Guide · WorkflowsAvailable now

Dictate GitHub pull request titles and descriptions

GitHub pull requests are a normal web form, so voice input works in the title, body, and every review comment.

Try the free voice toolFree · No signup · Runs in your browser

A good pull request reads like a short story about the change. Voice input helps you get that story out fast, and a cleanup pass turns it into a review friendly summary.

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 pull request title or description first.

What to dictate

Speak the problem, the change, and the risk in plain words. Save code blocks and command output for keyboard paste. Reviewers scan the summary first, so dictate that with care.

Draft in Zahvox for public copy

For anything attached to a change that other engineers or clients will read, 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.

Make the setup boring on purpose

The best voice workflows are the ones you stop noticing. Once dictate github pull request titles and descriptions works, resist the urge to keep tweaking it. Same mic, same shortcut, same place the transcript lands. Boring is the goal. When the mechanics fade into the background, your attention goes back to the actual thinking, which is the only reason you started dictating in the first place.

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 github pull request titles and descriptions 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.

Looking for something else? Browse the full guides library or open the free voice tool and practice as you read.