From Speech to Speech: A Tale about Amazon Nova Sonic from vBrownBag

vBrownBag

Episodes

About

Reviews

Promote

From Speech to Speech: A Tale about Amazon Nova Sonic

1 hour 8 minutes Posted Nov 3, 2025 at 7:58 pm.

– Intro & catching up with Eric Wright

– Meet Dominik Wosiński & Halo Radius

– Why speech-to-speech matters

– Challenges with chatbots and customer experience

– Latency, realism, and the human connection

– Evolution of synthetic voices (“Jennifer” demo)

– Why speech is hard for computers

– Architecture of speech-to-speech systems

– Inside Amazon Nova Sonic

– AWS Bedrock integration & limitations

– Pricing, tokens, and performance

– Lessons learned from real customer projects

– Live demo of Nova Sonic in action

– Q&A and closing thoughts

0:00

1:08:06

Download MP3

Share at current time

Show notes

In this week’s vBrownBag, Principal Software Engineer Dominik Wosiński takes us on a deep dive into Amazon Nova Sonic — AWS’s latest speech-to-speech AI model.

Dominik explores how unified voice models like Nova Sonic are reshaping customer experience, DevOps workflows, and real-time AI interaction, with live demos showing just how natural machine-generated speech can sound.

We cover what makes speech-to-speech difficult, how latency and turn-detection affect conversational design, and why this technology marks the next frontier for AI-driven customer support.

Stick around for audience Q&A, live experiments, and insights on where AWS Bedrock and generative AI are headed next.

👉 Subscribe to vBrownBag for more weekly deep-dives with community experts and learn something new in cloud, DevOps, and AI every episode!

⸻

Timestamps

How to find Dom:

https://www.linkedin.com/in/dominik-wosi%C5%84ski-b27535b7/

← See all 82 episodes of vBrownBag