> ## Documentation Index > Fetch the complete documentation index at: https://keebye.com/llms.txt > Use this file to discover all available pages before exploring further. # Keebye — Voice Dictation for Parallel Builders > Ship every lane at once, with your voice. Keebye is on-device dictation for Mac and Windows, for builders driving Claude Code, Cursor, and more in parallel. Keebye is push-to-talk dictation for Mac and Windows. Hold a key, say the thing, release — and the text lands in whichever app has focus, including your terminal. Speech-to-text runs entirely on your computer. ## Who it is for 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. - Terminal: Paste insertion with terminal-aware chunking, or synthetic typing that survives SSH and tmux. - Claude Code: Dictate a whole instruction into a running agent session without taking your eyes off the other lane. - Cursor: Speak the prompt into the composer; the text lands wherever the cursor is, cleaned up by rules you can turn off. - ChatGPT: Long prompts at speaking pace. Audio never leaves your computer — only the finished text reaches the chat box. - Slack: Any text field works, Slack included. On a Mac, password fields are refused by design. ## Who it is not for - Linux users: Keebye ships for Mac (Apple Silicon) and Windows (x64) only. - Anyone who needs live word-by-word transcription: Keebye transcribes in one pass when you release the hotkey. ## Platforms - Mac: Apple Silicon, macOS 11 or later. https://github.com/aiescu/keebye-releases/releases/download/v0.2.0/Keebye_0.2.0_aarch64.dmg - Windows: Windows 10 or 11, 64-bit (x64). https://github.com/aiescu/keebye-releases/releases/download/v0.2.0/Keebye_0.2.0_x64-setup.exe or https://github.com/aiescu/keebye-releases/releases/download/v0.2.0/Keebye_0.2.0_x64_en-US.msi - Not on Windows yet: the Apple Speech engine, the password-field check, and automatic updates. Setup: [Install and permissions](https://keebye.com/docs/install-and-permissions.md), [Getting started](https://keebye.com/docs/getting-started.md). ## Languages The default English-tuned engine is fast. Opt into the multilingual Canary engine for **exactly 25 languages**, pin one for your next utterance, or, on a Mac, use Apple's native engine in your system language. Details: [Languages and engines](https://keebye.com/docs/languages-and-engines.md). ## Privacy Speech-to-text runs on-device. The network is used to download models, check for updates and confirm your plan — **never to send audio**. No telemetry, either. Details: [History and privacy](https://keebye.com/docs/history-and-privacy.md). ## Pricing and trial 14 days free, then Pro monthly, annual, or once for life. Speech never leaves your computer on any plan. Prices and billing periods, including the first-month price for new subscribers, are at https://keebye.com/pricing.md. ### Trial — Free, 14 days · starts on first desktop sign-in The full app for 14 days, on Mac or Windows. - Every model: Parakeet (English), Canary (25 languages), local-LLM polish - Hold-or-tap hotkey, Esc to cancel - Paste insertion with terminal-aware chunking - Custom dictionary - Local text-only history, 30-day auto-delete - Unicode synthetic typing for SSH, tmux and non-QWERTY layouts ### Pro The same full app, kept after the trial. - Every model: Parakeet, Canary (25 languages), local-LLM polish - Every feature from the trial, after day 14 - Every future update ### Pro Lifetime Lifetime access to all Pro features. - Pay once, use forever ## FAQ ### Does my audio leave my computer? 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, on a Mac, use Apple's native engine in your system language. ### Is the website language the language I can dictate in? No, the two are separate. This website is translated into 33 languages, and the app's own screens are in English. What you can dictate depends on the speech engine: Parakeet, the default, is English; Canary covers 25 European languages; on a Mac, Apple's engine can also use your system language. Check the exact list in [Languages and engines](/docs/languages-and-engines) before you rely on a 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, Warp, and Windows Terminal — and typing-mode insertion works inside tmux and SSH sessions. On a Mac it deliberately refuses secure password fields; the Windows version has no password-field check yet. ### 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 Macs; on Windows, speed depends on your PC. 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? On a Mac, you can — Keebye can even run on Apple's engine there. 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: every model, every feature, every future update. Pro and Lifetime are the same full product — the only difference is how you pay. Paying is what keeps Keebye 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? Mac and Windows. On a Mac you need Apple Silicon and macOS 11 or later; on Windows, Windows 10 or 11 on a 64-bit (x64) PC. A few things are not on Windows yet: Apple's speech engine, the password-field check, and automatic updates. Setup for both: [Install and permissions](/docs/install-and-permissions). ### What happens when my 14-day trial ends? When your trial ends, you can't start a new dictation until a paid plan is active — anything already in progress can finish. There's no surprise charge: the trial takes no card, so doing nothing costs nothing. Subscriptions can be cancelled anytime and run to the end of the billing period. ### How do I get Keebye? Download the installer for Mac or Windows from the [download section](/#download), then sign in from the app. Your 14-day free trial starts at that first sign-in, and it needs no card.