AI Clip Maker for Shorts, Reels & TikTok

Turn one long video into a batch of ready-to-post vertical clips. AI watches the whole recording, finds the Wow moments and cuts them with animated subtitles — no timeline editing, no manual scrubbing.

Try for free

1Finds the moments

One long video · 21 min3 moments found by AI

The AI reads the whole conversation and cuts the parts that stand on their own — each with a title and captions.

2Finds the frame

Each shot is checked for faces and who is talking — the 9:16 frame is taken from there, not from the middle.

Original 16:9
Your 9:16 clip

Footage: “IELTS Speaking Test – Perfect Band 9” by IELTS Advantage, CC BY — excerpts, reframed.

How it works

  1. 1

    Upload your video

    Drop in a stream VOD, podcast, interview or any long recording.

  2. 2

    AI finds the moments

    The transcript is analyzed to detect the most engaging, quotable and emotional fragments.

  3. 3

    Download vertical clips

    Each moment becomes a 9:16 clip with animated word-by-word subtitles and a title overlay.

Real moment detection

AI reads the full transcript and picks fragments that hook viewers — punchlines, insights, reactions — not random cuts.

Vertical by default

Clips come out in 9:16 for Shorts, Reels and TikTok. The frame finds the faces in every shot and follows whoever is talking, so an off-centre speaker stays in the picture.

Animated subtitles built in

Word-by-word highlighted captions are burned into every clip — the style short-form viewers expect.

Minutes, not hours

A typical video is transcribed, analyzed and cut in 2–4 minutes. Batch a week of content in one coffee break.

Why an AI clip maker beats manual editing

Repurposing long-form content by hand is the single biggest time sink for creators. You rewatch an hour of footage, guess which fragments might perform, cut them, reframe them vertically, then caption every line. With Wow Cut Video the entire chain — transcription, moment detection, cutting, subtitling — runs automatically from one upload.

Under the hood, speech is transcribed with a Whisper-class model, then a language model scores the transcript for hooks: strong claims, emotional spikes, jokes, story beats. You choose how many clips you want and the AI returns the strongest candidates, each trimmed to short-form length and captioned.

The speaker stays in the frame

Cutting a 16:9 video to 9:16 keeps a third of its width. A plain centre crop keeps the middle third — and in an interview or a podcast that is often the empty space between two people, with both of them cut in half.

Wow Cut looks at every shot of each moment: it finds the faces, and when two people sit too far apart to fit in one vertical frame, it checks whose mouth is moving and takes the frame from there. The window changes only where the original video cuts, so it never drifts. You can always move the frame by hand in the editor.

Made for streamers, podcasters and coaches

Gaming streams, podcast episodes, webinars, sermons, lectures — anything with speech works. The clip maker handles source audio in about 100 languages and can output subtitles in 12, so one recording can feed several audiences at once.

The first analysis is free and takes minutes, so you can judge the results on your own footage before paying anything.

Frequently asked questions

How does the AI decide what to clip?

It transcribes the full video, then a language model scores the transcript for engaging fragments — punchlines, strong statements, emotional moments — and cuts clips around the highest-scoring ones.

Will the person speaking stay in the vertical frame?

Yes. For each shot Wow Cut finds the faces and places the 9:16 frame on the person who is talking; if two people fit, both stay in. It happens automatically before you review the clip, and you can switch it off or reframe by hand.

What video formats can I upload?

Common formats like MP4, MOV, MKV and WebM work. On the desktop app for macOS you can also paste a YouTube link instead of uploading a file.

How long does processing take?

Usually 2–4 minutes per video: transcription runs on a fast Whisper model and cutting is a single ffmpeg pass per clip.

Is there a free plan?

Yes — the first analysis is free, no card required. See current plans →

Do the clips include subtitles?

Yes, every clip gets animated word-by-word subtitles burned in, with the active word highlighted. You can review and edit the transcript before cutting.

Try it on your own footage

First analysis is free — upload a video and see your clips in minutes.

Try for free