How I Create AI Demo Videos for My Hackathon Projects
Using a local LLM with vLLM, Microsoft Edge TTS, and AI tools to turn project demos into clear, engaging videos. Why I built this workflow Building a hackathon project is only half the work. You also need to explain the problem, show the product working, and make the value obvious to judges. I wanted a repeatable way to create narrated demo videos without depending entirely on expensive…
Building a hackathon project is just the beginning. You also need to explain the problem, demonstrate the product working, and make the value clear to judges. The author wanted a repeatable method to create narrated demo videos without relying solely on expensive cloud APIs or recording voiceovers. The workflow combines a local language model for script creation, Microsoft Edge TTS to turn the script into spoken audio, and additional AI tools for visuals and subtitles.
The local language model assists in writing or refining the narration, while Microsoft Edge TTS converts the script into audio. Other AI tools help generate supporting visuals, diagrams, subtitles, or scene ideas. The screen recording and video editing tools showcase the real project and compile the final video. The goal is not to create an AI-generated video pretending to be the product, but rather to clearly explain the real product with AI's help in speeding up production.
The workflow involves collecting project information, generating a scene-by-scene script using the local LLM, generating the voiceover with Microsoft Edge TTS, recording the real product, adding visuals and editing in a video editor, and finally assembling the final hackathon demo video. The setup is reusable, flexible, and gives more control over the production process, albeit with some trade-offs such as hardware requirements for vLLM and reliance on an online service for Edge TTS.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
