AI-Short-Video-Engine orchestrates multiple AI modules in an end-to-end pipeline to transform user-defined text prompts into polished short videos. First, the system leverages large language models to generate a storyboard and script. Next, Stable Diffusion creates scene artwork, while bark provides realistic voice narration. The engine assembles images, text overlays, and audio into a cohesive video, adding transitions and background music automatically. Its plugin-based architecture allows customization of each stage: from swapping in alternative text-to-image or TTS models to adjusting video resolution and style templates. Deployed via Docker or native Python, it offers both CLI commands and RESTful API endpoints, enabling developers to integrate AI-driven video production into existing workflows seamlessly.