精选理由
微软把语音识别和代码生成串起来了，对着VS Code说话就能写代码，适合想偷懒的程序员试试。
微软AI用VS Code分支构建原型，让MAI-Transcribe、MAI-Voice和MAI-Code-1-Flash三个模型协同工作。用户说出编程指令，语音转录并解析后直接生成可运行代码。此流程将语音、转录和编码模型串联成一个统一工作流。原型展示了多模型协作在开发工具中的落地可能。
原文 · Microsoft AI
What happens when speech, transcription, and codin…
What happens when speech, transcription, and coding models work together?
This prototype demo, built using a VS Code fork, showcases how MAI-Transcribe, MAI-Voice, and MAI-Code-1-Flash can work together in a unified workflow to transform spoken instructions into working code. https://t.co/z35l4fV2xQ