Skip to main content
Both start the same way, by holding a button and talking. What happens to the words afterwards is the difference.

Dictation

The text goes into the app you are using, as if you typed it. Nothing is kept afterwards by default.

Notes

The text goes into Vox, saved and searchable. Nothing is inserted anywhere else.

Use dictation when

You have a cursor somewhere and you want words at that cursor. Writing a Slack message, filling a form, replying to an email, writing code comments.

Use notes when

You want to say something now and deal with it later. Walking between meetings, capturing an idea, leaving yourself a reminder. There is no target app and no cursor involved, so it does not matter what is on screen.

Telling them apart while you use them

TODO: describe the visible difference. Does the overlay pill look different for a note than for dictation? If it does, that is the thing to point at here, ideally with two screenshots side by side.

Switching between them

TODO: how does a user choose? Is it a separate button gesture, a mode toggle in the app, or does the Notes tab being open change the behaviour? Confirm before writing.

What happens to notes afterwards

Notes are listed in the Notes tab, newest first. You can search them, label them, and copy the text out.
Dictating into a text field and wishing you had kept it? Copy the text before you navigate away. Dictation does not keep a history of what it typed.