rt-vlm

Official

Real-time video analysis and captioning via NVIDIA VLM microservice.

AuthorNVIDIA-AI-Blueprints
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill enables users to generate dense captions and alerts for video streams and stored files, facilitating automated scene understanding and monitoring.

Core Features & Use Cases

  • Dense captioning for stored videos and live RTSP streams to summarize scene content.
  • Alert generation based on prompt design to detect anomalies or specific events in videos.
  • Use Case: Automatically process warehouse surveillance footage to produce real-time summaries and flag incidents such as missing safety gear or safety violations.

Quick Start

Use the rt-vlm skill to upload a video file, generate captions for each 10-second segment, and view streaming results with a natural language instruction.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: rt-vlm
Download link: https://github.com/NVIDIA-AI-Blueprints/video-search-and-summarization/archive/main.zip#rt-vlm

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.