Early access · English version in development

An Opus Clip alternative for long recordings you'd rather not upload

OxClipper is a desktop AI clip maker for full podcast episodes, livestream recordings, course sessions and client footage. It runs on your Windows PC or Apple silicon Mac, so the video file is never uploaded and local transcription and rendering aren't metered by the minute.

It's in use in Chinese today. The English version isn't out yet, so this page is a waitlist, not a download.

We'll email you when the English version opens. No spam, no sharing. Privacy

Side by side

Opus Clip and OxClipper, on the points that matter for long footage

Opus ClipOxClipper
Where the video is processedIn the cloud, in your browser. You upload or import the video.On your computer. Clip planning sends only the transcript text to an AI service.
How usage is counted1 credit per minute of the original video you import. Free: 60 credits. Starter: $15/month, 150 credits. Pro: $29/month (or $14.50/month billed yearly), 300 credits a month that roll over for 2 months.Local transcription and rendering aren't metered. AI clip planning is billed by transcript length, with an estimate before each run. English pricing isn't set yet.
Long recordingsEvery minute you process counts against your credits; you can trim the processing timeframe to spend fewer.No upload wait and no minute count for local work. Each AI analysis run has a transcript length cap (roughly four to six hours of continuous speech).
Choosing clipsAI picks clips and gives them a virality score (Starter and up).AI proposes 1–10 versions per run from the transcript. You play every segment, nudge in/out points, remove or reorder before anything exports. No virality score.
Vertical framingAI reframing that keeps the subject in frame (Starter and up).No face tracking. Fit the frame with a blurred background, or crop to fill.
PublishingBuilt-in scheduler for YouTube Shorts, TikTok, Instagram, LinkedIn, Facebook and X (Pro and up).Exports MP4 files to a folder. No posting or scheduling.
Where it runsAny modern browser.Windows 10 (1903+)/11 64-bit, and Apple silicon Macs on macOS 14+. Not Intel Macs or Linux.

Opus Clip details from opus.pro/pricing and the Opus Clip help center, checked September 27, 2026. Plans change; check their site for current terms. Opus Clip is a trademark of its owner; we're not affiliated.

Opus Clip is the better pick if…

  • You want AI reframing that follows the speaker, virality scores, or posting and scheduling built in.
  • You'd rather not install software, or you're on an Intel Mac, Linux or a Chromebook.
  • You need an English app today. We're not there yet.

OxClipper fits better if…

  • Your sources are long: full podcast episodes, multi-hour livestreams, course recordings, client footage.
  • You'd rather not upload the footage, or you don't want a monthly minute count to decide how much you clip.
  • You want several versions per run and to check every segment yourself before anything is exported.
  • You sell on livestreams and want the recording split by product first.

How it works

From one long video to several clips

This is how the current (Chinese) version works. The English version is planned around the same workflow.

  1. Import

    Drop in videos or whole folders, up to 100 files per project. Existing SRT subtitles work too.

  2. Transcribe

    On your computer with Whisper (the stronger engine for English) or SenseVoice, or with an optional cloud engine that's quoted before you start.

  3. Get clip plans

    AI reads the transcript and proposes 1–10 versions per run: highlights, condensed cuts, topic compilations or mixes.

  4. Review

    Play every segment, nudge in/out points by 0.1 s, remove or reorder. Changes save automatically.

  5. Batch export

    Export the versions you picked as MP4 with captions, titles, music and intros if you want them. Up to 5 at a time.

Straight talk

What it doesn't do

  • AI picks clips from the transcript, not from the picture. It doesn't judge faces, motion or "virality".
  • It doesn't tell speakers apart, so you can't ask for "only what the guest said".
  • No face-tracking reframe, and no posting to social platforms.
  • It isn't fully offline: AI clip planning needs an internet connection and sends the transcript text.
  • Some footage won't yield as many distinct versions as you asked for. You review before you export.
  • The English interface isn't released yet. That's what the waitlist is for.

FAQ

Questions

Is it really local? What leaves my computer?
With the local transcription engines, your video and audio stay on your computer. To generate clip plans, the transcript text (with timestamps) is sent to an AI service. If you choose cloud transcription, the audio is uploaded to that transcription provider. The video file itself is never uploaded.
How much will it cost?
English pricing hasn't been set. In the current Chinese version, local transcription and rendering aren't metered, and AI clip planning is billed by transcript length with an estimate before each run. Waitlist members hear about English pricing first.
When is the English version?
There's no date yet. The app is in use in Chinese today; the English version is in development. Join the waitlist and we'll email you once when it opens.
Can I paste a YouTube or livestream link?
No. It works with video files on your computer (MP4, MOV, MKV, WEBM, AVI, FLV, M4V, TS), plus SRT subtitles if you have them.

Be first to try the English version

One email when it opens. That's it.

No spam, no sharing. Privacy