Choosing audio tracks and a range (In–Out)
Which audio tracks to tick in the Napisy AI plugin, how to transcribe only part of a sequence (In–Out) and how the plugin handles cuts and speed changes.
In this article
Speech tracks
In the Ścieżki z mową (Speech tracks) section, tick the tracks that carry voice. By default the plugin ticks the first track with clips. Music, effects and ambience on the other tracks are left out of the transcription – the captions come out cleaner and the model does not “hear” song lyrics.
A conversation recorded on two microphones? Tick both tracks (e.g. A1 and A2).
Only a part: In–Out
Set the In and Out points on the sequence timeline and choose the In–Out source. The plugin transcribes only that part and uses minutes only for it. The captions land exactly in that place on the timeline.
Cuts, speed changes, nesting
The plugin exports the audio of the finished, edited sequence, so cuts, speed changes and nested sequences are already taken into account. Words land where they are spoken in your edit.