Edit videos at the speed of thought

Demo Video · Demo Website · Report Bug · Request Feature

CutOS is an AI-first video editor that understands natural language. Describe your edits in plain English, and watch them happen instantly. No steep learning curves, no complex menus—just tell the AI what you want.

"Split this clip at 10 seconds and add a vintage effect" — Done.

• Conversational Editing - Edit videos by describing what you want
• Semantic Search - Find moments in footage using natural language
• 29-Language Dubbing - Translate while preserving emotion and timing
• Real-Time Effects - GPU-accelerated WebGL rendering
• Web-Based - No installation required, works in your browser

CutOS Landing Page

• Multi-Track Timeline - 2 video tracks + 2 audio tracks with non-destructive editing
• Precision Tools - Split, trim, extend clips with frame-perfect accuracy
• Drag & Drop - Magnetic snapping for seamless clip placement
• Real-Time Preview - Canvas-based playback with instant effect rendering
• Effect Library - Grayscale, sepia, VHS, glitch, cyberpunk, ASCII art, and more
• Chromakey - GPU-accelerated green screen removal (any color)
• Undo/Redo - Full editing history with keyboard shortcuts

Find exact moments in hours of footage with natural language queries

Real-time chromakey with GPU acceleration

AI morph transition - made directly with CutOS

• Export to MP4/WebM at 1080p
• Cloud storage with Supabase
• Auto-save your projects
• Multiple quality presets (Low/Medium/High)

• Node.js 18+
• npm/pnpm
• Supabase account
• API keys (OpenAI, TwelveLabs, ElevenLabs, Kling)

# Clone the repository
git clone https://github.com/shamsharoon/cutos.git
cd cutos

# Install dependencies
npm install

# Copy environment variables
cp .env.example .env.local

# Add your API keys to .env.local
# See "Environment Variables" section below

Create a .env.local file:

# Supabase
NEXT_PUBLIC_SUPABASE_URL=your_supabase_url
NEXT_PUBLIC_SUPABASE_ANON_KEY=your_anon_key
SUPABASE_SERVICE_ROLE_KEY=your_service_role_key

# AI Services
OPENAI_API_KEY=your_openai_key
TWELVELABS_API_KEY=your_twelvelabs_key
ELEVENLABS_API_KEY=your_elevenlabs_key
KLING_ACCESS_KEY=your_kling_access_key
KLING_SECRET_KEY=your_kling_secret_key

npm run dev

Open http://localhost:3000

User: "Split the clip at 15 seconds and add a vintage VHS effect"
AI: ✓ Split at 15s. Applied VHS effect.

User: "Remove the green screen from intro.mp4"
AI: ✓ Green screen removed from 'intro.mp4'.

User: "Dub this video in Spanish"
AI: ✓ Dubbing to Spanish... (this may take a moment)

Search: "person walking on beach"
→ Finds all clips with people walking on beaches

Search: "car driving at night"
→ Finds nighttime driving scenes

cutos/
├── app/                      # Next.js App Router
│   ├── api/                  # API routes
│   │   ├── agent/           # AI agent endpoint
│   │   ├── dub/             # Dubbing API
│   │   ├── remove-noise/    # Voice isolation
│   │   └── twelvelabs/      # Video search
│   ├── projects/            # Project pages
│   └── page.tsx             # Landing page
├── components/              # React components
│   ├── ui/                  # shadcn/ui components
│   ├── editor-shell.tsx     # Main editor
│   ├── timeline.tsx         # Timeline component
│   └── media-panel.tsx      # Media library
├── lib/                     # Utilities
│   ├── agent/              # AI agent logic
│   ├── supabase/           # Database client
│   └── utils.ts            # Helper functions
└── public/                  # Static assets

1. Record with OBS/QuickTime

   • Record your screen at 1920x1080
   • Keep recordings under 30 seconds for optimal file size
   • Focus on one feature at a time

2. Convert to GIF

   # Using FFmpeg
   ffmpeg -i input.mp4 -vf "fps=15,scale=1000:-1:flags=lanczos" -c:v gif output.gif
   
   # Or use online tools:
   # - https://ezgif.com/video-to-gif
   # - https://cloudconvert.com/mp4-to-gif

3. Optimize GIF Size

   # Using gifsicle
   gifsicle -O3 --colors 256 output.gif -o optimized.gif

cutos/
├── docs/
│   ├── demo.gif              # Main demo GIF (homepage)
│   ├── effects-showcase.png  # Effects preview
│   └── images/
│       ├── editor-interface.png
│       ├── ai-chat.png
│       ├── effects-panel.png
│       ├── timeline-editing.gif
│       └── search-demo.gif
└── public/
    └── demo.mp4              # Demo video for landing page

• Use full editor interface at 1920x1080
• Crop to show relevant sections
• Add subtle drop shadows in post
• Use dark mode for consistency
• Compress with TinyPNG or similar

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the project
2. Create your feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

• Voice isolation requires clips to be uploaded to cloud storage first
• Morph transitions only work between sequential clips on the same track
• Large video files (>500MB) may experience slower processing

This project is licensed under the MIT License - see the LICENSE file for details.

• TwelveLabs - Semantic video understanding
• ElevenLabs - Voice AI technology
• OpenAI - GPT-4o for intelligent editing
• Kling AI - Morph transition generation
• Supabase - Backend infrastructure
• Vercel - Hosting and deployment

Team:

• Julian Cruzet
• Shams Haroon
• Vincent Wong
• Jonathan McKesey

Project Link: https://github.com/shamsharoon/cutos

Devpost: https://devpost.com/software/cutos

Demo Video: https://youtu.be/t0zHzwyXm_Q

Live App: https://cutos.vercel.app