LLM-Powered Video Editing via Natural Language Scripting with Local Models

Live demonstration of a local‑LLM video editor that builds and edits video structures from natural language prompts, translating changes into JSON for real‑time playback.

Overview

Live-demoing our video editor leveaging local llms (eg Gemma3/Qwen3 w/ Ollama) for content generation and editing.
We’ll walk through the core workflow:

generating the initial video structure (narration, image/video sequence defined in our custom JSON spec) from a prompt
editing the video by modifying a human-readable script representation; the LLM translates these natural language changes into precise JSON operations to update the underlying video spec
showing how the editor syncs the script, timeline, and Remotion-based player preview in real-time

We’ll highlight the technical challenge of reliably mapping freeform text edits to structured JSON modifications and how we use prompt engineering

Video

Tech stack