Build a conversational AI companion device for $10
We built an open-source project Starmoon and are using affordable hardware components to bring AI characters to real-word objects like toys and plushies (or even your talking fridge). With voice to voice models sounding more and more human every day, a cool use-case would be to take the conversation away from screens and personify real-world objects. For our project we use an ESP32-S3 microcontroller with a mic and a mono-speaker to keep the cost at $10. We are fully open-sourcing our frontend, backend and firmware so you too can get started and create and customize your companion device.…
In plain words
Starmoon is an open-source project that adds conversational AI to physical objects like toys, plushies, or household items using voice-based interaction. Built on an ESP32-S3 microcontroller with a microphone and speaker, the device costs approximately $10 to construct. Designed for makers and hobbyists, it lets users create customized AI companions by providing open-source firmware, backend, and frontend code. The system uses voice-to-voice AI models to enable natural spoken conversations without requiring a screen.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
We built an open-source project Starmoon and are using affordable hardware components to bring AI characters to real-word objects like toys and plushies (or even your talking fridge). With voice to voice models sounding more and more human every day, a cool use-case would be to take the conversation away from screens and personify real-world objects. For our project we use an ESP32-S3 microcontroller with a mic and a mono-speaker to keep the cost at $10. We are fully open-sourcing our frontend, backend and firmware so you too can get started and create and customize your companion device. Appreciate any feedback below, it will help us improve :)
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 · 26d ago · cactuscompute.com
Launched alongside, October 2024
the whole month →
Softr for Notion▲925Turn Notion databases into portals & apps with no code
Dev tools · 2024 · softr.io
One inbox for all your work discussions
Work · 2024 · generalcollaboration.com