构建和部署全栈语音AI代理的实践课程

这是一门关于构建和部署全栈语音AI代理的实践课程。您将学习如何使用LiveKit、n8n和MCP在AWS上创建一个具备实时语音交互和自动化工作流的完整系统。课程从在AWS EC2上配置Ubuntu服务器开始，接着集成LiveKit实现实时通信，配置OpenAI和Deepgram API，并构建AI代理。然后您将连接n8n实现工作流自动化（如预约安排和邮件通知），并通过MCP处理多通道任务。后端完成后，您将使用React/Next.js构建前端，通过NGINX和SSL证书确保安全，并使用PM2和Systemctl管理应用部署。课程结束时，您将拥有一个在云环境中完全可用的、安全的自动化语音AI代理。

制作人：Shikhar Verma
MP4格式 | 视频：h264，1280×720 | 音频：AAC，44.1 kHz，2声道
级别：所有级别 | 类型：在线学习 | 语言：英语 | 时长：63节课（2小时41分钟） | 文件大小：1.2 GB

Full-Stack Voice AI Agent with LiveKit, n8n and MCP on AWS。Build and deploy a real-time Voice AI Agent using LiveKit, n8n, MCP, and AWS with full automation and integration. Build your own end-to-end Voice AI Agent using LiveKit, n8n, and MCP — hosted on AWS.This course guides you step by step in developing a real-time intelligent Voice AI system with automation, voice interaction, and web integration.You’ll begin by setting up and configuring an Ubuntu server on AWS EC2, preparing your Python environment, and integrating LiveKit for real-time communication. Then, you’ll connect your AI Agent with n8n for workflow automation and MCP for multi-channel task handling — enabling features like voice-based appointment booking, email notifications, and calendar scheduling.Once the backend is complete, you’ll build and deploy a React/Next.js frontend, secure it using NGINX and SSL certificates, and manage your application using PM2 and Systemctl .By the end of the course, you’ll have a fully functional, secure, and automated Voice AI Agent deployed in a cloud environment.IntroductionWhat You’ll LearnSystem Setup on AWS EC2Set Up and Configure an Ubuntu Server on AWS EC2Connect to Your AWS EC2 Instance Using MobaXtermSet Up the Project DirectorySet Up Python Virtual EnvLiveKit Essentials: Setup, API Keys, and ConfigurationWhat is Livekit?Why LiveKit for Our AI Project?LiveKit Documentation OverviewInstalling LiveKit and Its DependenciesCreate LiveKit AccountSet Up Your OpenAI API KeyDeepgram Account & API SetupLiveKit Plugins SetupBuild and Test Your AI Agent in LiveKitBuild and Run the Agent Script (agent)Access via LiveKit PlaygroundIntegrate prompts. py with AI Agent How prompts. py Works in the ProjectAdd Task DefinitionDefine Session InstructionUpdate agent. py Based on prompts. pyRun Voice AI AgentIntegrating AI Avatars with Your Voice AI AgentWhat is an AI Avatar?How AI Avatar Integration WorksTavus Account & Persona SetupAdd Tavus Persona IDs and APIs to .envAdd Avatar in agent. pyRerun Voice AI AgentTest AI Avatar via LiveKit PlaygroundConfigure AI Agent as a Systemctl ServiceCreate a Systemctl Service File for the Voice AI Agent Integrating LiveKit AI Agent with a Custom React FrontendIntegrate with React FrontendClone the React Project and Install Node.jsRun the React App in Development ModeAccess the React Frontend via EC2 Public IPDeploy Next.js Frontend to Production Using PM2Overview of Next. js Production DeploymentBuild & Fix Build IssuesRun with PM2Verfiy deploymentPurchase a Domain and Configure DNS RecordsPurchase a Domain from GodaddyConfigure A RecordsSecure the Application using NGINX and Let’s Encrypt SSLOverview of the ProjectSet Up and Configure NGINXInstall Certbot Let’s Encrypt to Enable HTTPSVerify HTTPS Access Auto Renew SSL CertificatesIntegrating AI Agent with n8n and MCPOverview: AI Agent with n8n and MCPOverview of n8nWhat is MCP?How It Works: AI Agent – MCP – n8n FlowModify Agent Configuration for MCP ServerAdd an MCP Server Trigger Node in n8nAdd a Google Calendar Node in n8nFix Google Calendar AccessAdd Another Google Cal NodeAdd MCP Server URL in .env File on ServerRestart Agent and Verify n8n IntegrationModify prompts. py for Appointment Booking FlowBook an Appointment with Voice AI AgentBooking Validation: Prevent Double AppointmentsAI Agent: Book the Appointment and Send Email NotificationAdd a Gmail Node in n8n workflowSet the Parameters in Gmail Node in n8nModify prompts. py for Email NotificationsTest the Voice AI Agent: Book Appointment and Send Email NotificationLast Lecture。What you’ll learn
Build and deploy a full-stack Voice AI Agent using LiveKit, n8n, and MCP on AWS.
Set up and configure an Ubuntu server on AWS EC2 for development.
Create and manage virtual environments for Python projects.
Integrate LiveKit for real-time voice communication in AI systems.
Configure and connect OpenAI and Deepgram APIs for voice interaction.
Build and run the AI Agent, and test it via the LiveKit Playground.
Integrate prompts. py with the AI Agent for task and session control.
Add and test AI Avatars using Tavus for realistic voice experiences.
Deploy and manage the AI Agent as a system service using Systemctl.
Build and deploy a React/Next.js frontend and connect it to the backend.
Secure your AI application using NGINX and Let’s Encrypt SSL.
Automate booking workflows and email notifications with n8n.
Integrate Google Calendar and Gmail nodes within n8n workflows.
Configure PM2 to manage and monitor Next.js production deployments.
Test, verify, and troubleshoot AI booking and automation flows end to end.

Requirements
Basic understanding of Python programming and command-line usage.
A free or paid AWS account to create and manage EC2 instances.
Basic knowledge of AI tools or APIs like OpenAI and Deepgram (optional).
Enthusiasm to learn, explore, and build a real-time Voice AI system from scratch — beginners are welcome!