wiki:TextToSpeech

Version 2 (modified by kmaclean, 14 years ago) (diff)

--

  • MBROLA Project
    • The aim of the MBROLA project create a set of speech synthesizers for as many languages as possible, for use in non-commercial applications.
    • Languages: Afrikaans, American English, Arabic, Brazilian Portuguese, Breton, British English, Canadian French, Croatian, Czech, Dutch, Estonian, French, German, Greek, Korean, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Iranian, Japanese, Classical Latin, Lithuanian, Malay, Polish, Portuguese (European), Romanian, Spanish, Spanish Mexican, Swedish, Telugu, Turkish, Spanish Venezuelan
  • Festival and Festival related TTS engines
    • Festival Speech Synthesis System
      • offers a general framework for building speech synthesis systems as well as including examples of various modules. As a whole it offers full text to speech through a number APIs: from shell level, though a Scheme command interpreter, as a C++ library, from Java, and an Emacs interface.
      • Languages: English (British and American), and Spanish;
      • can use the Sable markup language.
    • Flite
      • Flite (festival-lite) is a small, fast run-time synthesis engine primarily designed for small embedded machines and/or large servers.
      • is designed as an alternative synthesis engine to Festival for voices built using the FestVox? suite of voice building tools.
    • FreeTTS
      • written in Java;
      • based on Flite.
    • festvox
      • Toolkit for building of new synthetic voices for the Festival Group of TTS engines.
  • gnuspeech
    • an extensible, text-to-speech package, based on real-time, articulatory, speech-synthesis-by-rules;
    • includes the MONET parameter editor.
    • Languages: English
  • Epos Speech Synthesis System
    • Epos is a language independent rule-driven Text-to-Speech (TTS) system primarily designed to serve as a research tool.
    • Language: Czech and Slovak
  • HTS (HMM-Based Speech Synthesis System)
    • comes with a small run-time synthesis engine (less than 1 MB including acoustic models), which can run without the HTK library.
    • uses the Festival Speech Synthesis System as a text analyzer.
  • MARY Text-to-Speech System
    • Languages: German, English and Tibetan.
    • Sable and SSML markup languages