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 67-minute Deadlock evening gave 33 of them — in 29 minutes.
Gold marks the moments that became clips — the phone plays the one marked ▶. Pick a recording or tap a card. You also get the score for every one that didn’t.
Real shorts the engine cut from our own recordings — exactly what you get back.
A real job: a SMITE session as our VTuber Rougeina, straight from OBS. Every gold band below became a short — move across the waveform to see what the engine heard at that moment.
The workspace doing our five demo jobs — the same recordings as the phone at the top — each replayed in about half a minute. The stages and the minutes are the real ones from the engine’s log; the shorts at the end are the ones it delivered.
Everything heavy runs on our servers. Close the tab if you like — the work carries on without you, and nothing touches your machine.
MEASURED END TO END ON A 67-MINUTE RECORDING: 33 SHORTS IN 29 MINUTES, DOOR TO DOOR · NOTHING RUNS ON YOUR MACHINE
Every number below we measured on real footage and can prove. The methods behind them are ours.
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.
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.
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.
Any game, any topic, any language. Nothing you say is bleeped, masked or left out — the engine clips what you said, the way you said it. The only line is the law.
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.
Not a template. A quick beat stays short; a twelve-turn exchange gets room. Sentences always finish.
Monthly hours reset each month — extra hours you buy never expire. A failed job is never charged.
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.
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.
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.
Yes. Pick the kinds of moments you want more of — laughs, kills, stories — set a preferred clip length, and add your own words so names and game terms come out spelled right. Every choice the engine made is visible to you afterwards.
Short videos are back in a few minutes, long ones well under their own length — a 67-minute Deadlock evening came back as 33 shorts in 29 minutes. All of it runs on our servers — start the job and close the tab.
Upload an hour and read the detector output yourself. That is the whole pitch.
Clip engine v5 · measured, not guessed