FujiwaraChoki / supoclip
An open-source OpusClip alternative
AI Architecture Analysis
This repository is indexed by RepoMind. By analyzing FujiwaraChoki/supoclip in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.
Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.
Repository Overview (README excerpt)
Crawler viewFuck OpusClip. ... because good video clips shouldn't cost a fortune or come with ugly watermarks. OpusClip charges $15-29/month and slaps watermarks on every free video. SupoClip gives you the same AI-powered video clipping capabilities - completely free, completely open source, and completely watermark-free, while still providing you with a hosted version, that doesn't cost the same amount as your mortgage. > For the hosted version, sign up for the waitlist here: SupoClip Hosted Why SupoClip Exists The OpusClip Problem OpusClip is undeniably powerful. It's an AI video clipping tool that can turn long-form content into viral short clips with features like: • AI-powered clip generation from long videos • Automated captions with 97%+ accuracy • Virality scoring to predict viral potential • Multi-language support (20+ languages) • Brand templates and customization **But here's the catch:** • **Free plan limitations**: Only 60 minutes of processing per month • **Watermarks everywhere**: Every free video gets branded with OpusClip's watermark • **Expensive pricing**: $15/month for Starter, $29/month for Pro • **Processing limits**: Even paid plans have strict minute limits • **Vendor lock-in**: Your content and workflows are tied to their platform The SupoClip Solution SupoClip provides the same core functionality without the financial burden: → ✅ **Completely Free** - No monthly fees, no processing limits → ✅ **No Watermarks** - Your content stays yours → ✅ **Open Source** - Full transparency, community-driven development → ✅ **Self-Hosted** - Complete control over your data and processing → ✅ **Unlimited Usage** - Process as many videos as your hardware can handle → ✅ **Customizable** - Modify and extend the codebase to fit your needs Quick Start Prerequisites • Docker and Docker Compose • An AssemblyAI API key (for transcription) - Get one here • An LLM provider for AI analysis - OpenAI, Google, Anthropic, or Ollama • Clone and Configure Create a file in the root directory: • Start the Services This starts: • **Frontend**: http://localhost:3000 • **Backend API**: http://localhost:8000 (docs at /docs) • **PostgreSQL**: localhost:5432 • **Redis**: localhost:6379 • Wait for Initialization First-time startup takes a few minutes. Check progress with: Wait until you see health checks passing for all services. • Access the App Open http://localhost:3000 in your browser, create an account, and start clipping! If you enable DataFast, also verify that: • loads from your own app domain • requests are proxied through your app domain • custom goals appear after successful sign-up, sign-in, task creation, billing, feedback, or waitlist actions Troubleshooting **Backend fails to start with API key error:** • Make sure you've set the correct LLM provider AND its corresponding API key in • Default is which requires • If using , you MUST set • If using , run Ollama and (optionally) set • Rebuild after changing : **Videos stay queued / never process:** • Check worker logs: • Ensure Redis is healthy: • Verify API keys are correct **Performance tuning (default is fast mode):** • • to cap clip count in fast mode • for fastest transcript model • View aggregate metrics: **Prisma errors on Windows:** • Run to clear volumes • Run to rebuild **Frontend shows database errors:** • Wait for PostgreSQL to fully initialize (check logs) • The database is automatically created on first run **Font picker is empty / cannot select or upload fonts:** • Add fonts to – see backend/fonts/README.md for TikTok Sans and custom fonts • Ensure is set in when using the hosted/monetized setup • Font upload is Pro-only when monetization is enabled; self-hosted users can upload freely **Subscription emails are not sending:** • Set and in • must be a verified sender/domain in your Resend account • The backend sends the “thank you for subscribing” email on • The backend sends the “sorry to see you go” email on Testing SupoClip now has a layered automated test setup: • for backend unit and integration tests • and Testing Library for frontend route and component coverage • for a small seeded browser smoke suite Repo-level entrypoints: App-level entrypoints: Local test runs expect PostgreSQL and Redis to be available. The easiest path is to start the stack with , then run the commands above. CI runs the same layers in GitHub Actions with Postgres and Redis service containers. Documentation Detailed documentation now lives in . Start with: • • • • • • • Hosted Billing Emails When you run SupoClip with monetization enabled ( ), subscription lifecycle emails are sent through Resend by the backend: • sends the thank-you-for-subscribing email • sends the sorry-to-see-you-go email Required env vars for this flow: • • • • • • Local Development (Without Docker) See CLAUDE.md for detailed development instructions. License SupoClip is released under the AGPL-3.0 License. See LICENSE for details.