Tom Ouyang

Most voice interfaces today are built as a 3-way cascade system (ASR/LLM/TTS). While functional, this cascaded approach introduces latency bottlenecks, strips away non-verbal nuance, and limits emotion-aware, multi-turn dialogue. Today, we are witnessing a profound shift toward native speech-to-speech models that process audio natively from end to end. In this session, we’ll explore the exciting paradigm at Google DeepMind to train speech-to-speech models for real-time voice agents. We will cover the high-level product and research challenges of building voice agents that feel truly conversational, optimizing for fluid turn-taking and low latency while maintaining enterprise-grade intelligence. Speakers: Valeria Wu — Google DeepMind; Tom Ouyang — Google DeepMind.