BitVoicer Server is a speech recognition and synthesis server for speech
automation. It was developed to enable simple devices, with low processing power, to become
In general, microcontrollers do not have enough memory and processing
power to perform advanced speech recognition and synthesis. BitVoicer Server eliminates the
effects of these limitations by performing the hard work so the microcontroller can allocate
most of its resources to its core functionality.
In BitVoicer Server automation solutions, microcontrollers can act as
one of the three basic device types: Input Devices, Output Devices, or Mixed Devices.
Input Devices are those capable of capturing, digitizing and sending
audio streams to the server. When BitVoicer Server identifies an Input Device, it assigns
one exclusive Speech Recognition Engine (SRE) to that device. SREs constantly analyze all
audio streams sent to the server and when a predefined sentence is identified, BitVoicer
Server performs the actions specified by the user. These actions are called commands
and can be used to start other applications, synthesize speech, play audio
files or send data (commands) to Output and Mixed Devices. The user can define one or more
commands for each sentence. The user can also define the order in which the commands will be
executed, the time interval between them, and which Output or Mixed Devices are the targets
of the commands. That is, with one single Input Device license you can control multiple
Output Devices. Lastly, there are the Mixed Devices that are capable of acting as Input and
Although BitVoicer Server has been developed mainly for the speech
automation of electronic devices, it can also be used for application automation. This is
possible because BitVoicer Server can use the server audio adapter to capture and reproduce
audio. Besides, BitVoicer Server exposes
Windows Communication Foundation (WCF)
services for inter-application communication. The WCF services exposed by the server use
Web Service (WS)
specifications that enable the integration with a variety of development platforms (e.g.
.NET, Java and Delphi). In case of .NET development, there is also the option of using the
integration library described in the product documentation.
Client devices can establish communication with BitVoicer Server through
two communication interfaces: serial and TCP/IP. Virtual serial ports, such as those created
by Bluetooth and USB/Serial adapters, are also supported. These adapters enable BitVoicer
Server to send commands to devices that use other communication protocols.
More information about BitVoicer Server is available in the
- Supports 17 languages from 26 countries and regions:
- Catalan (Catalonia)
- Chinese (China, Honk Kong and Taiwan)
- Danish (Denmark)
- Dutch (Netherlands)
- English (Australia, Canada, India, United Kingdom and United States)
- Finnish (Finland)
- French (Canada and France)
- German (Germany)
- Italian (Italy)
- Japanese (Japan)
- Korean (Korea)
- Norwegian, Bokmål (Norway)
- Polish (Poland)
- Portuguese (Brazil and Portugal)
- Russian (Russia)
- Spanish (Mexico and Spain)
- Swedish (Sweden)
- Multi-device: BitVoicer Server has a new manager for speech recognition
and synthesis engines which is able to serve multiple devices simultaneously. Each
device can function as a point of capture or reproduction and have its exclusive speech
recognition or synthesis engine.
- Enhanced protocol: The BitVoicer Server Protocol (BVSP) brings
significant improvements over the communication protocol used in the previous BitVoicer
versions. Now client devices are able to retrieve server status information and exchange
data with other applications running on the server through the same communication channel
used to transmit audio.
- Windows service: Besides consuming few hardware resources, BitVoicer
Server is executed as a Windows service. This enables BitVoicer Server to become a
transparent resource and cause little or no interference on the user interface.
- Integration: Application developers can retrieve the results of
recognition operations from the server and exchange data with client devices through
Windows Communication Foundation (WCF) services. For .NET development, there is also a
.NET integration library available.
- It does not require speech recognition engine training.
- It does not require pre-recording of sentences.
- Speaker-independent recognition.
- Unlimited number of sentences, commands and devices.