SpeechTech Company, Ltd., was founded as a spin-off University of West Bohemia. The company participates in various research areas, mainly with the Department of Artificial Intelligence, a leading research center in the Czech Republic at the Department of Cybernetics Faculty of Applied Sciences University of West Bohemia.
SpeechTech, Ltd. profiles as a company delivering complete solutions for voice technology with a specialization in languages of Central Europe. These are primarily systems based on proprietary technology:
- Speech recognition - enabling continuous speech recognition (Automatic Speech Recognition ASR), especially transcription or dictation recognition commands, numbers and names in interactive telephony application
- Speech synthesis - generating natural-sounding speech from text (Text-To-Speech, TTS), the use of telephony applications, in information systems, online advertising campaigns, telemarketing, and more.
- Voice dialog systems - applications made available via telephone (Interactive Voice Response, IVR), mainly used in the call center and telephone exchanges, enabling telephone access to extensive databases, automatic telephone switchboard, etc..
SpeechTech, Ltd. delivers not only basic modules for speech technologies, but also comprehensive solutions tailored to customer needs. The company offers a comprehensive analysis and subsequent implementation of systems using speech technologies. We also offer custom development in the following areas:
- Automatic recognition of dictation - analyze, design and implement a system for dictation in any domain (such as medical applications, the judiciary and the law ...)
- Telephone applications - software for call centers and interactive telephony applications (IVR), telemarketing, direct access to large databases
- Full-text search of audiovisual archives - indexing and searching large audio and video archives, client applications, remote access, search for specific words and phrases in real time
SpeechTech Archive is a system for creating and searching audiovisual archives. The purpose of the system is to provide users with the ability to quickly find events (occurrences of words or phrases) in a very large archives of video or audio recordings. For this purpose, the first the index files of all recordings in the archive is automatically generated, in which later the search is carried out. This procedure provides a much faster search found key phrases than can be achieved by direct application to search recordings on their own.
For telephone systems we offer the IVR server, enabling integration with your SIP / ISDN PBX. IVR server supports open standards such as W3C VoiceXML, SSML, SRGS and more. To achieve good interoperability with ASR and TTS support both our server and our 
SpeechTech Operator is a voice-controlled system for connecting telephone calls. Usually connected to the corporate telephone network via ISDN, or SIP. The purpose of the system is to connect a call by the caller, the caller does not know the telephone number dialed, but suffice to say the name of the person calling. The system is based on using our own technology for speech recognition.
Product SpeechTech ASR module is designed for use in other system units, which is required to use speech recognition technology. And both continuous speech and isolated words and phrases. This module is used internally in many other custom products such as 
SpeechTech MegaWord is an application for automatic transcription of spoken dictation into written form. We use our own highly advanced technology for automatic recognition of continuous speech, which can be also integrated into other products. To achieve very high quality of trascription, we are using carefully prepared domain specific language models in MegaWord. For example, in judicial domain, system achieves 97% success rate. We have plenty of other domains prepared, some of the with our partners or customers.
The core of TTS family products is a TTS engine with the set of our own original voices. The TTS product always consists of two parts - TTS engine and the voice. Versions of those parts used in the product determines the quality of the resulting synthetic voice and performance of the product in computing power.