We just built SKI — voice coding for Claude Code, Codex and more. It's not dictation: your agent answers you out loud, like a real teammate, so you build at the speed you think. You can even bring it into a meeting to build live, or send it in your place to speak for you. It's an ambient thing that just sits on your desktop — hit a key, talk, it works. All on your machine, free. Available on Mac & Windows.
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.
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.
Three things we care about:
• 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.
• 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.
• It's local. Speech in and voice out both run on your machine. No cloud, works offline.
Free for life — Mac and Windows today, Linux next.
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?
Really interesting concept! I like that you're focusing on conversation rather than simple voice input. Curious- does it work well across longer coding sessions, or is it optimized more for quick interactions? Congrats on the launch!
The "it answers you out loud" part is the interesting design problem, not the transcription part. Push to talk is a one person at a time model. If the agent is mid-sentence explaining what it did and you realize halfway through you want to redirect it, can you interrupt and start talking, or do you have to let it finish the response before you can push to talk again? A voice interface that can't be interrupted turns into the exact bottleneck it's replacing.
How do you keep knowledge for your product? Are there LLM wikis and tools you use?
In this niche, I think it would be better to release it in Linux too. Hit me up when that comes 🙌.
Congrats on the launch! 🚀
Any plans for a Linux version? There are quite a few Linux users who'd love to try it if native support is on the roadmap.
Best of luck with the launch!
Hey its been going well so far, it pretty cool to work with. That meeting use case really came in clutch. I didn’t even think it would make that much of a difference in meetings.
the risk-scoped gate idea further down is the right instinct. review-before-send on everything just turns voice back into typing with extra steps.
Voice coding makes total sense for describing intent, but a lot of my actual prompts to Claude Code are things like 'move the logic from RecurringContent.tsx into a new useRecurring hook in hooks/recurring' where exact file paths and camelCase names matter and saying them out loud is clunky. Does SKI do anything smart with recognizing code identifiers and paths specifically, or is that where the review-before-send step earns its keep?
The "it answers back" part is the bit that actually matters. Dictation just moves typing to your mouth, you're still sitting there reading output. Having the agent talk back changes the whole loop.
The ambient bit is smart too. Half the reason I don't use voice tools is the ceremony of opening one first.
Going to give this a proper run this week. Congrats on shipping.
Really love the concept and I always hated how Claude just took the voice input but not speak back. Now… I’m gonna try it in Claude code.
Quick question do we have to run some kind of voice model for this or does it come with pre-packed
Congrats on the launch. Just a quick question, how does the push-to-talk handle noisy environments or mechanical keyboard chatter during active coding?
This is definitely a valuable addition to the coding community. I currently use whisper flow for coding but I am wondering how this differs and maybe how it will be better given that it's tailored toward programmers.
Super cool! How does it compare to using WisprFlow on say Claude Code or OpenRouter
I run Claude Code all day as a solo dev and the thing that actually breaks my flow is drifting to another tab and not noticing when it's done or sitting blocked on an approval. Voice-out closing that loop is the part I actually want — does it speak up when the agent is waiting on me, or only when a task finishes?
Congrats on the launch. Assuming this can work with local models since you said it works with Hermes?
This is great! I tried Mac dictation and built in Claude dictation but neither allows for full "away from screen" experience.
Is it possible to call the agent? So that I could talk to it remotely? I guess it's the "bring it to the meeting" that was mentioned?
About SKI on Product Hunt
“Free voice coding for Claude Code, Codex and more”
SKI launched on Product Hunt on July 30th, 2026 and earned 594 upvotes and 316 comments, earning #1 Product of the Day. We just built SKI — voice coding for Claude Code, Codex and more. It's not dictation: your agent answers you out loud, like a real teammate, so you build at the speed you think. You can even bring it into a meeting to build live, or send it in your place to speak for you. It's an ambient thing that just sits on your desktop — hit a key, talk, it works. All on your machine, free. Available on Mac & Windows.
SKI was featured in Productivity (657.5k followers), Developer Tools (517k followers) and Artificial Intelligence (475.2k followers) on Product Hunt. Together, these topics include over 340.2k products, making this a competitive space to launch in.
Who hunted SKI?
SKI was hunted by Anand Balakrishnan. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how SKI stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Anand Balakrishnan
Hey Product Hunt 👋 I'm Anand, one of the makers.
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.
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.
Three things we care about:
• 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.
• 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.
• It's local. Speech in and voice out both run on your machine. No cloud, works offline.
Free for life — Mac and Windows today, Linux next.
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?