Skip to main content

View Moderation Example on GitHub

Check out the complete Moderation example in our GitHub repository
In this example, we build a real-time video moderation agent that detects offensive gestures using a custom Roboflow model running locally, censors them with a Gaussian blur, and issues escalating verbal warnings — ultimately kicking the user from the call on the third offense. The agent uses Gemini Flash Lite for language and Deepgram for speech, processing video at 15 FPS with local inference for low-latency detection.
Vision Agents uses Stream Video for real-time WebRTC transport by default. External WebRTC transports are supported as well. Most AI providers offer free tiers to get started.

​
What You Will Build

  • Detect offensive content in real time using a custom Roboflow model with local inference
  • Censor detected content with Gaussian blur applied directly to the video stream
  • Issue escalating verbal warnings via Gemini Flash Lite and Deepgram TTS
  • Automatically kick users from the call on the third offense via the Stream API
  • Run detection locally with no cloud round-trip per frame for low latency

​
Next Steps

Roboflow Integration

Train or find your own detection model on Roboflow

Docker Deployment

Docker setup and environment configuration