JVoiceXML http://jvoicexml.sourceforge.net is a free VoiceXML interpreter for JAVA with an open architecture for custom extensions. Demo implementation platforms are supporting JAVA APIs such as JSAPI and JTAPI.
VoiceXML is an implementation of VoiceXML 2.1, the Voice Extensible Markup Language, specified at http://www.w3.org/TR/voicexml21 as an extension to VoiceXML 2.0, specified at http://www.w3.org/TR/voicexml20/. VoiceXML is designed for creating audio dialogs that feature synthesized speech, digitized audio, recognition of spoken and DTMF key input, recording of spoken input, telephony, and mixed initiative conversations. Major goal is to have a platform independent implementation that can be used for free.
The new release JVoiceXML 0.7.5.GA can be downloaded from http://sourceforge.net/projects/jvoicexml/files/
Changes to JVoiceXML 0.7.4.GA include several bugfixes and feature enhancements. Most noteworthy are bugfixes in the cleanup of resources and initial support for Nuance compiled grammars. Moreover, a new implementation platform was introduced to have the synthesizer replaced by MARC, a talking head by LIMSI http://marc.limsi.fr