Jul 20, 2023

Language independent Text-to-Speech (TTS) system

Epos is a language independent rule-driven Text-to-Speech TTS system primarily designed to serve as a research tool. Epos is or tries to be independent of the language processed, linguistic description method, and computing environment. It has the following features

  • Czech and Slovak text to speech synthesis configuration
  • LPC and time domain speech synthesizers
  • Prosody modelling driven by rules, prosody models, and artificial neural networks
  • All language dependencies are defined in the configuration files, as opposed to the source code
  • Documentation in English included in the distribution

This is a port for the development version of Epos.

Checkout these related ports:
  • Zynaddsubfx - Realtime software synthesizer
  • Zrythm - Modern music production system, also known as DAW
  • Zplugins-lv2 - Collection of LV2 plugins to be bundled with Zrythm
  • Zmusic - GZDoom's music system as a standalone library
  • Zita-rev1 - Reworked version of the reverb originally developed for Aeolus
  • Zita-resampler - C++ library for resampling audio signals
  • Zita-njbridge - Command line client to transmit audio over a local IP network
  • Zita-mu1 - Simple Jack app used to organise stereo monitoring
  • Zita-jclient - Library to create a Jack client with a few lines of C++
  • Zita-dpl1 - Look-ahead digital peak level limiter
  • Zita-convolver - Fast, partitioned convolution engine library
  • Zita-bls1 - Blumlein Shuffler converter of binaural signals to stereo speaker pair
  • Zita-at1 - Autotuner Jack application
  • Zita-alsa-pcmi - Easy access to ALSA PCM devices
  • Zinf - GTK-based MP3 player