Voice coding for your agent
Let your coding agent
talk with you.
You talk. It builds. It answers — out loud, in a natural voice. Everything runs on your own computer; nothing you say ever leaves it. Free for life.
01 · How it works
One install. Your coding agent listens
and talks with you
From installer to conversation in under two minutes.
01
Install SKI
One installer — DMG on Mac, EXE on Windows. The setup wizard sets your mic, voice, and hotkey in a few steps — no credit card.
02
Connect your agent
One click per agent — Claude Code, Cursor, Codex, Gemini CLI, OpenClaw. A small skill your agent already understands: it hears you and answers.
03
Just talk
Say what you need out loud. The floating pill shows it heard you, your agent gets to work, and it answers out loud in a natural voice.
02 · The loop
Not dictation. A conversation.
Dictation tools stop at text-in. SKI closes the loop: replies are synthesized locally and spoken aloud — and full-duplex echo cancellation means you can interrupt it mid-sentence and be heard.
FULL-DUPLEXBARGE-INALL LOCAL
Live · see it in action
Watch SKI build a page — by voice.
Say what you want; your agent writes the code and it appears live. Here's a recipe page, start to finish — no hands.
03 · Private by design
Your voice never leaves your machine.
Sealed on your machine — inspectable, deletable, never uploaded.
A / Local models
Hears and speaks on your machine
Speech recognition and a natural neural voice, both running on-device. No audio is ever uploaded — there is nothing to upload it to.
B / Nothing hidden
No daemon, no cloud
The widget and your agent talk through plain files inside your own project. Inspect every byte; delete them any time.
C / You approve
Approve-before-send
Optional review mode: every transcript lands in an editable bubble first. Nothing reaches the agent until you hit ✓.
Now in the notch
It lives in your notch.
On Mac, SKI docks into the notch — black, flush with the menu bar, always in the same place; on a Mac without a physical notch it draws its own. On Windows it floats as a pill wherever you park it. Either way it rests as a quiet bar, then springs down into the full loop when there’s something to say.
04 · Features
Built for the way developers talk.
Every detail tuned for a real back-and-forth voice loop.
On-device, all of it
Speech-to-text and the voice both run on your own machine. Nothing you say ever leaves it.
Hears & speaks locally
Local speech in, a natural neural voice out — no cloud, works offline.
Live agent status
A green dot shows your agent is actually listening — real-time, not polled.
Full-duplex barge-in
Talk over the agent and still be heard cleanly on open speakers — no push-to-talk. It knows when you're done and sends the thought whole.
A voice per project
Bind several repos at once; each answers in its own voice and routes to whichever one you're addressing.
recipesweb-appapi-gateway
Screenshots on demand
Hit the hotkey to grab your screen — it rides along with your next spoken request. Your agent can grab one itself, too, when it needs to see what you see.
Calendar auto-join
Connect Google Calendar and SKI sends your agent — participant or silent notetaker — into a meeting or recurring series, right on time. The meeting's project just has to be connected and active.
Offline meeting recorder
Record any meeting right on your machine — your mic plus the room audio — unlimited, no bot in the call, nothing uploaded.
Smart end-of-speechFour local voicesGlobal hotkeysDraggable live-glass pill
05 · Meetings
Two ways into the room.
Record locally
Local meeting transcriber
Capture mic + system audio from Zoom, Meet, or Teams — transcribed on-device with speaker-tagged tracks.
- Unlimited recording time and retention
- Zero cloud — audio never leaves the machine
- Live transcript while the meeting runs
- Export to Markdown or plain text
Send your agent
Your agent, in the meeting
Paste a meeting URL into the widget and your coding agent joins the call as a live participant — speaking, listening, presenting.
- Agentic or notetaker — talks and helps, or silently takes notes
- Speaker-diarized transcript — tagged by who said what
- Sees the screen, screenshares, reads & sends chat
- Google Meet, Teams, Zoom — or create one from the widget
06 · Works with your agent
One skill for every agent.
Claude Codeuser + project
07 · FAQ
Plain answers to plain questions.
What is SKI?
A small floating app for your Mac or PC that lets you talk out loud to your AI coding assistant — and hear it answer in a natural voice.
What's a "coding agent"?
An AI assistant developers run alongside their code — tools like Claude Code, Cursor, Codex, or Gemini CLI. It can read files, write code, run tests, and answer questions. SKI gives it ears and a voice.
How does SKI actually work?
You speak; SKI turns it into text on your machine and hands it to your coding agent. The agent does the work — reads files, writes code, runs tests — then sends its reply back to SKI, which speaks it aloud in a natural voice and shows it in the pill or notch. A full spoken round-trip, over plain files in your own project.
What is silent mode?
Silent mode keeps SKI listening and replying, but the agent's answers appear only as text in the pill or notch — not spoken aloud (handy in a quiet room or on a call). It's the mirror of mute: mute silences your mic going in; silent silences the agent's voice coming out.
Do I have to keep the mic on the whole time?
No — mute it any time and SKI stops listening and releases the mic. On Mac you can also use the globe / fn key: tap to mute or unmute, or hold it as push-to-talk (Mac only; opt-in, needs one macOS permission).
How is this different from other voice tools?
Most are speech-to-text dictation — they put your words in a box and stop. SKI is a two-way voice loop for coding agents: it answers out loud, and it shows you what your agent is doing. Different job.
Do I need an internet connection?
No. Listening, understanding, and speaking all happen on your own machine. The only feature that touches the internet is sending your agent into a video meeting — and that's optional.
Is my voice recorded or sent anywhere?
No. Your voice becomes text on your own machine and is never uploaded. There's no cloud service listening in — there is nothing to upload to.
How much does it cost?
Free forever on Mac and Windows — register once, no credit card. Voice features and the meeting transcriber are all included. You only pay if you want your agent to join video calls through AgentCall — per minute, with free hours included.
How does SKI record meetings?
Two ways. Record locally — free, unlimited, on-device: SKI captures your mic and the meeting audio on separate tracks and transcribes them on your machine; nobody joins the call and nothing is uploaded (no per-speaker diarization in this mode). Send your agent in via AgentCall (cloud): a bot joins as an agentic participant (talks, answers, screenshares, sees the screen, reads and sends chat) or a silent notetaker, with a speaker-diarized transcript, connected to your project — the one paid feature, billed per minute with free hours included.
Where do my transcripts and sessions live?
In a built-in Transcripts window that lists your meetings, your voice sessions, and your local recordings — view, edit, copy, export (Markdown or plain text), or delete, all on your machine.
What do I need to run it?
An Apple Silicon Mac (M1 or later) on macOS 14.4 (Sonoma) or newer, or a PC on Windows 11 or 10. English today; more languages planned.
Is it the same app on Mac and Windows?
Yes — same voice loop, same agents, same on-device privacy, free for life on both. On Mac it docks into the notch (even on Macs without a physical notch); on Windows the pill floats wherever you drop it. Linux is on the list.
Just ski it.
Free for life. Register once — no card — and the voice loop, the meeting transcriber, everything on-device is yours forever. You pay only if your agent joins calls through AgentCall.
Free for life · On-device · Register once · English v1