Skip to main content

View Football Commentator Example on GitHub

Check out the complete Football Commentator example in our GitHub repository
In this example, we build a real-time sports commentator that combines Roboflow’s RF-DETR for player and ball detection with realtime models from Gemini and OpenAI. The system annotates video with bounding boxes, detects game events (like when the ball reappears after fast action), and triggers AI commentary. This example also explores the current limitations of realtime video understanding and showcases Vision Agents’ ability to hot-swap between providers with minimal code changes.
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 players and the ball in real time using Roboflow RF-DETR
  • Annotate live video with bounding boxes and detection overlays
  • Trigger AI commentary based on game events (ball reappearance, fast plays)
  • Compare Gemini Live vs OpenAI Realtime with a one-line swap
  • Run on Stream’s low-latency edge network

​
Next Steps

Roboflow Integration

Explore Roboflow detection models and configuration

AI Golf Coach

See another video processing example with YOLO pose detection