Cuescribe

Remove filler words

Drop a talking video or podcast. It is transcribed on your device, then every um, uh, false start, repeated word and skipped sound is listed in context. When you start a sentence again, only your last take is kept. Untick what you want to keep, preview the result with the cuts skipped, and download the tightened video, WAV, EDL or subtitles.

How to use it

  1. Drop the recordingIt is transcribed on your device; a transcript made here earlier is reused.
  2. Review the listFillers, retakes and repeats are ticked; tics and untranscribed sounds are listed but left alone.
  3. PreviewPlay the result with the cuts skipped before exporting anything.
  4. ExportThe tightened video, a WAV, an EDL for your editor, subtitles retimed to the cuts, or a CSV.

What you can download here

  • Tightened MP4cuts applied, picture and sound in sync
  • EDLfor Premiere, Resolve and Avid, so the cuts stay editable
  • Retimed SRTsubtitles that match the shorter video
  • WAV and CSVtightened audio, and a list of every cut

Good to know

Leaving some ums in sounds more natural: many podcasters remove only the distracting ones. Untick the ones that belong to the rhythm of the speech.

Free Chrome extension

Cuescribe for Chrome

A transcript side panel on every YouTube and TikTok video, a library of everything you transcribe, and one click to open any of it in these tools.

Get the extension
Pro · early access

Pro keeps this free

Every tool stays free. Pro (early access, $9/month) adds batch delivery for client work and the extension's Pro features; longer files and multi-file projects are in development. Early subscribers keep their price and choose what gets built next.

What Pro includes

Next steps

Silence removerCut dead air; get the tightened video, an EDL or a WAV.Mouth click remover NewLip smacks and mouth clicks found and repaired. A/B, WAV, video.Clip from transcriptClick sentences, export that clip as MP4 with its subtitles.Auto-reframe to vertical16:9 → 9:16 with a crop that follows the face.Apply a LUT New.cube LUT on video or photos, before/after, export.Batch LUT and export NewOne LUT on many clips, each exported with its original name.

All 44 free tools →

Questions

How does it find fillers the transcript doesn't show?

Speech models are trained to write clean text, so they often leave out "um" and "uh". We also look for sound between two transcribed words where the model wrote nothing: that is usually a dropped filler, a breath or a laugh. Those are listed as "untranscribed sound" and are not cut unless you tick them.

Can it keep only my last take?

Yes. When you stop and start a sentence again with the same opening words ("So today we… sorry. So today we're fixing the door"), the abandoned try is listed as a retake and cut, so the last try is what stays. It needs three or more matching words and a pause, an "um" or a "sorry" in between, so a point you deliberately repeat later is left alone.

Will it cut words I meant to say?

Only what is ticked. Fillers, retakes and repeated words are ticked by default; verbal tics like "like" and "you know" are listed but left alone, because they are often real words. Play any line to hear it in context.

Is there a limit or a credit cost?

No credits and no account. Everything runs in your browser, so the limit is your computer's memory: recordings up to about an hour work on most laptops.

Which editors can open the EDL?

Premiere Pro, DaVinci Resolve and Avid import CMX3600 EDLs. Relink to your original file when asked.