CutScript

An open-source, local-first, Descript-like text-based audio and video editor powered by AI. Edit audio/video by editing text — delete a word from the transcript and it's cut from the audio/video.

Architecture

• Electron + React desktop app with Tailwind CSS
• FastAPI Python backend (spawned as child process)
• WhisperX for word-level transcription with alignment
• FFmpeg for video processing (stream-copy and re-encode)
• Ollama / OpenAI / Claude for AI features (filler removal, clip creation)

Quick Start

Prerequisites

• Node.js 18+
• Python 3.10+
• FFmpeg (in PATH)
• (Optional) Ollama for local AI features

Install

# Root dependencies (Electron, concurrently)
npm install

# Frontend dependencies (React, Tailwind, Zustand)
cd frontend && npm install && cd ..

# Backend dependencies
cd backend && pip install -r requirements.txt && cd ..

Run (Development)

# Start all three (backend + frontend + electron)
npm run dev

Or run them separately:

# Terminal 1: Backend
cd backend && python -m uvicorn main:app --reload --port 8642

# Terminal 2: Frontend
cd frontend && npm run dev

# Terminal 3: Electron
npx electron .

Project Structure

cutscript/
├── electron/          # Electron main process
│   ├── main.js        # App entry, spawns Python backend
│   ├── preload.js     # Secure IPC bridge
│   └── python-bridge.js
├── frontend/          # React + Vite + Tailwind
│   └── src/
│       ├── components/  # VideoPlayer, TranscriptEditor, etc.
│       ├── store/       # Zustand state (editorStore, aiStore)
│       ├── hooks/       # useVideoSync, useKeyboardShortcuts
│       └── types/       # TypeScript interfaces
├── backend/           # FastAPI Python backend
│   ├── main.py
│   ├── routers/       # API endpoints
│   ├── services/      # Core logic (transcription, editing, AI)
│   └── utils/         # GPU, cache, audio helpers
└── shared/            # Project schema

Features

Keyboard Shortcuts

API Endpoints

License

MIT License — see LICENSE for details.