SI for Linux is shipping now. It will be demonstrated at the SpeechTEK trade show, Aug. 7-10 in New York City.

 
This article was originally published on LinuxDevices.com and has been donated to the open source community by QuinStreet Inc. Please visit LinuxToday.com for up-to-date news and articles about Linux and open source.