YapSketch 讓用戶把語音指示和螢幕標註交給編碼 Agent

Hey guys!

I made YapSketch to make it easier for me to communicate my feedback and ideas to coding agents.

I used to dictate in one app, take a screenshot, open another app to draw on it, then try to explain it all in the prompt. Now I hit a hotkey, talk, and draw on my screen. When I stop, I paste it into Claude Code (or Codex, Cursor, whatever) and the agent gets what I said plus a picture of each thing I pointed at.

It fully replaced Wisprflow for me, and it cut down the back and forth a lot. I can jam a ton of feedback into a single recording, and the agent gets all of it in one go.

It's 100% free and open source, and speech is transcribed locally on your machine.

If you're familiar with Jev, you can connect it in settings (sign in with Opper, Openrouter, or add your TypeSafe key) and it gets a lot smarter by matching what you said and your intent to what you drew and picks the best frame for each point. It works just fine without it too.

Website: https://yapsketch.com/

Github: https://github.com/farouqaldori/yapsketch

Star the repo if you like the app and I hope that you enjoy using it!