惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

C
Comments on: Blog
S
Schneier on Security
Microsoft Azure Blog
Microsoft Azure Blog
T
Tor Project blog
V
Visual Studio Blog
C
CXSECURITY Database RSS Feed - CXSecurity.com
Threat Intelligence Blog | Flashpoint
Threat Intelligence Blog | Flashpoint
Spread Privacy
Spread Privacy
月光博客
月光博客
罗磊的独立博客
Cisco Talos Blog
Cisco Talos Blog
P
Privacy International News Feed
T
Tenable Blog
阮一峰的网络日志
阮一峰的网络日志
AWS News Blog
AWS News Blog
T
ThreatConnect
博客园 - 三生石上(FineUI控件)
Recorded Future
Recorded Future
Hugging Face - Blog
Hugging Face - Blog
T
Tailwind CSS Blog
博客园 - 叶小钗
CTFtime.org: upcoming CTF events
CTFtime.org: upcoming CTF events
A
Arctic Wolf
L
LINUX DO - 最新话题
美团技术团队
大猫的无限游戏
大猫的无限游戏
I
Intezer
博客园 - 司徒正美
酷 壳 – CoolShell
酷 壳 – CoolShell
量子位
小众软件
小众软件
T
Threatpost
V
V2EX
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
宝玉的分享
宝玉的分享
The Register - Security
The Register - Security
Project Zero
Project Zero
J
Java Code Geeks
Cyberwarzone
Cyberwarzone
IT之家
IT之家
MyScale Blog
MyScale Blog
T
Threat Research - Cisco Blogs
T
The Blog of Author Tim Ferriss
腾讯CDC
S
SegmentFault 最新的问题
F
Fox-IT International blog
S
Security Archives - TechRepublic
Last Week in AI
Last Week in AI
G
GRAHAM CLULEY
M
MIT News - Artificial intelligence

herrkaefer

"Vibe planning \u003e vibe coding" "Anything to Markdown" "Built anocus: anonymous commenting for static sites" About - herrkaefer "日记与小说 -- AI 续写小说欣赏" "Any-podcast: from newsletters to a podcast" 关于 Tools 和 Skills 的一点感想 "Realtime monitoring of ComEd hourly price" "Introducing SwiftEdgeTTS" "Thoughts on the philosophy of building AI-native apps" jelly鼻屎 等饭的人 "Use home assistant to motivate my kid to brush teeth" "Migrated Blog to Hugo and Cloudflare Pages" "Easy Aspen monitoring for Chicago parents" "Introducing HabitBuilder: A simple Telegram bot for habit tracking" 鼓捣 "Open folder or file with Sublime Text from Finder toolbar" "Python dev workflow on macOS" "Create new text file from Finder toolbar" "Uno reinvented for 3-year-old kids" Uno变身儿童数字游戏 自动转发Twitter到微博 Handle annoying operations of objects in Realm DB Move Jekyll blog to Ubuntu VPS Introducing Mole Note taking without note taking app Deploy Python web application on Ubuntu server Setup Shadowsocks / VPN on Ubuntu Server Linode Notes - Basic Setup CLASS Style Adapted for Embedded Systems psycopgr Tutorial pgRouting Notes PostgreSQL Notes 阿城三王 这一年,这一把日子 另一面的发现——读《坟》 定理 封面与腰封 Google book下载 lulu最新写真出炉 The Big Bang Theory第三季 自拍婚纱照1 日全食 期待动画片 《麦兜响当当》动画电影主题曲 转:饶毅--“杂志拜物教”:何时发Cell Nature Science 论文害你 转:饶毅--提醒年轻人:何时SCI害你? 西安 3d打印机 twitter Dropbox 刷牙 贴几张照片 6156167 永久和凤凰 老板的想法 原来奥巴马也是个朗读者 应邀发Freeware List 2.0 史上最能睡的淘宝老板 至少出名的效果是达到了 错怪了msn 独立游戏节2009 114 馒头 Crayon Physics Deluxe 2008,2009 盖章记 小虎队附身许巍 怎么给word文档加索引:排序问题 怎么给word文档加索引Q&A 怎么给Word文档加索引 教我如何不疯掉 二则 哦!报告 P 蓝天 萧翰 lm 故宫印象 转:美国历任总统像 time can kill itself 建议,只是建议哦 奥地利行记3 奥地利行记2 奥地利行记1 叶子 GayBoy 天使教你扔frisbie 门徒因何面容愁? 手机教堂 丝竹管弦之盛 残奥 争座位 秋意浅
"Made MicPipe: a simple voice input tool using ChatGPT dictation"
2026-01-28 · via herrkaefer

image

GitHub repo: https://github.com/herrkaefer/micpipe

Voice input is getting popular again (thanks, vibe coding). I tried a few apps (spokenly, 闪电说, Typeless, etc.) and couldn’t decide. Then I realized: the voice dictation inside the ChatGPT web app is already really good. It’s fast, accurate, handles Chinese + English mixing very well.

So I had a thought:

Can I use that as a system-level “voice input method”, and use it for any app?

That thought turned into this little tool: MicPipe.

The idea / workflow is simple:

[You start recording] → MicPipe presses the dictation button in the ChatGPT chat box → [You stop recording] → it presses stop dictation → grabs the text → switches back to your original app → pastes the text.

This solves my problem of choosing.

A few notes:

One hotkey, two modes

My “original invention” 😆

  • Hold Fn to talk, release to finish and paste → Hold mode
  • Tap Fn to start, tap again to finish and paste → Toggle mode

I’ve seen many apps use two separate shortcuts for “hold to talk” and “toggle on/off”… it doesn’t have to.

The hotkey is customizable:

image

ChatGPT & Gemini

Both are supported. But honestly, Gemini’s dictation quality isn’t as great as ChatGPT yet.

AI Pipe

image

You can send the dictation result into a preset prompt, and then paste the processed output back into the original input box.

There are five preset prompt slots, all editable.

Examples:

  • Fix grammar / typos (Grammar Fix)
  • Rewrite in a more email-like tone (Email Writer)
  • Turn my messy requirements into cleaner “instructions for an AI to code” (Vibe Coder)

Of course, doing a second step makes it slower – This is expected. This can’t beat a cloud workflow that returns a combined result at once.

Not cross-platform

I tried:

  1. CDP (Chrome DevTools Protocol) — didn’t work. With CDP, ChatGPT couldn’t log in.
  2. Playwright — also no. In headless mode the microphone can’t be enabled.

So I used AppleScript.

MicPipe opens a “dedicated but minimal” Chrome window for the dictation flow. I place it outside the screen so it doesn’t bother me.

Stability still needs work. Star / PR / fork welcome.