We often share large video files of interviews within our team to log soundbites. Speech to Text could be exteremely useful for producers to select sound and use clip timecode so our editors can find the correct soundbite.
Alas, Speech to Text transcription is basically useless to us in it's current implementation because Premiere only inserts sequence timecode when transcribing and not CLIP timecode. I suggest allowing users to select and option to use either clip timecode or sequence timecode when generating transcription files.
AdChoices