mutonby/openshorts

**Open source AI video platform** with 3 tools in one: **Clip Generator**, **AI Shorts (UGC videos with AI actors)**, and **YouTube Studio**.
Real OpenShorts output, not a mock-up. Source: Turn the Tables with Dan and Shoshana Jordan, Heritage of Faith, licensed CC BY.
Two people on camera? OpenShorts stacks them instead of shrinking the wide shot, puts the captions on the seam where they cover nobody, and switches back to a face-tracked crop when the cut goes to one person. The AI picks the layout per video; nothing to configure.
**Two ways to run it, same software either way:**
| | Self-hosted (this repo) | Hosted on openshorts.app |
|---|---|---|
| **Price** | Free forever, MIT | Free plan, paid from $12/mo |
| **Speed** | 5 to 8 min per 8-min video on CPU | About 50s on our NVIDIA GPU |
| **API keys** | Bring your own Gemini, ElevenLabs, fal.ai | Gemini included, nothing to set up |
| **Watermark / limits** | None, ever | Watermark and 20 min/mo on the free plan, neither on paid |
| **Setup** | Docker, 8GB+ RAM, model downloads | Sign in and paste a link |
| **MCP / API for agents** | Same /mcp endpoint, but only while your machine is on | Always-on endpoint at mcp.openshorts.app, API keys in one click |
| **Your data** | Your server | Ours |
Self-hosting is genuinely free and always will be. It costs you a machine, your own API keys and the time to keep it running. The hosted plans exist to cover that hardware and those keys, not to unlock features.
https://github.com/user-attachments/assets/b45fa983-16b4-48b5-ac5b-a267836b9ad9
Video Tutorial: How it works
*Click the image above to watch the full walkthrough.*
---
3 Tools in 1 Platform
1. Clip Generator
Turn your long-form videos — podcasts, webinars, livestreams, vlogs, interviews — into viral-ready 9:16 shorts for TikTok, Instagram Reels, and YouTube Shorts.
2. AI Shorts (UGC Video Creator)
Generate marketing videos with AI actors for **any product or business**. No camera, no studio, no influencer budget. Just describe your product or paste a URL.
- **Two cost modes**: Low Cost (~$0.65/video) and Premium (~$2/video)
- Works for any business: SaaS, restaurants, e-commerce, coaching, local businesses
- AI-generated actors with lip-sync, voiceover, b-roll, and TikTok-style subtitles
- Choose from a shared avatar gallery or upload your own photo
- Publish directly to TikTok, Instagram, and YouTube
3. YouTube Studio
Complete free AI YouTube toolkit: thumbnails, titles, descriptions, and direct publishing.
- AI thumbnail generator with face overlay
- 10 viral title suggestions with refinement chat
- Auto-generated descriptions with chapter timestamps
- One-click publish to YouTube
UGC Video Gallery
All generated videos and avatars are saved to a public gallery with SEO pages for each video.
- Public gallery page with hover-to-play (/gallery)
- Individual SEO video pages with og:video meta tags (/video/{id})
- JSON-LD structured data for search engines
- Avatar gallery with prompt history
---
Key Features
Clip Generator
- **Viral Moment Detection**: Google Gemini 3.1 Flash-Lite analyzes transcripts and scene boundaries to detect 3-15 high-potential moments
- **Runs fully local if you want**: point LLM_BASE_URL at Ollama, LM Studio, vLLM or any OpenAI-compatible server and the moment picker runs on your own model, no Google key needed (see Run without a Google key)
- **Smart 9:16 Cropping**: AI reframing per scene — TRACK mode (MediaPipe + YOLOv8 face tracking), GENERAL mode (blurred background), SPLIT mode (two speakers stacked, captions on the seam) and SCREENCAST mode (screen over presenter); the layout is picked per video by Gemini or forced from the dashboard
- **Auto Subtitles**: faster-whisper with word-level timestamps, styled and burned into clips
- **AI Voice Dubbing**: ElevenLabs integration for 30+ languages with voice cloning (bring your own ElevenLabs key, on the cloud too)