Descript is where podcasters and video editors live, and voice input keeps the writing side moving so the edit side never waits on a script.
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.
Click into the script pane or a note field before you speak so the caret sits inside it.
Scripts vs project notes vs comments
Scripts hold the words you plan to say on tape. Project notes carry the shape of the show. Comments hold the review pass. Speak in each shape and cleanup stays quick.
Draft in Zahvox for public copy
For anything published as show notes, a description, or a public transcript, 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 scripts and show notes in descript, 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 scripts and show notes in descript 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.
