How is this different from ChatGPT's voice mode?

Voice mode is OpenAI's cloud feature for having a spoken conversation with ChatGPT. Keebye is text input: you speak, the transcript lands in the prompt box, and you review and edit it before sending. It also works in every other app on your Mac, not just ChatGPT.

Does OpenAI ever hear my audio?

No. Speech-to-text runs on-device and audio never leaves your Mac. ChatGPT receives only the final text you choose to send, exactly as if you had typed it.

Does it work in the browser and the desktop app?

Yes. Focus is all Keebye cares about — the prompt box behaves identically whether it lives in a browser tab or in the desktop app.

Does it work offline?

Dictation does, after the one-time model download — transcription needs no network connection. ChatGPT itself of course needs one.

How do I start and stop dictating?

Hold Right Command as you dictate the prompt and release when done; a tap toggles for longer sessions, and Esc bails out. If Right Command is inconvenient, Fn and Right Option are the built-in options.

Voice Dictation for ChatGPT on Mac

Why dictate prompts to ChatGPT

The prompts that get the best answers out of ChatGPT are long: context, constraints, examples, the exact question. That's paragraph typing, and it's exactly the kind of writing that costs less effort to speak than to key in — especially when you're doing it many times a day.

ChatGPT does have a voice feature of its own — voice mode, which runs in OpenAI's cloud and turns the session into a spoken conversation. That's a different job. Keebye is input dictation: your words become text in the prompt box, where you can read them, fix them, and add to them before anything is sent. If you want to speak your prompts but still edit them before the model sees them, that's the gap this fills. And because Keebye works everywhere on your Mac, the same hotkey covers your editor, your terminal, and every other chat box too.

How it works

Click into the ChatGPT prompt box — any browser, or the desktop app — hold Right ⌘, and say the prompt. On release, your words appear at the cursor for you to review, edit, or send. Keebye types into whatever field has focus, so there's no ChatGPT-specific setup.

The transcription engine lives on your Mac: Parakeet covers English out of the box, and once the model is downloaded, no connection is required and no telemetry is sent. Your audio never goes to OpenAI or anyone else; ChatGPT receives only the final text you decide to send.

Setup in two minutes

Two minutes covers it: install, say yes to the Accessibility and microphone permission prompts, and settle on a hotkey — Right ⌘ works out of the box, with Fn and Right ⌥ as the other choices. Add launch-at-login and it's waiting whenever a browser tab is.

Then add your recurring vocabulary to the custom dictionary — product names, project names, the technical terms you use in every prompt — so they transcribe correctly the first time.

Limits, honestly

The text arrives after you release the key, in one batch — not as live captions while you talk, and not as a spoken back-and-forth with the model. For an actual voice conversation, OpenAI's own voice mode is the tool.

Keebye is macOS only.