PC Personal Voice Assistant

Meet the PC Personal Voice Assistant: a local-first, voice-driven assistant that transforms how you interact with your computer. It operates as both an intelligent knowledge source and a hands-free PC controller. You can ask it to explain complex concepts, look up live information via Google Search Grounding, or perform actions on your desktop—all while it talks back to you seamlessly via AssemblyAI's real-time WebSocket pipeline. Everything core runs locally on your PC. The auth server binds only to localhost, keeps API keys secure in a local DuckDB store, and requires no complicated deployments. It intelligently catalogs your OS and installed applications, allowing it to launch real software securely by name. Beyond simple commands, the assistant features vision-guided UI automation utilizing Gemini Computer Use, enabling it to execute screenshot-decide-act-verify loops on your desktop or browser. It functions as a sophisticated planner where multi-step goals become checkpointed, resumable plans. With built-in semantic memory, an auto-reversible undo layer, on-device openWakeWord detection, and real-time barge-in support, the assistant provides a highly fluid conversational experience. Layered security features—including prompt-injection detection, a signed tool manifest, and explicit confirmation queues for dangerous commands—ensure your machine remains safe while unlocking entirely hands-free productivity.