About WizzScribe SI (Speaker Independent) for Linux

Through the use of an offline (deferred, a.k.a speak now, reco later) mode of voice recognition, WizzScribe SI for Linux supports a wide variety of input devices and methods, and can add speech recognition capability to "industrial strength" server-based applications whenever large volumes of audio need to be converted into text for searching, data-mining, storage and analysis. This technology incorporates a conversational model, thus eliminating the dependence on user training and enrollment that is normally required in traditional dictation models. Many emerging speech recognition applications do not enable speaker enrollment/training, yet they still require a fairly high level of accuracy. For these applications and environments, it is recommended that Developers consider WizzScribe SI for Linux.

Licensing

WizzScribe SI for Linux $3,400.00

		License for internal development use or deployment and/or external distribution. License for internal development use or deployment and/or external distribution. Please note that licensing for this product is limited to usage for data mining, jist analyst and prioritization type of usage. It is not licensed for usage as a voicemail to text converter.

Runtime deployment/distribution licensing package: Prices are based on volume & scenario

Note: All licensing is based on volume grids where the per unit prices decrease as volumes increase. Each license covers one speech engine on one processor. For example: Wizzscribe SI for Linux Server licenses start at $3400.00 for one processor.

Functional Attributes

• Powered by state-of-the-art IBM speech recognition technology.
  
• Provides speech recognition and conversion to text at the request of a client application (not provided as part of WizzScribe SI for Linux) through the server API.
  
• WizzScribe SI for Linux is run and you specify command line parameters (including name of the audio file and different options).
  
• Processes WAVE PCM 8khz-16 bit-Mono wavefiles from telephony, microphone, or handheld device and converts them directly to text.
  
• Supports two modes of speed, (fast and accurate) - fast mode recognition processing time is about equivalent to the length of the audio.
  
• Shows time boundaries (within the audio) for each recognized word.
  
• Generates the list of alternatives for each recognized word.
  
• Provides confidence scores for each recognized word.
  
• Scalability can be provided for such that multiple WizzScribe SI for Linux Servers can handle large volumes of audio processing.