Multiphone is a research text-to-speech system for the Russian and Belarusian languages ​​with wide experimental opportunities for changes in voice intonation and many other parameters of the synthesized speech.

Text-to-speech synthesis is based on lexical and grammatical analysis of the input text by simulating the processes of speech formation, given the rules of sound pronunciation and intonation in Belarusian or Russian. After putting an orthographic text into the program, a number of specialized processors (text, prosodic, phonetic and acoustic ones) runs. In line with the idea of developing a multilingual tts system, these processors are language-independent, and linguistic specificity is defined by a corresponding set of data and knowledge bases.