I have found that filler words at the start of sentences are removing the breath before them. I want tighter filler removal and all the breathes left in. Sometimes I can have the speaker not breathe for 3mins if they are "ummers".

I really don't like this new update when if I undo a ignored filler word, it still leaves the edit point and a slight break in the audio.

I spend a lot of time listening to every filler word to make sure it can be removed. What's funny is that all it requires is an eyeball on the waveform, and I can tell 95% of the time if a filler can be removed. If my eye can do it, surely Descript can as well.

Please see this new suggestion to preview filler word removal instances -- maybe merge it into this one?

Title: Preview Filler word removal before committing the edit

Posted by: Tony Tang

Post: Sometimes when filler words are removed, the edit is not clean. I would like an easy way to go through all the detected filler words and hear a preview of each removal and hit a button to accept or reject the removal. That way I can hear if the automatic removal will be clean before committing to the edit.

What I really want is to take my human generated transcript and sync with prejudice. What ever isn't in the human transcript is deleted.

Special prejudice: A special code when the human didn't understand the text to allow Descript to pull in the missing parts and then (keep or delete) based on filler word "rules"

I got bit by this today with a podcast. Going forward, I'm only going to manually remove filler words.

Yep. Use descript for content edits and hire a professional for proper distraction editing. the AI will never know the right move with filler removal and how to sound natural

First time using Descript and I learned the hard way to (a) correct my transcript before trying to remove filler words because they might be misidentified and (b) don't bother using Descript to remove filler words because the results are very hit or miss compared to editing manually with, say, iZotope RX. It would be nice to be able to round-trip edits, perhaps by setting up markers and then re-importing audio, though I suppose the resulting audio I would import would be a manually "flattened" version of the original...

Totally agree. You've created an amazing product, guys! And many many thanks for your talent and passion... but yeah sometimes it works a little bit too aggressive, and one should double check its work.