openai-realtime-embedded-SDK Build AI assistants on microcontrollers
Hi HN! This is an SDK for ESP32s (microcontrollers) that runs against OpenAI's new WebRTC service [0] My hope is that people can easily add AI to lots of 'real' devices. Wearable devices, speakers around the house, toys etc... You don't have to write any code, just buy a device and set some env variables. If you have any feedback/questions I would love to hear! I hope this kicks off a generation of new interesting devices. If you aren't familiar with WebRTC it can do some magical things. Check out WebRTC for the Curious[1] and would love to talk about all the cool things that does also.…
In plain words
The openai-realtime-embedded-SDK is a software package that enables developers to add AI capabilities to ESP32 microcontrollers using OpenAI's WebRTC service. It targets creators building internet-connected devices like wearables, smart speakers, and toys. The SDK requires minimal coding—users can set environment variables without writing code. It uses WebRTC technology to handle real-time communication between the microcontroller and OpenAI's AI services.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi HN! This is an SDK for ESP32s (microcontrollers) that runs against OpenAI's new WebRTC service [0] My hope is that people can easily add AI to lots of 'real' devices. Wearable devices, speakers around the house, toys etc... You don't have to write any code, just buy a device and set some env variables. If you have any feedback/questions I would love to hear! I hope this kicks off a generation of new interesting devices. If you aren't familiar with WebRTC it can do some magical things. Check out WebRTC for the Curious[1] and would love to talk about all the cool things that does also. [0] https://platform.openai.com/docs/guides/realtime-webrtc [1] https://webrtcforthecurious.com
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
