Vishal goyal@CodeVishal-17

Axon Voice is a voice-first AI desktop agent built to let people interact with their computer naturally through conversation. Instead of only answering questions, Axon can understand a spoken request, inspect the computer, take controlled actions, and verify the result. Axon uses AssemblyAI Voice Agents as its real-time voice interface, while the local Axon control plane handles computer interaction, permissions, safety policies, and verification. It can discover and launch installed Windows applications, focus applications, read accessible UI elements, interact with controls, open the user's default browser, and perform multi-step tasks. The system is designed around a simple loop: Observe → Understand → Check permissions → Act → Verify. Consequential actions can require explicit user approval, while sensitive information such as API keys is protected from being exposed or typed into applications. Axon also demonstrates computer interaction through Microsoft Paint, where a spoken request such as “Open Paint and draw a house” causes Axon to progressively create the drawing on the real Paint canvas and verify the result. The goal is to move beyond the traditional chatbot experience toward a voice interface for the computer itself one that can understand what the user asks, interact with the applications they already use, and remain transparent about what it can and cannot verify.

🌎 Online Hackathon | 💻 Month-long challenge | Dates: Sep 1–30, 2026 | 🏆 $10,000 Prize Pool ($5k cash + $5k in AAI credits) A month-long online challenge run by lablab.ai together with AssemblyAI, the Voice AI infrastructure company for builders. Every participant builds on AssemblyAI. You can join at any point — registration stays open for the whole build window, so you can start on day one or pick the project up halfway through and still submit. 🌍 Fully online hackathon. Join and build from anywhere in the world.