- Home
- Skills
- APIs & Backend
- Raspberry Pi Live Streaming & WebRTC Talkback Rig
Raspberry Pi Live Streaming & WebRTC Talkback Rig
Deploy low-latency video streaming and WebRTC talkback on Raspberry Pi with optimized BLE/Wi-Fi co-existence.
Free
Works with the AI Agents you already use
Raspberry Pi Live Streaming & WebRTC Talkback Rig
Example session with this skill installed
Write a systemd unit file for the srs-publisher service and provide the ffmpeg command to stream 720p video from a CSI camera to a local SRS instance.
- Read your context and instructions
- Compiled the raspberry pi live
I have generated the systemd unit configuration and the optimized FFmpeg pipeline for your Raspberry Pi smart helmet.
Service Configuration and Media Pipeline
[Unit]
Description=Raspberry Pi Smart Helmet SRS Publisher
After=srs.service network-online.target
Wants=network-online.target
[Service]
Type=simple
User=pi
WorkingDirectory=/home/pi/helmet
ExecStart=/bin/bash -c 'rpicam-vid -t 0 --inline --width 1280 --height 720 --framerate 24 --bitrate 1100000 -o - | ffmpeg -re -f h264 -i - -f alsa -ar 16000 -ac 1 -i hw:3,0 -c:v copy -c:a aac -b:a 64k -f flv rtmp://127.0.0.1:1935/live/helmet'
Restart=always
RestartSec=5
[Install]
WantedBy=multi-user.target
Implementation Details:
- Video Pipeline: Uses
rpicam-vidfor hardware-accelerated H.264 encoding to minimize CPU load. - Audio Mixing: Captures mono audio from ALSA device
hw:3,0(adjust based onarecord -l) and encodes to AAC. - Latency Control: Piped directly into RTMP at 1.1Mbps to maintain sub-second latency for the HTTP-FLV egress.
Next steps
- Run
arecord -lto verify your USB microphone is mapped tohw:3,0. - Enable the camera overlay in
/boot/firmware/config.txtand reboot. - Start the service with
sudo systemctl enable --now srs-publisher.
Connects securely to your tools. The creator never sees your data.
About this skill
Struggling with high-latency video and Wi-Fi drops on Raspberry Pi IoT projects? This skill provides the configuration and logic needed to build a low-latency smart helmet system using SRS (Simple Realtime Server) and ARM-optimized media pipelines.
What it does
- Low-latency streaming implements sub-800ms video egress using HTTP-FLV and mpegts.js for real-time monitoring.
- Two-way talkback routes browser-based WebRTC audio directly to physical Pi speakers via dedicated ingress scripts.
- Radio contention management provides specific configurations to prevent Bluetooth LE scans from dropping Wi-Fi video frames.
- Offline-resilient capture automates video chunking and metadata logging to ensure data integrity during network outages.
- Edge provisioning enables zero-touch Wi-Fi onboarding via optical QR code scanning at boot.
How it works
- Configure hardware by enabling CSI/USB camera overlays and identifying ALSA audio device indices.
- Deploy SRS via Docker or native binary to act as the media broker for RTMP, FLV, and WebRTC protocols.
- Initialize daemons using the provided systemd units for isolated video publishing, API handling, and GPIO monitoring.
- Proxy traffic through a public gateway or local subnet to bridge the gap between cloud frontends and local Pi APIs.
Frameworks & tools
Raspberry Pi (4B/5), SRS (Simple Realtime Server), FFmpeg, Python (Flask), Next.js, mpegts.js, WebRTC, BLE (Cypress CYW43455), and systemd.
Why this beats prompting it yourself
Generic AI prompts often suggest high-overhead tools like LiveKit or Ngrok which fail on resource-constrained ARM hardware. This skill enforces specific hardware-level optimizations for ALSA mixing and radio frequency isolation that general LLMs typically miss.
Use cases
- Industrial safety for real-time remote inspection with two-way audio and PPE detection.
- Field service to provide hands-free technical support via low-latency head-mounted video.
- Edge monitoring for remote sites where cellular bandwidth requires strict 50MB file chunking.
Known limitations
Requires hardware-specific paths for ALSA (e.g., hw:3,0) and CSI camera overlays. High-throughput video requires 5GHz Wi-Fi to avoid 2.4GHz BLE interference.
Requires manual ALSA device indexing. 2.4GHz Wi-Fi will experience frame drops during active BLE scans. Designed specifically for Raspberry Pi 4B/5 hardware.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 12 days ago
- Free with an Agensi account