How to remove filler words
- Drop your video. A talking-head clip, a lesson, a podcast video or a screen recording with your voice.
- Find the fillers. Press Find pauses and fillers. Each “um”, “uh” and set-off “like” or “you know” is marked in red on the timeline.
- Check the ones that matter. Tick or untick each one in the list, or edit the filler list for your language. Tick sounds with no words to also catch the “um”s the speech model didn't write down.
- Export. Download the cut MP4 and the matching subtitles.
Filler words it knows
| Language | Always cut | Only when set off by commas |
|---|---|---|
| English | um, uh, erm, er, ah, hmm | like, you know, I mean, so, basically, actually, literally, kind of, sort of |
| Spanish | eh, em, este, mm | o sea, pues, bueno, sabes, vale, digamos, tipo |
| Portuguese | é, hum, ã, ah | tipo, né, então, assim, sabe, olha |
| French | euh, heu, hum, bah, ben | genre, en fait, du coup, voilà, quoi, bon, tu vois |
| Hindi | अ, अं, उम, हम्म | मतलब, तो, अच्छा, यानी, बस |
| Urdu | ام, ہمم, آ | مطلب, یعنی, تو, اچھا, بس |
| Arabic | اه, امم, ممم, إيه | يعني, طيب, خلاص, بس |
The list is editable in the tool: add the words you lean on, or remove one you want to keep.
How it finds pauses and fillers
Most silence removers look only at loudness, so they cut quiet words and keep loud breaths. This one starts from a transcript: Whisper large-v3 turbo, on your graphics card, writes every word with its start and end time. A pause is the gap between two words, and its edges are checked against the sound, because the model often stretches a word's end into the pause after it. Fillers are words from a list for your language: “um” and “uh” anywhere, and words that are also real words (“like”, “you know”, “I mean”, “o sea”, “tipo”, “du coup”, “يعني”, “मतलब”) only when the transcript sets them off with commas, so “I like it” stays.
Voice inside a pause with no word attached is shown as its own block: usually a breath, a cough, or an “um” the model chose not to write. Speech models are trained on clean transcripts and tend to leave disfluencies out, so on some recordings this catches more fillers than the word list does. It is off by default because it can also catch a breath you want to keep.
Jump cuts, smoothed
Cutting a pause out of the middle of a talking-head shot makes the face jump. Tick Smooth jump cuts and every other section is punched in by 8%, the trick editors use to make a jump cut look deliberate, and the audio joins get a softer 40 ms fade. Without it, joins still get a 12 ms fade so they never click.
Subtitles that match the cut
The words are already timed, so the subtitles for the shorter video come for free: every word moves with its section, cut words (the fillers) are dropped, and the lines are rebuilt to two rows of 42 characters (26 for vertical video). Download SRT for YouTube, Premiere, Resolve and CapCut, or VTT for web players, and translate them with the subtitle translator.
More free video tools
- Auto captions: subtitles for the cut video, with a full caption editor and styles.
- Noise remover: take fans, traffic and hum out of the voice first.
- Video compressor: make the cut small enough for Discord, WhatsApp or email.
- Subtitle translator: the SRT in Spanish, Hindi, Urdu, Arabic, Portuguese or French.
- Text to speech: a natural voice-over for an explainer or slides, made on your device.
Privacy
Your video is read, transcribed and cut by your browser on this page. It is not uploaded, stored or seen by anyone. The only download is the speech model, once; your browser keeps it for next time.
Questions
How do I remove “um” and “uh” from a video?
Drop the video here and press Find pauses and fillers. Each “um” and “uh” in the transcript is marked; they are cut by default, and you can keep any of them. Tick “sounds with no words” to also cut the ones the speech model left out of its transcript.
Why does it miss some “um”s?
Speech models learn from tidy transcripts that leave disfluencies out, so they often skip “um” and “uh” even when they hear them. The tool still sees the voice in that gap and shows it as “sound, no words”; tick the option to cut those too, and listen to the preview to check.
Will it cut “like” in “I like it”?
No. Words that are also real words are only cut when the transcript sets them off with commas, as in “it was, like, huge”. You can change the list.
Can I add my own filler words?
Yes. Open the filler list under the cuts, add a word or phrase per line, and end it with a comma if it should only count when set off by commas.
Is my video uploaded?
No. Transcription, the cut and the export all happen in your browser. The file never leaves your device.
Is it free? Is there a watermark?
Free, with no watermark and no sign-up, for videos up to 10 minutes. Longer files will be part of SubForge Pro.
Which browsers work?
Recent Chrome and Edge on desktop are best: they have WebGPU for fast transcription and WebCodecs for the export. Safari 26 works too. Firefox can transcribe but may not be able to export MP4 yet. Without WebGPU the transcription runs on the CPU, several times slower.