待翻译：Clips Kitty Open-source local AI video clipping and editing

AI 服务暂时不可用，以下为来源正文，待恢复后补全翻译。

Notifications You must be signed in to change notification settings Fork 4 Star 30 BranchesTags Open more actions menu Latest commit History 438 Commits 438 Commits Folders and files NameName Last commit message Last commit date .github .github analysis analysis config config core core creator creator docs docs examples examples feedback-relay feedback-relay llm llm longform longform multilingual multilingual packaging/winget packaging/winget publish publish scripts scripts server server site site sources sources tests tests third_party third_party transcription transcription twitch-proxy twitch-proxy ui ui video video video_editor video_editor web web whop-app whop-app .dockerignore .dockerignore .gitattributes .gitattributes .gitignore .gitignore ARCHITECTURE.md ARCHITECTURE.md CHANGELOG.md CHANGELOG.md CODE_OF_CONDUCT.md CODE_OF_CONDUCT.md CONTRIBUTING.md CONTRIBUTING.md Dockerfile Dockerfile KNOWN-ISSUES.md KNOWN-ISSUES.md LICENSE LICENSE NOTICE NOTICE README.md README.md ROADMAP.md ROADMAP.md SECURITY.md SECURITY.md clips-studio.spec clips-studio.spec docker-compose.yml docker-compose.yml main.py main.py pyproject.toml pyproject.toml requirements-build.txt requirements-build.txt requirements.txt requirements.txt Repository files navigation Clips Kitty was called Clips Studio until version 1.1.3, renamed to meet Microsoft Store naming requirements. Same app, same repository, same data. Turn long streams and videos into ready-to-post Shorts, Reels, and TikToks — entirely on your own machine. Clips Kitty is a free, open-source AI clip generator and video editor for creators: paste a YouTube, Twitch, or Kick link and it finds the best moments, crops them to 9:16 with the speaker kept centred, burns in word-synced captions, and writes titles, descriptions, and hashtags. No cloud AI. No subscription. No per-clip fees. No upload of your footage to anyone. Why it exists: most creators growing a channel are doing all of it themselves — filming, streaming, editing, posting. 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 per video or per month, and cutting them by hand takes a day you needed elsewhere. This runs on hardware you already own, so it costs nothing to use and there is no cap on how many clips you make. Local AI video processing · AI clip generator · Twitch clip generator · Kick clip generator · YouTube Shorts automation · AI video editor · open-source OpusClip alternative Contents What it does How it works Features What it's built for Requirements Install and run Pick your AI model Tested hardware and performance Supported platforms Supported languages GPU acceleration Command line use Build on it Architecture Contributing Roadmap License What it does You give Clips Kitty a long video. It gives you back a folder of finished vertical clips you can post, plus a studio to review and fix them before you do. It is built for the content most clipping tools handle worst: live streams, IRL and talking-head footage, podcasts, and gym/fitness content — long, loosely structured videos where the good moments are buried and a transcript alone won't find them. How it works Video input (YouTube · Twitch VOD · Kick VOD · local file) │ ▼ Transcription faster-whisper, word-level timestamps, local │ ▼ AI video analysis audio · visual · reaction signals, computed │ over the whole video in 1-second bins ▼ Clip detection local LLM scores the transcript in context of and scoring those signals; signal peaks become candidates │ too, so laughs and hype aren't missed ▼ Video editing YOLOv8 pose tracking + TalkNet active-speaker │ detection → 9:16 crop that cuts to whoever is │ speaking; trims, cuts, watermark ▼ Captions/subtitles word-synced, burned in, fully editable │ ▼ Multilingual translate, subtitle, or dub into 19 languages │ ▼ Export organized folders, clean filenames, metadata Every stage above runs on your computer. The only thing that touches the network in a normal run is downloading the source video. The stages in detail Transcription — faster-whisper. Word-level timestamps, running on CUDA where available and falling back to CPU. Word timing is what makes captions land on the right syllable and clips start on a real sentence boundary. AI clip scoring. The transcript is one signal among five. Audio gives loudness spikes, burst density (what laughter and applause look like), and silence→explosion payoff shapes. Visual gives scene cuts, motion, and face-area changes. A reaction signal fuses those. Each is normalized within that video, so a quiet podcast and a screaming stream both produce meaningful peaks. Where real audience data exists — Twitch chat replay measured by unique chatters, YouTube's most-replayed heatmap — it adds a small capped bonus. The local LLM sees the transcript plus a timeline of those events, so it can weigh "the words are mild but the room exploded" correctly. Because small models score everything in a narrow band, the finalists then get compared head-to-head in one rerank call — relative judgment is much easier for a 7B model than absolute scoring. Creator Profiles. The app builds a knowledge base per creator across their videos: recurring topics, series, collaborators, running jokes, and ongoing storylines. That context helps it write accurate titles and spot callbacks. It is deliberately conservative — a catchphrase has to actually repeat before it counts, knowledge that stops being mentioned goes dormant, and every score contribution from it is additive, capped, and can be switched off. Video editor. Non-destructive: trims, internal cuts, mutes, muted words, volume, fades, speed, hook text, music, and watermark are stored as operations