Philosopher plush
A plush toy that recognizes you, reads your mood and talks back.
By msalsas (GitHub repository owner)
- GitHub stars
- 8 (GitHub)
Build sheet
- Board
- Raspberry Pi Zero WH
- Other parts
- OV5647 CSI camera, USB mic + speaker, SG90 servo, USB hub, plush toy, laptop (8GB+) as brain
- AI model or service
- faster-whisper, dlib face recognition, FER+ emotion, Kokoro/Piper TTS, LangGraph memory, Hermes 3 Llama 3.1 8B via any OpenAI-compatible local server
- Difficulty
- Intermediate
Overview
A plush toy with a Pi Zero WH body (camera, mic, speaker, SG90 nodding head) that streams to a LAN laptop 'brain' doing Whisper STT, dlib face ID, FER+ emotion recognition, Kokoro/Piper TTS and per-person LangGraph memory, with a local 8B Hermes LLM as the 'mind'.
How it works
A Pi Zero WH body streams camera and audio to a LAN laptop that runs faster-whisper, face and emotion recognition, a local 8B LLM, memory and TTS.
Hardware
- Raspberry Pi Zero WH
- OV5647 CSI camera
- USB mic + speaker
- SG90 servo
- USB hub
- plush toy
- laptop (8GB+) as brain
Like this build? Get the weekly builds
Get the best new AI hardware builds every Thursday. One email a week, free.
Built something? Submit a build
This page is a short summary written by HardwareLab. Build steps, code and photos belong to the creator; follow “View original” for the full project.
Featured? Add this badge
Built this? Paste the badge into your README. It links back to this page.
Markdown
[](https://hardwarelab.dev/projects/philosopher-plush/?utm_source=badge&utm_medium=referral&utm_campaign=launch_2w)HTML
<a href="https://hardwarelab.dev/projects/philosopher-plush/?utm_source=badge&utm_medium=referral&utm_campaign=launch_2w"><img src="https://hardwarelab.dev/badge.svg" alt="Featured on HardwareLab" width="188" height="20"></a>
