You talk. It builds. It answers — out loud, in a natural voice. Everything runs on your Computer; nothing you say ever leaves the machine. Free for life.
From DMG to conversation in under two minutes.
One DMG. The setup wizard sets your mic, voice, and hotkey in a few steps — no account, no cloud sign-up.
One click per agent — Claude Code, Cursor, Codex, Gemini CLI, OpenClaw. A small skill your agent already understands: it hears you and answers.
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.
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.
Say what you want; your agent writes the code and it appears live. Here's a recipe page, start to finish — no hands.
Sealed on your Mac — inspectable, deletable, never uploaded.
Speech recognition and a natural neural voice, both running on-device on Apple Silicon. No audio is ever uploaded — there is nothing to upload it to.
The widget and your agent talk through plain files inside your own project. Inspect every byte; delete them any time.
Optional review mode: every transcript lands in an editable bubble first. Nothing reaches the agent until you hit ✓.
On Apple-silicon MacBooks, SKI docks into the notch — black, flush with the menu bar, always in the same place. It rests as a quiet bar, then springs down into the full loop when there’s something to say.
Hear it work: it rests listening, springs open to think, then answers in violet — then folds back to the bezel.
Every detail tuned for a real back-and-forth voice loop.
Speech-to-text and the voice both run on your Mac. Nothing you say ever leaves the machine.
Local speech in, a natural neural voice out — no cloud, no account, works offline.
A green dot shows your agent is actually listening — real-time, not polled.
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.
Bind several repos at once; each answers in its own voice and routes to whichever one you're addressing.
Capture mic + system audio from Zoom, Meet, or Teams — transcribed on-device with speaker-tagged tracks.
Paste a meeting URL into the widget and your coding agent joins the call as a live participant — speaking, listening, presenting.
→
A small floating app for your Mac that lets you talk out loud to your AI coding assistant — and hear it answer in a natural voice. Think of it as a phone call with the AI that helps you build software.
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.
It helps where typing doesn't — handing off a multi-step task, hearing the output while you look elsewhere, working hands-free, and accessibility. It's additive to your keyboard, not a replacement for typing exact syntax.
It's less “dictate every character” and more “delegate a task.” You hand off a job and get a spoken result back — handy across the room, hands-free, or when your wrists need a break.
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.
No. Listening, understanding, and speaking all happen on your Mac. The only feature that touches the internet is sending your agent into a video meeting — and that's optional.
No. Your voice becomes text on your own Mac and is never uploaded. There's no cloud service listening in — there is nothing to upload to.
Free forever on Mac — 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 (pay-as-you-go).
Yes. SKI records and transcribes any meeting playing on your Mac — Zoom, Meet, or Teams — with no time limit, stored only on your machine, exportable as text.
Any Mac on macOS 14.4 (Sonoma) or newer. Apple Silicon (M1 and up) is fastest. English today; more languages planned.
Free for life on macOS. 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.