Upload once.Get every short worth posting.

The engine watches your whole stream — the laughs, the reactions, the moment the room turns — and hands back finished vertical shorts, captioned and ready for TikTok, Reels and Shorts. One ten-hour stream gave 25 of them — in 91 minutes.

Two free hours every month · no card · your link is not stored until you sign in
The whole recording, scored end to end
00:00SCORING EVERY SECOND09:54:00

Gold marks every moment that cleared the bar — and they all become clips. You also get the score for the ones that didn’t.

0posts from one sitting — five weeks of daily content
faster than realtime
0every clip delivered vertical, whatever the source
0plugins or timelines to touch
SOURCE stream_10h.mp4 1280×720 · 30 fps · 44.1 kHz → DELIVERED 1080×1920 DETECTOR ACTIVE

A deliberately unflattering source — a 720p 30 fps recording, the kind most people actually have. Every clip still leaves at 1080 × 1920 with the captions checked pixel by pixel against the screen.

Position
Laughter (4–8 Hz)
Hype density
Event terms /20 s
Speaker
Move across the waveform — the detector reports what it measured at that point.
See it happen

Paste a link. Come back to clips.

This is the workspace doing a real job, replayed in forty seconds: the stages are the engine’s own, in the proportions they took on the ten-hour stream; the clips at the end are the ones it delivered.

vigge.pro/app
Paste a Twitch or YouTube link — or drop a file
Two free hours every month · no card
Processing stream_10h.mp4 · ~91 min
    Nothing runs on your machine — close the tab, we email you when it lands.
    Delivered · 25 shorts · 91 minutes · nothing charged until now
    Download allSchedule to YouTubeShare
    1. Paste
    2. Engine
    3. Delivery
    What arrives

    You send one file. You get a delivery.

    Everything heavy runs on our servers. Close the tab if you like — the work carries on without you, and nothing touches your machine.

    01Vertical shorts, captioned Ready for TikTok, Reels and Shorts. Karaoke captions, a hook title, a progress bar. Every moment that clears the bar becomes a clip — no quota to fill. 9:16MP4
    02The full transcript The whole recording as text, timed and speaker-labelled. Yours to re-use for descriptions, chapters, subtitles or search. SRT + TXTFULL
    03Your original video, subtitled Full length, original quality, captions burned in. A by-product of the analysis — we hand it over rather than throw it away. BONUSMP4
    04The report on what we skipped Every moment we scored and did not keep, with its timestamp and what was said. You can check our judgement instead of trusting it. PER JOBLOG

    MEASURED END TO END ON A 10-HOUR STREAM: 91 MINUTES, DOOR TO DOOR · NOTHING RUNS ON YOUR MACHINE

    What it handles

    Measured on real recordings

    Every number below we measured on real footage and can prove. The methods behind them are ours.

    Finds the reactionsDETECTION

    Laughter, sudden energy, the moment several people talk at once — the engine hears the room turn and does not need the transcript to spell it out. Flat routine chatter is checked on every job and must score zero.

    Flat routine chatter scores 0.00
    Knows who is speakingVOICES

    Separates speakers and gives each their own caption colour. When two voices overlap and it cannot be certain, it leaves the line uncoloured rather than colour it wrongly.

    Recall on a named voice 100 %
    Swedish and English togetherLANGUAGE

    Switching language mid-sentence is expected, not an error case. The engine adapts to what is actually being talked about before it writes a word down.

    High-confidence lines 95 %
    Protects your channelGATE

    Slurs are masked in text and bleeped in audio. Beyond that, moments that read as racist are never cut into a clip at all — because a bleep does not save a clip that is about the joke.

    Runs before selection, on every job
    Captions that are really thereVERIFIED

    Word-by-word karaoke, several speakers in separate screen zones. We then sample the finished file and check the pixels — a caption that failed to render is caught before you ever see it.

    Burned-in text present 24/24 frames
    Length follows contentADAPTIVE

    Not a template. A quick beat stays short; a twelve-turn exchange gets room. Sentences always finish.

    Spread 18–55 s across one batch
    Pricing

    One credit is one hour of stream

    Monthly hours reset each month — extra hours you buy never expire. A failed job is never charged.

    Free
    $0
    Enough to judge the engine on your own footage — every month.
    • 2 hours of stream every month
    • 3 shorts, watermarked
    • Captions and audio mastering
    • Full transcript (SRT + TXT)
    • The whole video subtitled, as a bonus
    • Full detector readout
    Pro
    $24 / month
    Everything the engine can do. One flat price.
    • 100 hours of stream every month
    • Unlimited shorts · no watermark · 1080p
    • Priority in the render queue
    • Top up more hours whenever you need — they never expire
    • Plus everything in Free: YouTube publishing, face-tracking crop, custom words, trim, API
    Questions

    Straight answers

    How do you decide what is a highlight?

    Several independent signals from the audio and the picture, weighted and scored across the whole recording. We publish the result rather than the recipe: every job comes with the score each moment got and the reason the ones we skipped lost. You can check the judgement on your own footage — that is what the two free hours are for.

    Why does the language matter so much?

    Because a transcriber that guesses the wrong context does not degrade gracefully — it produces confident nonsense. The engine works out what is actually being talked about before it commits, which is why Swedish streams that slide into English come out readable instead of mangled.

    What happens to my footage?

    The upload is stored for processing and deleted automatically within 7 days of delivery. We do not train models on your content. Voice profiles exist only if you create them and can be deleted at any time.

    Can I steer the output?

    Yes. Pick who should be in focus, set preferred length, and extend the list of words that disqualify a moment entirely. Every choice the engine made is visible to you afterwards.

    How long does a stream take?

    Short videos are back in a few minutes. Long streams run several times faster than real time — a ten-hour stream came back in 91 minutes. All of it runs on our servers — start the job and close the tab.

    Get started

    Your next short is already in your last stream

    Upload an hour and read the detector output yourself. That is the whole pitch.

    Clip engine v5 · measured, not guessed