The free, open-source Opus Clip alternative

For creators doing it all themselves

Our mission: Clips Kitty is a free, open-source AI video editor built to help small streamers and creators turn their long-form videos and livestreams into short-form content without hiring an editor or spending hours editing footage themselves.

If you are growing a channel, you are probably the one filming it, streaming it, editing it and posting it. Clipping is how people find you, and it is usually the first thing that gets dropped. An editor is a cost most channels cannot justify yet, clipping tools charge for every video, and cutting them by hand takes a day you needed for something else. So the clips do not get made.

That is the reason this exists. Clips Kitty runs on your own computer, so it costs nothing to use: no subscription, no credits, no charge per clip, no limit on how many you make. If you have a PC and something worth posting, you can promote your channel without paying anyone, me included.

Clipping tools like Opus Clip charge a monthly fee or a price per video. Clips Kitty does not charge anything. It runs on the computer you already own. Whether you are just starting out or already growing, the clips should not be the thing you have to pay for. Here is the full Opus Clip comparison, prices and all.

How it works

Every step that makes the clip runs on your PC unless you choose otherwise: OpenRouter, signed in with your own account, can run the AI or the transcription when your PC is too old, and posting sends the finished clips. Otherwise the only thing that touches the network in a normal run is downloading the video you asked for.

1. Watching a channel, if you want it New videos on a YouTube, Twitch or Kick channel you watch are spotted (YouTube's through its RSS feed) and queued by themselves.
2. Video in A YouTube link, a Twitch or Kick VOD, or a file from your PC.
3. Transcription faster-whisper with word-level timing, so captions land on the right syllable and clips start on a real sentence. On your PC, or through OpenRouter.
4. Signal analysis Loudness spikes, laughter-shaped bursts, scene cuts, motion and on-screen reactions, measured across the whole video. For a match, the score box and the crowd too.
5. Scoring A language model reads the transcript alongside those signals, so a quiet line during an explosive moment is judged correctly. Local through Ollama by default, or through OpenRouter.
6. Framing The 9:16 crop follows whoever is speaking, follows the ball in a match, or puts the webcam and the game together for a game stream. A stream that was vertical all along keeps its own layout. Crops are never stretched.
7. Captions and titles Word-synced captions in your style, plus a title, description and hashtags, all editable before you export.
8. Languages and export Translate, subtitle or dub a clip into 19 languages, then export to organized folders with clean file names.
9. Posting, if you want it Send a clip, or a whole batch, to nine platforms at once through a publishing service you connect: now, on a schedule, or by itself for a channel you watch. Optional and off by default.

What you get

What it's built for

Worth knowing before you download, so you're not guessing why a clip came out the way it did.

• People on camera, talking. IRL, just chatting, podcasts, vlogs, interviews. This is what the clip-picking and the framing are tuned for, and it's what gets tested on real streams before anything ships.
• Game streams and reaction videos. Gaming / Reaction puts the streamer's webcam and the game together in one of eleven layouts, picked on the video's own frames, and scores the in-game moments and the reactions to them. Characters inside the game aren't taken for the streamer.
• Soccer matches. Tick Sports and a match's goals, saves and cards become clips, found from the score box, the crowd and the commentary. Club or phone footage has no score box or commentary, so its goals come from the match events you give it. Basketball and cricket are next.
• VTubers aren't supported. The framing looks for a real person on camera; with an avatar, the game fills the screen instead.
• Reaction videos raise a copyright question. Re-uploading someone else's footage is worth settling yourself before you post it.

Nothing here refuses to run. Feed it anything and it will produce clips. These are the cases where it's doing less thinking than it looks like, and where you should expect to reach for the editor more often.

What you need to run it

Everything happens on your own machine, so your hardware is what decides how long a stream takes. Worth checking before you download.

A graphics card is optional. Without one everything runs on the CPU — slower, but complete. The RTX 2060 is where the GPU path starts working; GTX 10-series and older fall back to the CPU and are below the minimum.

Below the minimum it may still run — nothing refuses to start — but it isn't supported, and hardware from before roughly 2019 will be slow enough that the app feels broken when it's actually working.

Why local matters

Getting started

Download ClipsKitty-Web-Setup.exe and run it. A setup wizard takes it from there. It checks your computer and downloads an AI model sized to your graphics card.

Prefer a terminal? winget install ColinGPT9.ClipsKitty installs the same thing.