AWS 教程:用 AgentCore 与 Nova Sonic 构建语音旅行助手
AWS Machine Learning Blog 发布教程,演示如何在 Amazon Bedrock AgentCore 上部署一个语音旅行客服:用 Amazon Nova 2.5 Sonic 做实时语音识别与语音回复,用 Strands Agents 构建智能体,并通过 AgentCore Gateway 以 Model Context Protocol 调用航班、座位、会员等后端服务,用 Bedrock Knowledge Bases 结合 RAG 回答行李、退改签等政策问题。文中称 Nova 2.5 Sonic 具备更强的工具调用与多步任务能力,并支持双向流式、异步工具调用、延迟掩饰与自然打断。整套方案用 AWS CDK 一键部署,前端托管在 Amplify。
它给出了一套可直接复用的托管语音智能体参考架构,说明把实时语音模型接进企业既有后端所需的组件已经标准化。
Airlines already have apps and websites where travelers check flights, pick seats, and manage bookings, and adding a natural voice layer opens those tasks to spoken requests. With this voice layer, a traveler can change a seat or check a delay by speaking, without leaving the app or navigating through screens. Building it requires careful engineering on several fronts. You stream audio in both directions and hold the thread of a conversation across many turns. You also reach your existing backend systems without coupling the agent tightly to them, and you scale when traffic spikes before a holiday weekend.
This post shows you how to add a voice travel concierge to an airline application, built on three managed services. Amazon Bedrock AgentCore is an agentic platform for building, deploying, and operating AI agents securely at scale with your choice of framework and model. Amazon Nova Sonic on Bedrock is a speech-to-speech model for real-time voice. Amazon Bedrock Knowledge Bases is a fully managed retrieval augmented generation service that grounds answers in your own documents. A traveler speaks, and the concierge pulls up their itinerary, changes a seat, updates a meal preference, answers a policy question, and connects them to a live agent on request.
#AWS#Amazon Bedrock AgentCore#Amazon Nova Sonic#Amazon Bedrock Knowledge Bases#Strands Agents#Model Context Protocol