Best take
You start a sentence, fumble it, stop, and say it again. On camera that is two takes of one line, and the first is dead weight you have to find by watching the whole thing back.
Included on every paid plan, and in the 7-day trial. Needs the local speech model.
Two nearby stretches of speech are a retake when enough of their words line up in the same order, allowing for the fact that a second attempt is rarely word-for-word. You drop a word, add one, change the ending.
At least four matched words are required, and on a short line that floor drops to the length of the shorter attempt, so “so today we’re — today we’re looking at” still registers.
Both attempts are shown side by side with the words that matched. By default the later one is kept, because a retake is normally an improvement on the one before it, but only you know which you meant.
The discarded attempt is removed from picture and dialogue together, as an ordinary cut you can undo or adjust.
It will not judge performance. A take you delivered badly but said correctly looks identical to a good one in a transcript. This finds repetition, not quality, and it will never remove a line you said only once.
It errs towards missing a retake rather than proposing to delete something you meant to keep, because a false match costs you a line and a miss costs you ten seconds with the razor tool.
Usually too long between the two attempts, because two similar sentences ten minutes apart are more often a deliberate callback than a stumble. Rephrasing entirely also breaks the match, since the second attempt shares no words with the first.
Yes, so the local speech model has to be installed. It runs on your machine and nothing is uploaded.
7 days of the whole product, no card. Nothing changes in your projects when it ends.
Start free