From Speech to Speech - A Tale about Amazon Nova Sonic

Explore Amazon Nova Sonic, AWS's latest speech-to-speech AI model, in this comprehensive technical webinar featuring Principal Software Engineer Dominik Wosiński. Discover how unified voice models are transforming customer experience, DevOps workflows, and real-time AI interactions through detailed explanations and live demonstrations showcasing the natural quality of machine-generated speech. Learn about the fundamental challenges that make speech-to-speech processing difficult for computers, including latency issues and turn-detection mechanisms that affect conversational design. Examine the architecture of speech-to-speech systems and get an in-depth look at Amazon Nova Sonic's capabilities, AWS Bedrock integration, current limitations, pricing structure, and token-based performance metrics. Gain insights from real customer project implementations and witness live demonstrations of Nova Sonic in action. Understand why this technology represents the next frontier for AI-driven customer support and where AWS Bedrock and generative AI are headed. The session includes audience Q&A, live experiments, and practical insights for implementing speech-to-speech solutions in production environments.

Syllabus

00:00 – Intro & catching up with Eric Wright
05:00 – Meet Dominik Wosiński & Halo Radius
06:15 – Why speech-to-speech matters
10:00 – Challenges with chatbots and customer experience
15:00 – Latency, realism, and the human connection
20:00 – Evolution of synthetic voices “Jennifer” demo
25:00 – Why speech is hard for computers
30:00 – Architecture of speech-to-speech systems
40:00 – Inside Amazon Nova Sonic
48:00 – AWS Bedrock integration & limitations
52:00 – Pricing, tokens, and performance
55:00 – Lessons learned from real customer projects
57:00 – Live demo of Nova Sonic in action
01:04:00 – Q&A and closing thoughts