FreeTTS 1.2 released

Willie has just rolled a new release of FreeTTS, the speech synthesizer written entirely in the Java programming language. Check out the release announcement. Some notable changes with this release:

  • Improvements to the emacspeak server demo
  • Performance improvements for time-to-first-sample and cancel
  • Improvements to the state name expansion logic
  • Pronunciations for British Sterling and "not" sign
  • New pronunciations for Linux terms
  • Clarifications to speech.properties message
  • Fix for -dump{Multi}Audio problem in freetts app
  • Elimination of hang with JDK1.5
  • Tools specifically for importing CMU ARCTIC Voices.
  • Fix for MBROLA phoneme remapping
  • Rudimentary internationalization to FestVox import.
  • Support to build FreeTTS w/o requiring JSAPI
  • Only build tests on demand (more freedom from JUnit)

If you want to try out FreeTTS, check out the Talking clock webstart demo.

Posted on: Feb 07, 2005

Posted by: plamere

Category: Java

Permanent link to this entry

Comments:

i have a dumb question, and couldnt find the answer in my quick browse in the FreeTTS page. What is the effect of the language in FreeTTS? lets say i want a turkish speech sythesis software, i can provide stree points, syllabels etc, would it be enough? or core has to change for that?

Posted by ahmet on February 07, 2005 at 10:22 PM EST #

Currently FreeTTS supports only english. Adding support for new languages is possible. It typically includes a new dictionary, new unit data, and new sets of statistically trained classification data for proper parsing, phrasing, pausing, and prosody.

This document describes the steps to add a new voice in a new language.

Posted by Ahmet on February 08, 2005 at 05:17 AM EST #

A very plesant talking clock. " Almost an Idea of an old Wood speaker desktop radio, with just this application. " A proxsimity sensor to tell you the time when you come in to the room. And to keep you company. a burgular would certainly do a double take, nearing your apartment door and hearing the announbcment. thanks developers; it just keeps on getting better rtg.

Posted by BOMBOVA on March 20, 2005 at 02:58 AM EST #

i want to build an application using FreeTTS. where a midp client will send request to FreeTTS server to synthesize the text (given by client). since the server processes the text and sends the audio stream back to the client, is it possible to have a midp client which will give text to server and take the stream audio back? how will the midp client get request from server (which is audio) and play it using AudioPlayer? or can i modify the server code to just take the text as input, process it and speak it out without sending it back to client?

Posted by newbie on March 21, 2007 at 04:00 PM EDT #

Post a Comment:

This blog copyright 2010 by plamere