Build real-time conversational AI experiences using Amazon Nova Sonic and LiveKit
Machine Learning Blog
This article discusses how Amazon Nova Sonic and LiveKit enable developers to build real-time conversational AI voice applications with simplified infrastructure and low-latency performance.
- Amazon Nova Sonic is a state-of-the-art speech-to-speech foundation model for real-time conversational AI
- Integrates with LiveKit's WebRTC framework to simplify audio pipeline management
- Supports multiple speaking styles, expressive voices, and function calling
- Provides a step-by-step guide for developers to set up a local voice AI agent using Python
- Removes complexity of managing audio streaming and signaling protocols
The solution enables developers to focus on building engaging conversational experiences by handling complex real-time audio infrastructure automatically.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Dec 2
2025
2025
Announcing Amazon Nova 2 Sonic for real-time conversational AI
Apr 8
2025
2025
Introducing Amazon Nova Sonic: Human-like voice conversations for generative AI applications
Apr 7
2026
2026
Building real-time conversational podcasts with Amazon Nova 2 Sonic
Dec 2
2025
2025
Introducing Amazon Nova 2 Sonic: Our new speech-to-speech model for conversational AI
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.