and applied at render time. There's an AI edit chat too — "make it 5 seconds longer", "the caption says gost, it should say ghost" — where the model proposes and validated code applies. Long-form processing. An opt-in 16:9 path using the same analysis: horizontal clips, X/Twitter-length cuts, a best-of highlight reel, or the full stream with dead air removed. Multilingual pipeline and AI dubbing. Captions are translated and shown for review before anything is written or burned, so a bad line gets fixed while it's still fixable. A glossary protects channel names, sponsors, and in-jokes from being translated. Dubbing uses local TTS with auditionable voices. Local GPU acceleration. CUDA for detection and transcription, hardware video encoding via NVENC/AMF/QSV (auto-detected, with CPU fallback), and the LLM on GPU through Ollama. Features Multimodal clip detection — moments scored 0–100 by fusing what's said, audio excitement, visual activity, on-screen reactions, and hook/payoff strength. Every clip clearing the quality bar is kept, with no arbitrary cap. Speaker-aware face tracking — YOLOv8 pose detection keeps the subject centred, and in group footage the camera follows whoever is actually speaking, decided by TalkNet active-speaker detection from the face and the audio together rather than from movement. When the speaker changes the framing cuts to them instead of panning across, the way an editor would. Crop-only framing: never stretched, never distorted. Podcast mode — for multi-camera footage, each shot gets its own steady crop on one person, so cuts land on a face with no panning. Within a shot the subject is chosen by mouth motion, falling back to the most prominent face. Editable burned-in captions — word-synced, in your style: colour, size, position, words per line, casing, or off. Fix a transcription mistake line by line before export. AI edit chat — describe what's wrong in plain language and it re-edits. AI titles, descriptions, and hashtags, all editable before export. Creator Profiles — the app learns each creator over time to pick and title clips better. Everything stays on your computer, and you can inspect, correct, or wipe it. Multilingual publishing — 19 languages, with review before anything is burned. AI dubbing — local text-to-speech with voice auditioning per language. Long-form export — 16:9 clips, highlight reels, or a de-duplicated stream edit. Watermark and branding profiles — per-creator defaults applied automatically. Model manager — swap the AI brain from inside the app; download, remove, and switch models with progress bars and no terminal. In-app feedback — bug reports with auto-collected diagnostics, no account needed. Accessible UI — keyboard focus, reduced-motion support, adjustable font and size. What it's built for Everything runs on any video you give it. These are the cases where it's doing more or less thinking than the feature list suggests, so nothing comes as a surprise: Content How it does IRL, just chatting, podcasts, vlogs, interviews What it's tuned for and what gets tested on real streams before release Gaming and split-screen Not shipped yet. Framing did not reliably find the part of the screen where the action was, and subject tracking mistook characters inside the game for the streamer — to a person detector, a person on screen is a person on screen. The result was clips centred on the wrong human, so it is held back rather than shipped half-working Reaction videos Not yet either, and for a related reason. Clips are chosen from what's said, and it can't see the video you're reacting to — so the moment that made the clip is invisible to it Clip selection is transcript-and-signal driven. When the funny thing is visual only and nobody comments on it, expect to find it yourself in the editor. Requirements If you use the installer, this is the whole list: Windows PC (the Python engine should run on Linux/macOS; the app is developed and tested on Windows). No Mac build exists and the maintainer has no Mac to test one on — see #62 if you have one and want to help 16 GB of RAM. Not a suggestion: 8 GB will analyse a whole video and then render nothing, which looks like a crash rather than a memory limit Recommended: an NVIDIA GPU (see GPU acceleration) Around 20 GB free, plus room for the videos you clip Running from source needs the things the installer would otherwise bundle for you: Python 3.10+ and Node.js 18+ FFmpeg on your PATH Ollama with a model pulled: ollama pull gemma:7b Install and run The easiest way is the Microsoft Store. One click, it updates itself, and Windows raises no security prompt — Microsoft certified and signed the package, so the SmartScreen warning described below does not appear at all. Or grab the installer. The latest Web Setup from Releases and run it. It carries the app, the Python engine, every library, FFmpeg, the AI runtime and all the detection and transcription weights — no Python, no PATH, no terminal, and no second program to install. The one thing it doesn't carry is the language model itself, because those ship under licences the person downloading has to accept rather than something that can be accepted on your behalf. The setup wizard starts that download by itself, picks the size that suits your graphics card, and shows a progress bar. So: one download, one double-click, one progress bar. After that it runs offline. Windows will warn that the app is unsigned the first time you run it — click More info → Run anyway. A signing certificate is on the list. From source git clone https://github.com/ColinGPT9/clips-studio cd clips-studio pip install -r requirements.txt cd ui npm install npm run dev # opens the Clips Kitty desktop app The app start [truncated for AI cost control]