Shell work leaves thin history, and voice input keeps a written trail of what a session did so future you does not repeat the same debug.
Start voice input
On Mac press the Fn key twice inside the target field.
On Windows press Windows plus H to open voice typing.
On Chromebook enable dictation in Accessibility settings.
Open a notes file in your editor of choice from the terminal, then click into it before you speak.
Notes vs script comments
Notes carry the story of the session. Script comments carry the intent of a line. Speak longer sentences into notes and shorter lines into comments.
Draft in Zahvox for public copy
For anything published as a runbook or a public postmortem, dictate the raw thought in Zahvox, tighten the wording, then paste it back. That extra pass keeps the tone steady and removes filler.
Small habits that keep it readable
Say punctuation out loud, including commas and periods.
Keep one thought per sentence so cleanup is fast.
Do a short review pass at the end of every session.
Save common phrases in a snippet tool so voice input can call them.
Measure the workflow by output, not by feel
A month into using dictate command notes and shell history in the terminal, look at what actually shipped: emails sent, notes filed, posts published, tickets closed. That number is the honest scorecard. The workflow either produced more finished writing than the keyboard-only version or it did not. If it did, keep going and stop second-guessing. If it did not, one specific piece is broken — usually the edit step, not the capture step — and that is the piece to fix next.
Where Zahvox fits after the raw capture
Zahvox is the careful second pass that sits after the raw capture. The browser, the OS, or the app you used for dictate command notes and shell history in the terminal gave you words on a page. Zahvox at /tool is where you paste those words, tighten the wording, fix the shape of the sentences, and copy the result back into wherever it needs to live. Raw capture anywhere, careful edit in Zahvox — that is the whole loop, and it stays the same whether the source was a laptop, a phone, or a meeting transcript.
