Is there an AI video editor that removes filler words and adds captions in one step?

Yes. In Shorty, one brief does both: write “remove the ums and add word-by-word captions,” and the director cuts the fillers, then times the captions to the speech as it is after the cuts. Other editors can do both inside one app, but as separate steps, and captions made before a cleanup can fall out of sync.

Key takeaways

  • Shorty removes filler words and adds captions in one brief, with captions timed to the clean take.
  • Captions made before a cleanup can fall out of sync, because each cut moves the words after it.
  • If you use two steps, remove the fillers first and add captions second.

Why the order matters

Every cut moves the words after it earlier. If captions are made first and the fillers removed afterwards, each caption after the first cut is late unless the tool re-times it. OpusClip’s API guide says captions added before cleanup shift and have to be redone. Doing the cleanup first and the captions second avoids that, but it means two passes.

How it works in Shorty

Shorty transcribes each clip once, word for word, and shares that transcript between filler removal and captions. When the director cuts the fillers, it rebuilds the caption timing, sound cues and the edit’s length from the cut transcript. The captions you see are the words as spoken in the final video, with nothing to re-sync.

How other editors handle it

Filler removal and captions in other editors
ToolFiller removalCaptions
DescriptRemove filler words in AI ToolsCaptions follow the edited script
CapCutIdentify filler words while generating auto captionsTranscript edits are linked to captions
VEEDMagic CutSubtitles generated in the same editor
OpusClipSpeech CleanupCaptions added before cleanup shift and need redoing, per its API guide

Sources: Descript: filler words · CapCut: filler word removal · VEED: Magic Cut · OpusClip: filler-word removal API guide. Competitor features checked 20 October 2026 in each tool’s own documentation. Plans and features change, so check the current page before you choose.

Example brief

Adapt this brief to your footage and review the captions against the speech.

Cut this interview into a 40-second vertical video. Remove the ums, uhs and false starts, open on my strongest sentence, and add bold word-by-word captions at the bottom.

See it on four real talks

We ran four public talks through the same tool the director uses inside an edit. Across them, 107 words came out in 80 cuts, including every “um” and “uh” in the transcripts, and every kept word survived in order. The launch post plays each one before and after, with every removed word struck through.

Filler-word removal on four public talks (Shorty, October 2026)
RecordingLength before → afterWords cutCutsUms and uhs left
Nik Storonsky, Revolut2:00 → 1:49.840280 of 13
Prime Intellect, NVIDIA event1:00 → 0:53.238270 of 16
Arjun Karanam, Trajectory2:00 → 1:54.422210 of 8
Elon Musk, Tesla Roadster event2:00 → 1:58.4740 of 1

Sources: Shorty News: four talks before and after. Measured on excerpts of public YouTube talks on 20 October 2026. Results depend on the recording.

Questions, answered.

Do captions stay in sync after removing filler words?

In Shorty, yes: captions are timed from the cut transcript, after the fillers are gone. In tools where you caption first and clean up later, check the timing after every cut.

Should I add captions before or after removing filler words?

After. Each cut moves the words that follow it, so captions made first can end up late. Shorty does both in one pass in the right order.

How do I remove filler words in Shorty?

Add your footage and say it in your brief, for example “remove the ums, uhs and false starts.” The director cuts them from the picture and the sound and builds the rest of the edit, captions included, on the clean take. You can also ask for it in a revision of a finished edit.

Which languages does Shorty’s filler removal support?

English and Russian are tested by ear today. French, German, Spanish, Portuguese, Italian and Dutch are set up and in testing. Speech that mixes languages isn’t supported yet. Each clip can have up to three minutes of speech, on up to four clips per edit.

Take this page into your chat.

Open it in ChatGPT or Claude with the page already loaded, or read the plain-Markdown version.

Your next video starts here.

Bring the footage. Tell us the idea. Shape the edit.

Remove the ums in Shorty