Aseiel/VideoHighlighter

What it solves

VideoHighlighter solves the problem of manually scrubbing through hours of raw video footage to find important moments. It automates the discovery of highlights by analyzing video, audio, and motion locally, ensuring your private footage never leaves your machine.

How it works

The app processes video files using a variety of local detectors—such as object detection, motion tracking, and transcript analysis—to score segments based on their significance. You can define custom "composition rules" to combine these signals (e.g., detecting an object within a specific area) to identify events. Every decision is documented in a detailed report that explains exactly why a moment was selected, allowing you to audit the logic behind the highlights.

Who it’s for

It is designed for creators, security-conscious users, and researchers who need to process large volumes of video—such as long streams, security footage, or raw camera cards—without relying on cloud services or internet connectivity.

Highlights

• Local-first privacy: All analysis happens on your machine; no data is uploaded.
• Transparent reporting: Every highlight includes a breakdown of the signals and arithmetic that led to its selection.
• Flexible composition engine: Create custom rules to define what constitutes an "event" by combining different detection signals.
• Automated workflows: Includes an "Auto" pipeline to ingest footage, cut highlights, add music, and build a finished reel.
• Cross-platform support: Runs on Windows, macOS, and Linux with support for Intel, AMD, and NVIDIA hardware acceleration.