Which coding agents does Keebye work with?

All of them, because it doesn't integrate with any of them. Keebye types into whatever field has focus — Claude Code in a terminal, Cursor's composer, ChatGPT in a browser — with no per-tool setup.

Does it handle several agent sessions at once?

Yes, in the simplest possible way: the hotkey follows your focus. Click into whichever terminal or window needs direction, hold, speak, release, move on.

Do my prompts or audio go to the cloud?

No. Recognition runs on-device, the audio stays put, and there is no telemetry — each agent gets only the final text, as if typed by hand.

Does it work offline?

Yes — the model downloads once, and from then on dictation touches no network at all.

Can it learn my stack-specific vocabulary?

Yes. Load your repos, branches, tools, and framework names into the custom dictionary and they'll be spelled right from the start.

Voice Dictation for Vibe Coders

Why vibe coding runs on your voice

If you code with agents, be honest about what your hands do all day: they type prompts. The code increasingly comes from Cursor, Claude Code, or ChatGPT; what you produce is instructions — multi-sentence paragraphs about what to build, what to leave alone, and what done looks like. That's a speaking workload wearing a typing costume.

Keebye exists because its founder lives this exact day: parallel high-stakes startup lanes with $1M+ investment stakes riding on them, two kids at home — one under six months — and several agent workstreams grinding at once. When the baby is in one arm and three terminals are waiting for direction, speaking the next prompt is the difference between the lanes moving and the lanes stalling.

How it works

Focus whichever agent needs direction, hold Right ⌘, speak, release. Your words land as text at the cursor, and the workflow is the same everywhere: in Claude Code it lands in the terminal with chunked typing so long prompts arrive intact; in Cursor it fills the chat or composer; in ChatGPT it drops into the prompt box in any browser or the desktop app. Terminals in general get special treatment — the terminal page covers why.

All of the speech recognition happens locally — Parakeet is the English default — and after the single model download it keeps working with no network and reports nothing back. Your agents see only the finished text; the audio never leaves the machine.

Setup in two minutes

One install, two permission grants — Accessibility and microphone — and a hotkey choice, and you're set. Hold Right ⌘ by default, or switch to Fn or Right ⌥. With launch-at-login enabled, Keebye is running before your first agent session is.

Then load the custom dictionary with your stack: repo names, branch names, the tools and frameworks in every prompt. One minute of setup, and your jargon transcribes correctly the first time.

Limits, honestly

Keebye waits for the key release before transcribing — batch, not streaming — so nothing appears until you let go, and then the whole prompt lands.

Keebye is dictation, not orchestration — it doesn't manage your agents or watch their output, and it has no voice commands. It moves your words into the box faster; the judgment calls stay yours.

Keebye is macOS only.