Speech Synthesis

  • HOME > 
  • Speech Synthesis > 
  • Selvy TTS-Server

Selvy TTS-Server  

Provides a high performance/capacity text-to-speech (TTS) solution through server-based solutions, regardless of platform or specifications
Supports seamless text-to-speech conversions in various languages including Korean, English, Chinese, Japanese and others, using sophisticated language processing technology
Selvy TTS Server is optimized to provide reliable services, in real-time, for simultaneous users by using both multi-tasking and multi-threading.
  • Supports natural intonation and accurate pronunciation enhanced by language-specific rhythm
  • Maintains a fast text-to-speech conversion speed and high system reliability
  • Guarantees stable operations for large-scale multi-channel services
  • Supports various types of system environments through server/client solutions
  • Supports secure server monitoring and control functions, including management,
    statistics and log control
  • High-quality consultancy through R&D and commercialization performance over 10 years
  • Applicable to the IVR system, voice homepage and broadcasting transmission services
  • Solution proven through obtaining the Good Software (GS) certification
Major Application Examples  
ARS at call-centers
(Banking, securities, insurance, cards, transportation, aviation, weather, culture)
Applies to a voice service used to read out variable customer information in the ARS
(Unified Messaging System)
Applies to the voice message transfer by using speech synthesis technology in UMS
(Audio guidance website for the visually impaired)
Applies to the audio listening feature of the audio guidance service on websites for the visually impaired
Voice Portal
Applies speech synthesis technology to real-time information services on websites and telephone networks
text_to_speech_solution_for_cti Speech Solution for CTI
Selvy TTS Server can be applied to ARS and telebanking systems for financial institutions, public institutions and enterprises, by rapidly generating a TTS voice without the need for pre-recording by a voice actor. This can be used for various service scenario changes and events, in addition to providing the customer with an age-specific voice service.
Furthermore, when customers are verifying and inquiring about information, it increases their satisfaction with the service through the use of natural sound quality.
text_to_speech_solution_for_education Speech Solution for Education
In line with the requirements of foreign language curriculums of language institutes, educational institutions or educational software, Selvy TTS Server provides the voice of a native speaker for a foreign language learner to listen to and repeat to develop listening skills,
as well as recording and reading out the learner's vocalizations, which they can then compare with the sound of TTS, assisting the learner with fluent and correct pronunciation.
With the aid of a speech recognizer, pronunciation correction is also possible. This is applicable to Korean, English, Chinese and Japanese, and is already being used in language institutes and public educational institutions.
text_to_speech_other Other fields of application
TTS enables the visually impaired or people with disabilities to conveniently use the websites of public offices through voice control.