MaxMBROLA: A Max/MSP MBROLA-based tool for real-time voice synthesis

In this paper, we present the first step of a project that is able to perform both speech and singing synthesis controlled in real-time. Our aim is to develop a flexible application allowing performers to produce complex and versatile singing - as well as speech - articulations. Thus, we have adapted an existing speech synthesizer, the MBROLA software, to real-time singing constraints. The work presented in this paper concerns the integration of the MBROLA speech synthesizer into the Max/MSP real-time environment through the development of an external object. We present real-time control functions of the object and discuss its limitations. We further discuss about perspectives in the development of MBROLA-based computer music applications.