Tag
Someone attempted to push Claude Opus 5.5 to its limits using Houdini and concluded there is no ceiling in sight — the entire scene, including final color grading, was completed via iPhone voice commands with MCP, and rendered for 50 hours on an RTX 5090, showcasing the enormous potential of AI-driven creative workflows.
Point and Yap 是一款免费开源的 Mac 小工具，双击 Control 键后即可对着屏幕上的元素说话，将语音与所指内容通过 MCP 传输给编码 agent。
walkai-talkai 让你通过手持对讲机的 PTT 按键免提与 AI 编码代理对话，语音在 Mac 本地用 Whisper 转写后输入到 Cursor、Claude Code 等工具，再以神经语音通过无线电回放，音频不离开本机。
Harness by Autonomous 推出了一款开源的编码代理指挥中心，可在 Mac 和 Linux 上统一管理 Claude Code、Codex、Hermes 等各类编码代理，并支持终端、桌面应用以及 iOS/Android 语音应答，还扩展到 CAD、电路、机器人等领域。
m’kay is an open-source tool that allows voice interaction with multiple AI coding agents like Claude Code, Codex, and Cursor from your phone or browser, with local processing and user confirmation for data transmission.
RemoteConsole is a mobile SSH terminal for developers to manage and steer AI coding agents like Claude Code or Codex from their phones, with features for NAT traversal, voice control, and an SFTP browser.
Shootsolo 2.0 is an updated voice-controlled camera and teleprompter app for solo creators, featuring hands-free recording, AI editing tools, and offline functionality on iOS and Android.
A tweet discusses how voice-controlled computer use may become mainstream in 6-12 months, highlighting an example of a fast voice command tool called Jev for Mac.
TypeDash is a desktop application that lets users control their computer and dictate text via voice commands, featuring app launching, web search, and optional ChatGPT-powered cleanup for speech recognition.
Proto-Mind is a floating AI workspace for Mac that integrates AI chats, websites, and documents with features like parallel task execution, model selection, voice control, and editable long-term memory.
AutoBot is an open-source agentic harness that enhances AI task completion by 18.5% over baseline on benchmarks like OSWorld 2.0 and AssistantBench, featuring self-improvement, hierarchical memory, and live voice control for complex workflows.
Apple's iOS 27 update significantly improves Siri with Google's Gemini models, enabling complex requests and on-screen context understanding.
Diurnal is a native Mac app for quick day planning, allowing users to capture thoughts via keyboard shortcuts or voice commands, integrate with Google Calendar, and use it offline.
Grimo AI is an iOS app that uses AI to convert spoken or typed sentences into tasks, calendar events, and notes, simplifying personal organization.
Eric Zakariasson announces the addition of dictation and voice skills to apps via Cursor plugins, enabling real-time voice interaction with Grok and text-to-speech features.
Qoder now offers a mobile app that pairs with its desktop version, allowing users to speak their ideas, control actions from the lock screen, and review results on their phone.
Ugreen has launched its HomeAgent smart home platform, featuring local AI processing and storage for enhanced privacy and eliminating subscription fees.
The tweet promotes a video about Jamcat, a voice-controlled generative music software that integrates voice UI deeply, potentially revolutionizing music creation interfaces.
Don Yansen founded Kiwi Health, a voice-controlled wristband for seniors, inspired by MIT AgeLab research on technology use in caregiving.
Matic is a home robot that responds to voice commands and uses eye and finger tracking to locate spots on the floor, demonstrating advanced interaction capabilities.