An autonomous YouTube content pipeline that runs 24/7. 12 engines work together: trend detection, dual AI script generation (Qwen + Ollama cross-scoring), TTS voiceover, B-roll footage, cinematic FFmpeg rendering, and scheduled upload. Unlike existing AI video tools that produce generic content, Mesin Cuan uses dual parallel AI with cross-provider scoring to eliminate AI slop. Self-hosted, MIT license, runs on Ollama cloud with no GPU needed.
I built this because I was tired of spending 8+ hours editing a single video. Hiring editors was too expensive and existing AI tools felt generic and too pricey.
The breakthrough was the dual AI system — two models compete and score each other's output. The better script wins. This eliminates the "AI feel" most tools have.
Built solo at 18. Open source so others can build on it. Would love feedback from the PH community.
Report
No reviews yetBe the first to leave a review for Mesin Cuan Viral Architect