Rescript vs TimeBolt: free filler and silence cutting

Rescript vs TimeBolt

TimeBolt automates the tedious part of editing spoken video: detecting and cutting silences and filler words in bulk, locally, with a handoff to Premiere, Final Cut, or Resolve. Rescript does the same two cleanups in one click each, and adds the workflow around them — a Whisper transcript you can edit directly, speaker labels, editable cut edges, and respeaking a fumbled line in the original voice. Rescript is free and open source; TimeBolt's NLE handoff is better than Rescript's, which renders finished media instead of a timeline.

Try it in your browser Download desktop app Source

The Rescript editor: a transcript on the left with a struck-through word, video preview on the right, and a waveform timeline underneath.

Automatic cuts, then judgement: the transcript is what lets you pick between three takes of the same sentence rather than only trimming dead air.

Side by side

Rescript compared with TimeBolt.

Feature comparison between Rescript and TimeBolt
Feature	Rescript	TimeBolt
Price	Free and open source for noncommercial use	Paid
Where your media goes	Nowhere. It never leaves your device	Processes locally
Works offline	Yes, once the model has downloaded a first time	Local processing, licence check online
Source code	Public on GitHub — auditable	Proprietary
Silence removal	One click, pauses of 0.3s and over	Automatic, tuneable
Filler word removal	One click across the whole file	Automatic filler cutting
Delete words to cut footage	Word-level, with a live preview of the cut	Cuts words, but the transcript isn't the editing surface
Speaker detection	Local diarization, speakers renameable	No diarization
Rewrite a line and have it spoken	Yes — cloned from that speaker's own audio, on-device	No
Round-trip to Premiere / Final Cut	Not yet — renders finished media instead	Premiere, Final Cut, Resolve, and more
Runs on	Browser, macOS, Windows, Linux	macOS and Windows

Details about other products come from their own public pricing and documentation pages and change often — check theirs before you decide. Corrections are welcome as a GitHub issue.

Automation plus judgement

Automatic cutting handles the parts of an edit that don't need thought — dead air, throat-clearing, "um" — and both tools do that well. What it can't decide is which of your three attempts at a sentence to keep, or that a tangent halfway through should go entirely.

That's where the transcript matters. Rescript runs the same cleanups, then leaves you reading the result as text. Every automated cut stays editable: drag its edges, restore words, or fix a word's timing when Whisper drifts.

What Rescript adds after the cleanup

Local speaker diarization groups a multi-person recording by who's talking and lets you rename each speaker, which makes an interview far easier to read.

Regenerate handles the case cutting can't: a line you got wrong. Rewrite it, and Rescript speaks it in that speaker's cloned voice — generated on your machine from about ten seconds of their own audio, and fitted to the exact span it replaces.

Which one

They're good at different jobs.

Choose TimeBolt if…

You batch-process many episodes and want cutting fully automated.
You finish in an NLE and need editable cut points, not a rendered file.
You want fine-grained control over silence thresholds and padding.

Choose Rescript if…

You want to read the recording as text and make judgement calls, not only automate.
You want it free, open source, and running on Linux too.
The recording has several speakers and should be grouped by who's talking.
You'd rather fix a bad line than cut around it.

FAQ

Questions people actually ask

Is there a free tool that removes filler words and silences automatically?

Rescript does both in one click each — every detected "um" and "uh", and every pause of 0.3 seconds or longer — running entirely on your own machine and free for noncommercial use.

Can Rescript export cuts to Premiere or Final Cut?

Not as a timeline. It renders the finished cut to MP4 or WebM and exports SRT, VTT, and JSON captions. Timeline interchange is on the roadmap; TimeBolt is the better fit if you need that handoff today.

Keep comparing