What is it?

FreeTTS is a speech synthesis system written entirely in the Java^TM programming language. It is based upon Flite: a small run-time speech synthesis engine developed at Carnegie Mellon University. Flite is derived from the Festival Speech Synthesis System from the University of Edinburgh and the FestVox project from Carnegie Mellon University.

FreeTTS includes:

• Core speech synthesis engine
• Support for three voices: an 8khz diphone voice, a 16khz diphone voice and a 16khz limited domain voice
• JSAPI 1.0 speech synthesis support
• Extensive API documentation

What can I do with it?

Here are a few possible uses of FreeTTS:

• JSAPI Synthesizer. We provide a partial support for the Java Speech API (JSAPI) 1.0 using FreeTTS.

• Remote TTS Server. FreeTTS can serve as a back-end text-to-speech engine that works with a speech/telephony system. Our client/server demo shows how this can be done.

• Desktop TTS engine. You can use FreeTTS as your workstation/desktop TTS engine. For example, our Emacspeak demo works right out of the box with Emacspeak.

What does it sound like?

Here are some samples of what FreeTTS sounds like:

• Talking clock (16k limited-domain voice) au wav
• Talking machine(8k voice) au wav
• Talking machine (16k voice) au wav
• Susie Shines Shoes(16k voice) au wav
• Cookie Cooks (16k voice) au wav

Where can I get it?

• Browse FreeTTS documentation at SourceForge.net.
• Download the source distribution from the FreeTTS project page at SourceForge.net.

Hosted by SourceForge.net