📰 2026-03-11 01:30 更新
🔸 Show HN: RunAnwhere – Faster AI Inference on Apple Silicon / Show HN ： RunAnwhere – Apple Silicon上更快的人工智能推断
🔗 Show HN: RunAnwhere – Faster AI Inference on Apple Silicon
🔥 11 points
原文:
Talk to your Mac, query your docs, no cloud required. RCLI is an on-device voice AI for macOS. A complete STT + LLM + TTS pipeline running natively on Apple Silicon — 43 macOS actions via voice, local RAG over your documents, sub-200ms end-to-end latency. No cloud, no API keys. Powered by MetalRT, a proprietary GPU inference engine built by RunAnywhere, Inc. specifically for Apple Silicon. Real-time screen recordings on Apple Silicon — no cloud, no edits, no tricks. Voice Conversation
译文:
与您的Mac通话，查询您的文档，无需云。RCLI是适用于macOS的设备语音AI。完整的STT + LLM + TTS管道在Apple Silicon上本地运行—通过语音执行43个macOS操作，在您的文档上执行本地RAG ，端到端延迟低于200毫秒。无云，无API密钥。由MetalRT提供支持， MetalRT是由RunAnywhere, Inc.专门为Apple Silicon构建的专有GPU推理引擎。Apple Silicon上的实时屏幕录制—无云， 无需编辑，无需技巧。语音对话
自动更新 · 正文抓取 · 双语翻译