> ## Documentation Index > Fetch the complete documentation index at: https://docs.trugen.ai/llms.txt > Use this file to discover all available pages before exploring further. # Basic TypeScript Example > Get your first AI avatar running using a TypeScript Express server. This guide will walk you through setting up a minimal example of an interactive AI avatar using a backend built with TypeScript and Express. ## Prerequisites * A TruGen API key (get one [here](https://app.trugen.ai/api-keys)) * A TruGen Agent ID (create and get one [here](https://app.trugen.ai/teammate-library)) * Node.js installed on your machine * A modern web browser with microphone access ## Project Setup Initialize a new project and install the required runtime and development dependencies: ```bash theme={null} npm init -y npm install express dotenv @trugen/js-sdk npm install -D typescript ts-node @types/express @types/node ``` Create a `tsconfig.json` file in the root of your project: ```json theme={null} { "compilerOptions": { "target": "ES2020", "module": "commonjs", "lib": ["ES2020"], "strict": true, "esModuleInterop": true, "skipLibCheck": true, "outDir": "dist", "rootDir": "." }, "include": ["server.ts"], "exclude": ["node_modules", "dist"] } ``` Set up the following directory layout: ```text theme={null} project/ ├── .env ├── server.ts ├── public/ │ └── index.html ├── tsconfig.json └── package.json ``` Create a `.env` file and add your API key and Agent ID: ```env theme={null} TRUGEN_API_KEY=your_trugen_api_key AGENT_ID=your_agent_id ``` Never expose your API key in the browser. The server reads it from `.env` and returns only a short-lived session token to the client. Create `server.ts` — this fetches the session token on the backend to keep your credentials secure: ```typescript theme={null} import express, { Request, Response } from "express"; import path from "path"; import dotenv from "dotenv"; dotenv.config(); const app = express(); app.use(express.static("public")); app.get("/token", async (_req: Request, res: Response): Promise => { try { const response = await fetch("https://api.trugen.ai/v1/auth/conversation", { method: "POST", headers: { "Content-Type": "application/json", "X-API-Key": process.env.TRUGEN_API_KEY as string, }, body: JSON.stringify({ agentId: process.env.AGENT_ID, }), }); const data = await response.json() as { token: string }; res.json({ token: data.token }); } catch (error) { console.error(error); res.status(500).json({ error: "Failed to create session token" }); } }); app.listen(3000, () => { console.log("Server running at http://localhost:3000"); }); ``` Create `public/index.html`. The frontend runs plain browser JS and imports the SDK from esm.sh directly, so no TypeScript compilation is required for the client side: ```html theme={null} TruGen SDK Test (TS)

TruGen SDK Test (TypeScript Server)



``` Start the server with `ts-node` for quick testing without a separate build step: ```bash theme={null} npx ts-node server.ts ``` Open `http://localhost:3000` in your web browser, allow microphone access, and click **Connect**.