What problem does it solve?
This Skill provides a comprehensive platform for understanding, searching, editing, and generating video and audio content, streamlining complex media workflows.
Core Features & Use Cases
- Video Ingestion & Streaming: Upload local files or URLs, ingest live RTSP feeds, and get playable stream links.
- Content Understanding: Index spoken words and scenes for powerful semantic and temporal search, returning exact moments with timestamps and evidence.
- Media Editing & Generation: Transcode, normalize, edit timelines, add overlays, generate subtitles, and create new media assets.
- Desktop Capture: Record screen, mic, and system audio for real-time alerts, session summaries, and searchable memory.
Quick Start
Upload the video file located at /path/to/your/video.mp4 and then index its spoken words.