Instead of recording for multiple minutes and then taking forever, can it just stream what it recognizes.
Right now it's bad UX. You speak for 5min
then it you wait, hoping it worked, or even listened at all. Sometimes it says it fails, and things are gone. So you waisted time..
Instead i wanna see the words as I talk appear...
Instead of recording for multiple minutes and then taking forever, can it just stream what it recognizes.
Right now it's bad UX. You speak for 5min
then it you wait, hoping it worked, or even listened at all. Sometimes it says it fails, and things are gone. So you waisted time..
Instead i wanna see the words as I talk appear...