{
  "id": 6641107,
  "title": "Jetson + ROS 2 + Voice AI: Build a Robot You Can Talk To",
  "url": "https://urgent.news/2026/09/10/jetson-ros-2-voice-ai-build-a-robot-you-can-talk-to",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-10T20:29:27.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/vmodal_ai/jetson-ros-2-voice-ai-build-a-robot-you-can-talk-to-2k37"
  },
  "original_language": "en",
  "account": "This article provides a step-by-step guide to building a voice-commandable robot using an NVIDIA Jetson developer kit, ROS 2, and voice AI technology. The tutorial outlines the architecture, prerequisites, and steps to set up the development environment, create a ROS 2 workspace and package, understand the data flow, publish a simple ROS 2 message, add the main AI/robot component, logging and diagnostics, safety measure, Flutter integration, testing, optimization, and reproducibility. It emphasizes the importance of separating responsibilities, validating commands, and ensuring safety at every layer before connecting Flutter for operator control.",
  "summary": "Jetson + ROS 2 + Voice AI: Build a Robot You Can Talk To Build a voice-command architecture: microphone → speech-to-text → intent extraction → safety validation → ROS 2 command → robot action → text-to-speech response. Keep the language model away from direct motor control. Every generated action should pass through deterministic validation and safety rules. What You Will Build By the end of this…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}