Dev Radar
Support
LiveUpdated 2026-10-30 21:12 UTC

用语音输入回消息,说完一看满屏「嗯」「那个」口头禅,还得一句句删,最后还不如直接打字。

用语音输入回消息,说完一看满屏「嗯」「那个」口头禅,还得一句句删,最后还不如直接打字。 谷歌 Gemini 团队最近开源了一个语音输入工具:Jot ,用的是 Gemini 3.5 Transcribe 转写模型。 按住 fn…

This is a dev post classified by AGK Intelligence as Mobile & desktop (a tool drop), kept by the Dev Radar because it carries real work, not commentary.

用语音输入回消息,说完一看满屏「嗯」「那个」口头禅,还得一句句删,最后还不如直接打字。 谷歌 Gemini 团队最近开源了一个语音输入工具:Jot ,用的是 Gemini 3.5 Transcribe 转写模型。 按住 fn 说话,松手后文字就出现在光标所在的地方,标点加好,口头禅去掉。若说到一半改了主意,它只写最后那个说法。 GitHub:http://github.com/google-gemini/jot-gemini-transcribe-macOS 录音从按下那一刻就存进硬盘,软件崩了、电池没电,下次打开还能找回来。没网时先排着队,联网后自动补上。 人名、产品名可以加进词典,跟着音频一起发给模型,像 Kubernetes 这种词就不会被听错了。 要自己填一个 Gemini API Key,声音直接发给 Google,中间没有别的服务器,也有免费额度。

Posted by GitHubDaily (90.5k followers) 2 days ago · 96 likes · 15.4k views · view the original post on X. Kept by the Dev Radar as Mobile & desktop. Tools mentioned: jot-gemini-transcribe-macos.

More dev work like this

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 21:12 UTC. Full method.