This isn't just a tutorial about building a project — it's about how to collaborate with an AI agent to build it together.

Created by Ethan Sijun Huang

[email protected]

What We're Building

A real-time interactive system: speak a poem into your microphone, and an AI-generated image appears on screen.

Tech Stack:

• Claude Code — AI coding agent (the "co-builder")
• TouchDesigner 2024 — Real-time visual programming environment
• OpenAI Whisper API — Speech-to-text
• OpenAI DALL-E 3 API — Text-to-image generation

Final Workflow:

🎤 Speak a poem → 📝 Whisper transcribes → 🎨 DALL-E generates image → 🖥️ Display in TouchDesigner

Demonstration

https://youtu.be/xkVNx9h8YCc

Part 0: Installing Claude Code

Before anything else, you need Claude Code — the AI agent that will help you build this entire project.

What is Claude Code?

Claude Code is Anthropic's official CLI (command-line interface) tool for Claude. It's an AI agent that can read files, write code, run commands, and help you build projects interactively — all from your terminal.