Ship every lane at once. With your voice.
Keebye is on-device dictation for builders running parallel AI-agent workstreams. Hold a key, say the thing, and the text lands in whichever lane has focus — Claude Code, Cursor, Slack, anywhere you can type.
macOS · early access · audio never leaves your Mac
lane-1 · claude code refactoring the auth module…
lane-2 · cursor tests green, awaiting review
lane-3 · you, by voice "merge lane one, then draft the changelog"
Illustration: three lanes, one voice.
Why this exists
Keebye exists because its founder ran out of hands. Working with high-stakes startups — the kind where a $1M+ investment rides on shipping — meant running several lanes of work in parallel, at home with two kids, one of them under six months old. The only way to multiply output without multiplying hands was voice: dictate into one lane while another lane builds.
Built for the parallel-lane workday
Drive agent lanes by voice
While Claude Code grinds in one terminal, dictate the next prompt into another. Review, redirect, and queue work across lanes without breaking your typing flow in the lane your hands are in.
Reply while you build
Slack threads, emails, PR comments — focus the window, hold the key, and dictate the reply. Then get back to the lane that actually needs your hands.
Hands busy? Still shipping.
Holding a baby, eating lunch, pacing while you think. Hold the hotkey, talk, release — the words land wherever your cursor is.
How it works
- 01
Hold a key, speak
The default hotkey is Right ⌘ (Fn or Right ⌥ if you prefer). Hold to talk, or tap once to toggle a longer dictation. Esc cancels.
- 02
Transcribed on your Mac
Speech-to-text runs locally: a fast English-tuned default model, an optional multilingual engine covering 25 languages, or Apple's native engine. Once a model is downloaded, dictation works offline.
- 03
Text lands in the focused app
Keebye pastes — or synthetically types, which is what you want in terminals, SSH, and tmux — into whatever app has focus. It refuses password fields by design.
- 04
Cleaned up, your way
Fillers stripped, repeats collapsed, capitalization and punctuation fixed by fast rules — with an optional local-LLM polish pass that also runs entirely on-device.
Lands wherever your cursor is
…and anything else on your Mac that accepts text.
The honest feature list
- On-device speech-to-text — audio never leaves your Mac
- Works offline once the model is downloaded
- Optional multilingual engine — 25 languages, still on-device
- Types into terminals, SSH, and tmux sessions
- Custom dictionary for your project's jargon
- Local, text-only history — auto-deleted after 30 days
- No telemetry, no analytics
- Lightweight native menu-bar app, built with Tauri
- Launch at login, stay out of the way
Where Keebye is different on purpose
The category is crowded and the big tools are genuinely good. Keebye competes by being narrower and more honest — not louder.
On-device is the only mode
Most AI dictation routes your voice through cloud servers, or treats local models as the second-class tier. Keebye has no cloud path at all: speech-to-text runs on your Mac, and offline isn't a fallback mode — it's the architecture. The network is for model downloads, update checks, and license checks — never audio.
Terminal-grade text insertion
Most dictation is built for docs and chat. Keebye is built for where agents run: paste with terminal-aware chunking, or synthetic typing that survives SSH sessions, tmux panes, and non-QWERTY layouts. Password fields are refused by design.
Every plan is the whole app
No feature tiers, no word meters, no locked models. The 14-day trial and every paid plan are the same full product — the only thing Keebye sells is time. Pick monthly, yearly, or lifetime once it earns its keep.
Numbers we can defend
The multilingual engine supports exactly 25 languages — counted, not rounded up. Transcription runs in one pass when you release the key — we say batch because it is batch. And macOS is the only platform we advertise, because it's the only build we ship.
How Keebye compares
Wispr Flow and Superwhisper are both capable dictation tools with real followings. Keebye is built for a narrower job: driving parallel agent lanes with speech that never leaves your machine. Honest breakdowns:
Pricing
Try everything free for 14 days. Keep it when Keebye becomes part of how you ship.
Free trial
$0
14 days · no card required
Full dictation, free for two weeks. The trial starts the first time you sign in from the app.
- On-device transcription — audio never leaves your Mac
- English dictation, works offline after the model download
- Hold-or-tap hotkey dictation
- Custom dictionary and rule-based cleanup
- No telemetry
Pro
$8.33/month
$99.99 billed once a year
Save 76% vs paying monthly
After the trial, Pro is the whole app — every feature, every update. No tiers, no meters.
- Everything in the free trial
- Unlimited dictation — no meters, no caps
- All models: 25-language multilingual (Canary) and Apple native
- Optional on-device local-LLM polish
- Synthetic typing for SSH, tmux, and non-QWERTY layouts
Pro Lifetime
$199.99
one-time payment
All of Pro. Pay once, use it forever.
- Everything in Pro, forever
- One payment — no subscription
- Every future update included
- Local text-only history, auto-deleted after 30 days
Questions, answered plainly
Does my audio leave my Mac?
No. All speech-to-text engines run on-device. The network is used to download models, check for app updates, and confirm your trial or plan — never to send audio.
Does it work offline?
Yes. Once a speech model is downloaded, transcription runs locally without an internet connection.
Which languages does it support?
The default engine is English-tuned. Switch to the multilingual Canary engine for 25 languages — including Spanish, French, German, Portuguese, Romanian, Polish, and Ukrainian — or use Apple's native engine in your system language.
Which apps does it work in?
Anything that accepts text. Keebye inserts by pasting or by synthetic typing into the focused app, with terminal-aware handling for apps like iTerm2 and Warp — and typing-mode insertion works inside tmux and SSH sessions. It deliberately refuses secure password fields.
How fast is it, honestly?
Transcription runs in one pass when you release the hotkey — there is no live word-by-word stream. Prompt-sized utterances land quickly on Apple Silicon, though the very first dictation after launch can be slower while the microphone and model warm up.
Is my voice used to train anything?
No. There's no telemetry and no analytics, and audio is processed on-device — never uploaded. Your dictation history is stored locally as text only and auto-deletes after 30 days.
Why not just use Apple's built-in dictation?
You can — Keebye can even run on Apple's engine. What Keebye adds is the workflow: a hold-or-tap push-to-talk key, terminal-aware insertion that works over SSH and tmux, a custom dictionary for your project's jargon, and rule-based cleanup with an optional on-device LLM polish pass.
What does paying for Pro actually get me?
The whole app, after the 14-day trial. Keebye doesn't do feature tiers — the trial and every paid plan are the same full product. Paying is what keeps it developed.
Is there a free plan?
No — Keebye is a paid app with a 14-day full-featured free trial, no card required. The trial starts the first time you sign in from the app, not when you create your account. We'd rather give you the whole product for two weeks than a metered version forever.
What platforms are supported?
macOS today. A Windows port exists in the codebase but hasn't shipped a build yet, so we don't advertise it.
How do I get Keebye?
Keebye is in early access. Create an account to claim your spot — your 14-day free trial starts the first time you sign in from the app, and we'll let you know the moment the macOS build is ready to download.
Your hands are the bottleneck. Your voice isn't.
Put a dictation key under your thumb and keep every lane moving.
macOS · 14-day free trial · audio never leaves your Mac