Features
Universal video ingestion: feeds, streams, files, recordings, audio
Real-time live stream processing via RTStream (GA)
Scene detection and segmentation
ASR transcription for speech
Semantic search across video content
Custom computer vision model integration
Video editing: inline edit, overlay, resize
Generative AI: dubbing, translation, image gen, audio gen, video gen
Playable clip retrieval from search results
Webhooks and event-driven integrations
Transparent usage-based pricing with unit rates
Video streaming and delivery
SDK for Python (pip install)
Reka Edge 2 frontier-level edge intelligence model for physical AI
Inference engine and API for multimodal AI
Scalable video tagging, reasoning, search, and clipping
Claru builds training data: egocentric video, robotics trajectories, world-model footage
Expert human judgment at scale via Claru
PhysicalRealismBench-U benchmark for video world models
Integration with OpenRouter for zero-code model switching
n8n community node for video and image analysis
Vision integration without replacing existing VMS
Private AI models for public sector trust and intelligence
Partnership with Moonvalley for physical AI models
CS2-10k dataset for egocentric video research
Model Context Protocol (MCP) support for video infrastructure
