Text-To-Video-AI

Why we included this project

Text-To-Video-AI takes a plain topic and turns it into a finished short-form clip by wiring several AI services together. You hand it a subject, and it writes a script with an LLM, generates a voiceover, pulls matching B-roll, and adds timed captions before composing everything into a portrait or landscape MP4. That makes it handy for content creators and small teams who want a repeatable pipeline instead of editing each video by hand. You can swap the providers used for script, speech, and video generation, and control caption styling and orientation from a config file. It is also a decent reference for orchestrating multiple generative APIs if you would rather build your own pipeline.