Zumbo Download
How to

Voice typing for Google Docs on Mac.

Docs has its own voice typing and it is genuinely useful inside a Docs tab. The question is what happens when you leave the tab.

What Google already gives you

Google documents voice typing under Tools, Voice typing. Its own page states that the feature works with the latest versions of Chrome, Edge and Safari, and that your web browser controls the speech to text service. It also states that voice commands are available only in English, and that both the account language and the document language must be English for them to work.

If you write long documents in Docs, in English, in a supported browser, that is a real feature and this page is not arguing you should stop using it.

The three places it runs out

It lives in a tab. The moment you leave the Docs window you are back on the keyboard: the email about the document, the message telling someone it is ready, the comment on somebody else's file, the search box. Most of a working day is not inside a Docs tab.

Commands are English only. Google states this plainly, along with the requirement that both the account and the document language are English. If you work across languages, the dictation may still write but the commands stop.

There is no vocabulary to teach. Whatever the browser's speech service hears is what you get. Product names, client names and technical terms come out as the nearest ordinary word every time, and there is nowhere to tell it otherwise.

The system wide version

your shortcut
Listening… 0:04

Hold it to talk, tap it to toggle, Escape cancels. Pick the key in Settings.

One shortcut for the document, the comment, the email about the document and the message saying it is ready.

Zumbo types where the cursor is, so Docs is simply one of the places with a cursor. The same shortcut works in the document body, a comment, a suggestion, the title, the Drive search box, and then in Gmail, Slack, Mail and everything else without changing anything.

  1. Put the cursor in the document.
  2. Hold your shortcut, which you chose in Settings during setup.
  3. Talk for as long as you need. There is no session limit.
  4. Let go. The text lands in about a fifth of a second, punctuated.

Where the audio goes

Google's page says the browser controls the speech to text service. Zumbo is unambiguous in the other direction: the speech engine ships inside the app and runs on your Mac, there is no account and no API key, and no network request is needed to transcribe. That also means dictation keeps working when the connection does not, which is a strange thing to discover you needed while a document refuses to load.

Teaching it your words

Twenty one vocabulary packs cover fields like developer tools, legal, medical, design and marketing, switched on during setup. For anything still wrong, correct it once with Teach and it is heard your way from then on, with the correction stored on your Mac. After a week the vocabulary matches the documents you actually write.

Related: dictating into Gmail, speech to text on the Mac, and adding custom words to Mac dictation.

Questions
Does Google Docs already have voice typing?

Yes. Google documents it under Tools, Voice typing, and states that it works with the latest versions of Chrome, Edge and Safari, with the browser controlling the speech to text service.

So why use anything else?

Three reasons. It only works inside a Docs tab, so the rest of your day is not covered. Google states that its voice commands are English only, with both the account and document language set to English. And it has no vocabulary you can teach.

Will dictation work in comments and suggestions?

With system wide dictation, yes: comments, suggestions, the document title, the file search and everything else with a cursor, in any browser.

Does it need the internet?

Zumbo does not. The speech engine ships inside the app and runs on your Mac, so the dictation works even when the document does not.

Can I teach it names and terms?

Yes. Select the word that came out wrong, type what you meant, press Teach, and it is heard your way from then on. The corrections stay on your Mac.

Free for 3 days, everything unlocked. Then $15 once. macOS 14 or later, Apple silicon.