Converting text information to speech, thanks to speech synthesis

Text2Speach allows you to voice any, including non-standard texts, in such a way that the listener has the feeling that he hears a natural human voice.

The text can be read by various voices. Each voice is based on the use of the speakers speech base of about 10 hours of speech marked on 9 levels, including text interpretation, markup for words, syllables, allophones, pauses, markers of verbal and phrasal stress, intonation types, non-speech phenomena and other phonetic phenomena.

For correct intonation and determination of the place of stress in words, is a powerful module for automatic processing of Russian text , using morphological, syntactic and semantic types of analysis.

Features synthesizer
  • Adjustable pronunciation rate
  • Custom dialing number
  • Pause between dialing attempts
  • Response time
  • Voice type: Male or Female
  • Emotionality: Neutral, Joyful, Annoyed
  • High quality and natural sound on free text
  • Accounting for phonetic, morphological and grammatical features of the Russian language
  • Natural intonation cloning technology
  • Correct placement of stresses
  • Proper interpretation of abbreviations, numbers, abbreviations and special characters
  • Ease of use and deployment
Options for use
  • Building automated information and reference telephone systems for voice self-service in Contact Centers (GHS - voice self-service system)
  • Variable robot for outgoing or incoming calls.
  • Autoinformer
  • Two-factor authentication
How you can work
  1. Personal Account
  2. API documentation (SIP, SMPP, HTTP, XML, SOAP)