Table of Contents
Raspberry Pi TetherBox
Raspberry Pi units are ideal where power and space are constrained - lamp posts, vehicles, hidden mounts on the side of racks, or anywhere traditional hardware will not fit. Prefer Raspberry Pi 5 for a new installation: its estimated recording capacity is about 11 cameras; plan for up to 10 to leave headroom. Existing Raspberry Pi 4 units can handle up to 4 cameras. See CPU Recommendations for sizing.
Raspberry Pi 4 Model B is still in production, not end-of-life. Raspberry Pi's official lifecycle statement (opens in a new tab) commits to production until at least January 2034. Continued production and support do not make it our preferred choice over Pi 5 for a new TetherBox.
For sizing the rest of the unit (RAM, storage, GPU) see Hardware Specifications. For storage hardware specifics see Storage Hardware Recommendations.
Key Requirements
Cooling is critical - Ensure the enclosure has good passive or ideally active (fan) cooling. Raspberry Pi units can last 7+ years, but only if cooling is adequate. Units that run hot will fail prematurely.
Storage for video recording - If using a Raspberry Pi to record video, you MUST use adequate external storage or an M.2 HAT with an appropriate drive. SD cards and USB memory sticks are not suitable for continuous video recording. See Storage Hardware Recommendations.
Power supply - Use the official 27W USB-C adapter on Raspberry Pi 5. Undersized power supplies cause undervolting and CPU compute errors under load.
Raspberry Pi AI Hat+ / AI Hat 2
The Raspberry Pi AI Hat+ (opens in a new tab) and AI Hat 2 (opens in a new tab) add a Hailo AI accelerator to Raspberry Pi 5. Choose the exact accelerator variant using Hailo AI Accelerators, which lists the camera capacities and analytics settings. The number of cameras recorded by the Pi is separate from the number receiving AI analytics.
What it enables:
- TetherX AI - AI-powered smart motion detection using object recognition to detect and classify people, vehicles, and animals, track their trajectory across frames, and make recordings searchable by what was seen
- TetherX Audio AI - Real-time audio event detection that classifies security-relevant sounds such as glass breaking, screaming, gunshots, smoke alarms, dog barking, and vehicle horns
Key details:
- AI capacity depends on the Hailo variant, rather than the HAT name alone. See Hailo AI Accelerators
- The Hailo accelerator runs model inference; stream decoding, preprocessing and other host tasks still require CPU and RAM
- Connects through the Raspberry Pi 5 PCIe connector; choose an enclosure with clearance for the exact HAT and active cooler
- TetherBox automatically detects the Hailo accelerator and enables AI analytics when available
Note: The AI HAT uses the Pi's PCIe connection. Use suitable USB storage for recordings, or an explicitly compatible expansion arrangement that supports both storage and AI. Do not assume a second M.2 HAT can be stacked onto the same connection. Check power requirements for the complete configuration. See Storage Hardware Recommendations for drive and enclosure guidance.
Referenced in: