Correct while you listen
- Click a word or a line – playback jumps right there.
- Play at 1×, 1.5× or 2×.
- Find and replace across the whole transcript, with undo.
- Your own words: names and terms that must always be spelled right go into a list once; Lautnote uses them while transcribing.
Who said what
Lautnote recognizes the speakers and gives each a colour and initials, so they can be told apart without colour too. Give them names, merge two speakers that are really one, or split one that is really two. The bar above the transcript shows each person's share of the speaking time.
In our test with three voices (two of them similar), Lautnote attributed 93.7 % of the words to the right speaker. The test used synthetic voices; real recordings with crosstalk are harder. Speaker detection runs on the processor and adds about 8 minutes per hour of audio on our test PC.
Light, dark or the same as Windows – you choose in the settings.