Tag
A demo shows GPT Realtime 2 enabling hands-free voice control of a computer, highlighting its potential as the future of operating systems.
A demonstration shows controlling a computer entirely by voice using GPT-Realtime 2.0, showcasing a hands-free operating system interface.
Fulloch V2 is an open-source local voice assistant that integrates with Home Assistant and Obsidian, using Qwen models for ASR/TTS, with features like semantic note search and long-term memory.
We gave a Reachy Mini robot a real-time voice brain using GPT Realtime, allowing it to hear, see, talk, and physically react via motion tools. The project is open-source on GitHub.
Apple announces new AI-powered accessibility features for iPhone, Mac, and Vision Pro, including on-device speech recognition for uncaptioned videos and enhanced image descriptions.
Apple announced new accessibility features powered by Apple Intelligence, including enhanced VoiceOver and Magnifier with image exploration and natural language queries, improved Voice Control, on-device auto-generated subtitles, and Apple Vision Pro wheelchair control. These updates are coming later this year.
A guide on setting up voice control on Android and iOS to perform various tasks hands-free, covering apps like Voice Access and built-in accessibility features.
Shadow is an AI-powered tool that enables computer screen and voice control with custom automation capabilities.
An open-source spy-satellite simulator that visualizes real-time global data such as aircraft, ships, and satellites in a photorealistic 3D browser interface, with voice control and public data sourcing.
This video demonstrates using ChatGPT's voice feature to quickly compare and refine recipe versions in a cooking workflow, highlighting seamless AI integration in real-time tasks.