Auto Project Narrator – Text to Video Converter

The growing demand for a better way to describe how a technical project will be completed has created the need for intelligent systems that automatically create multimedia (e.g., video) explanations of a project from text only. Preparing a presentation using traditional methods typically requires manually putting together slides, creating images, narrating the presentation, and doing a video demo; all of which can take time and effort to accomplish. This project proposes an artificial intelligence-based system to create a video description of a project automatically using NLP, RAG, Stable Diffusion and neural TTS technologies. The system takes a user-provided description of a project and builds structured documentation using a combination of retrieve systems and Large Language Models (LLMs). The documentation that is generated is converted into a multi-scene storyboard that uses the content from the documentation to create each scene of a video. Each visual prompt created from the storyboard is used as input to the Stable Diffusion model in a high-performance GPU cloud computing environment to generate images for each scene. Finally, the speech output from the neural TTS synthesis process is used to produce clear and natural audio to accompany each video scene. The generation methodology's final output, an explanatory video with a project report summary, will consist of images and audio generated and synchronized together by the new TDMs and then assembled using a video-processing method. Empirical evaluation of the new system indicates that it will automate the creation of a substantial portion of the presentation of a multimedia project, thus reducing the number of hours required for manual production of completed media and increasing the clarity of presentation as well as the attractiveness of the presentation. The new framework is designed to allow for easy scalability to enable the automated generation of educational media and provide intelligent documentation of multimedia.