But this is still possible to do if you track the whole run of text. You could replace all of it each time so it LOOKS like it’s streaming but earlier words also change. I’m hoping the streaming models do this eventually.

I believe the built-in iOS dictation already does this.

▲

kristiandupont 11 hours ago | parent [-]

What would be the benefit of this, besides from looking cool?

▲

atonse 11 hours ago | parent | next [-]

More accuracy. Like others have said, homonyms (their, they're, there) is easier to determine once you have more context. So then you may need to go back a couple words and update them.

Same with punctuation, you could determine that a comma belonged in a certain place once you have enough words.

▲

knowknowledge 11 hours ago | parent | prev [-]

In iOS this means you can edit the text as it’s being transcribed. For example, I want to dictate a todo list and after each item I can hit enter to go to the next line.

	▲	yorwba 9 hours ago \| parent [-]
		Do the parts before you hit enter still get updated if later context indicates you said something else?