This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey. We are aware some courses have accessibility limitations and are working to address. If you require accommodation, please contact AWS Training and Certification Customer Support.
Learners can gain an understanding of how to build production-grade, real-time voice agents by combining Stream's Vision Agents open-source framework with Amazon Bedrock and Amazon Nova 2 Sonic. The course covers orchestrating speech-to-speech models, managing low-latency audio streaming, and handling connection lifecycle challenges. Participants will explore code examples and advanced capabilities such as function calling, automatic reconnection, and multilingual voice support -- equipping them to deliver natural, responsive voice experiences across web, mobile, and desktop applications in minutes rather than months.
