This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
TalkCut
Edit video by editing text. Free, offline, open source.
TalkCut is a free, open-source desktop editor. Transcribe on your own computer, then delete words to cut the video. One click removes ums, pauses and retakes. Local voice cleanup, captions, recording and 4K export with no watermark. No account, no uploads.
Text-based editors make cutting ums, long pauses and flubbed retakes easy, but the ones I tried were subscriptions with transcription limits that wanted my files in the cloud. So I built a free one that runs entirely on your computer:
Edit the transcript, edit the video. Delete words and that stretch of media is cut. Non-destructive, with undo.
One-click cleanup. Preview filler words, long gaps and repeated takes, then apply them as one undoable edit.
Voice cleanup. Local noise removal and loudness normalisation, with a live Before/After switch.
Captions (SRT/VTT), titles, layers, and screen/camera/mic recording with a teleprompter.
Export MP4 up to 4K or MP3, with no watermark.
No account, no uploads. Transcription runs locally with whisper.cpp. Optional cloud AI is off by default.
It's MIT-licensed and on GitHub for Windows, macOS and Linux. Honest caveats: the installers aren't code-signed yet (you'll see a SmartScreen/Gatekeeper prompt; checksums are on the release page), and the Mac build is Intel and runs on Apple Silicon via Rosetta for now.
What I'd love from you: try it on one real recording and tell me what the cleanup missed or got wrong. Thanks for checking it out!
No comment highlights available yet. Please check back later!
About TalkCut on Product Hunt
“Edit video by editing text. Free, offline, open source.”
TalkCut was submitted on Product Hunt and earned 2 upvotes and 1 comments, placing #131 on the daily leaderboard. TalkCut is a free, open-source desktop editor. Transcribe on your own computer, then delete words to cut the video. One click removes ums, pauses and retakes. Local voice cleanup, captions, recording and 4K export with no watermark. No account, no uploads.
TalkCut was featured in Productivity (665.7k followers), Open Source (69.1k followers), GitHub (41.5k followers) and Video (2.1k followers) on Product Hunt. Together, these topics include over 241.2k products, making this a competitive space to launch in.
Who hunted TalkCut?
TalkCut was hunted by Rajan Gupta. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how TalkCut stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Hi Product Hunt 👋 I'm Rajan, and I built TalkCut.
Text-based editors make cutting ums, long pauses and flubbed retakes easy, but the ones I tried were subscriptions with transcription limits that wanted my files in the cloud. So I built a free one that runs entirely on your computer:
Edit the transcript, edit the video. Delete words and that stretch of media is cut. Non-destructive, with undo.
One-click cleanup. Preview filler words, long gaps and repeated takes, then apply them as one undoable edit.
Voice cleanup. Local noise removal and loudness normalisation, with a live Before/After switch.
Captions (SRT/VTT), titles, layers, and screen/camera/mic recording with a teleprompter.
Export MP4 up to 4K or MP3, with no watermark.
No account, no uploads. Transcription runs locally with whisper.cpp. Optional cloud AI is off by default.
It's MIT-licensed and on GitHub for Windows, macOS and Linux. Honest caveats: the installers aren't code-signed yet (you'll see a SmartScreen/Gatekeeper prompt; checksums are on the release page), and the Mac build is Intel and runs on Apple Silicon via Rosetta for now.
What I'd love from you: try it on one real recording and tell me what the cleanup missed or got wrong. Thanks for checking it out!