SKI

<p>Hey Product Hunt 👋 I'm Anand, one of the makers.<br><br>We build with coding agents every day, and kept catching ourselves typing a three-sentence prompt we could've said out loud in four seconds. Thinking is fast. Typing is not.<br><br>So we built SKI. You hold the Function key, say what you want, and your agent goes and does it — then answers you out loud, like a real person. It's an ambient thing: it sits in your notch and never interrupts your flow.<br><br>Three things we care about:<br><br>• It answers. Voice input for agents already exists — it's one-directional, words in, text out. SKI closes the loop: it speaks the result back.<br><br>• It comes to meetings. Bring your coding session into a call as a real teammate and build live — or send your agent in your place to speak for you.<br><br>• It's local. Speech in and voice out both run on your machine. No cloud, works offline.<br><br>Free for life — Mac and Windows today, Linux next. <br><br>First launch for us, so hard questions are genuinely welcome. What agent do you use, and what would make you keep this open all day?</p>

hahaha, this is interesting! Now this will definitely feel like having a junior programmer with me. How are you handling accents? especially when it comes to code, where specific keywords and syntax is very important?

<p>Very promising approach - two things which made me uninstall it after a few minutes: <br><br>a) I need a way to select input and output. I have multiple mics (Jabra wireless headset for meetings, Rode mic for video recordings, some system loops etc) and also multiple outputs. (When it gets late I want that output on my headset to not annoy my family)<br><br>b) price intransparency. I understand that you need to make money. We all do. But if you tell me "free for lifetime" then I am annoyed if I see $2.50 somewhere in the fineprint of my account status. Be open about your pricing. You are competing against other tools that I pay for and I am happy to pay for a better tool</p>

<p>Dictation and voice commanding fail differently, and I think that is the interesting part here. A misheard word in dictation sits on the screen and you fix it. A misheard word here goes to something that acts.</p><p></p><p></p><p>Delete the test file and delete the rest of the file are both fluent, both plausible, and ASR will be confident about the wrong one. So confidence scores do not save you, and push to talk only controls when it listens, not what it commits to.</p><p></p><p>You speak the result back, which closes the loop after the agent has already done it. Does it ever repeat the instruction before, on the ones that are hard to undo?</p>