Natural human interaction is highly dynamic and responsive: interlocutors produce utterances incrementally, smoothly switch speaking turns with

virtually no delay, make use of on-the-fly adaptation and (self) interruptions, execute movement in tight synchrony, etc. We present the conglomeration of our research efforts in enabling the realization of such fluent interactions for Embodied Conversational Agents in the behavior realizer ‘AsapRealizer 2.0’ and show

how it provides fluent realization capabilities that go beyond the state-of-the-art.