( How to )
How to remove filler words from a podcast
Three steps: upload the episode (it transcribes itself), open the Fillers panel, and cut every hesitation in one click. The cuts snap to quiet points in the waveform, so the speech stays intact — and every cut is reversible.
Step by step
- 01Upload the episodeDrop the audio file into Cast. Transcription starts automatically — no credits, any plan.
- 02Open FillersThe Voice Editor lists every “um”, “uh” and “mm”, counted per speaker and pinned to its timecode. Flip on discourse markers like “like” per word if you want them too.
- 03Cut all — or one at a timeOne click takes the lot; each cut lands on a quiet point between sounds. Anything that sounds wrong afterwards is one Restore away.
Why the cuts don’t chop words
Bulk filler removal usually fails at the edges: a cut placed by timestamp clips the syllable next to it. Cast snaps each cut to a quiet point in the waveform, and where clean edges don’t exist it mutes the filler instead — so the one-click pass is one you can trust.
FAQ
01How does filler detection decide what counts?
The Voice Editor finds them for you and lists them. Hesitations — "um", "uh", "mm" — are flagged by default and you can cut them all in one click. Discourse markers like "like" and "so" are detected too, but stay off until you switch them on word by word.
Read more →02Can I undo the cleanup later?
Yes. Undo and redo work as normal, and separately, every cut and mute is listed under Recent edits with its own Restore. Because Cast never overwrites your recording, you can put back one filler word you removed twenty edits ago without losing anything you did since.
Read more →03Does it cost credits?
Only generation — music and sound effects. Transcription, every kind of transcript editing, noise removal, captions and exporting are free on every plan. The exact price is shown next to the Generate button before you spend anything.
Read more →