Close
0%
0%

Chatbot Zero - AI on Raspberry Pi zero

An AI chatbot build on Raspberry Pi zero 2w, with a small LCD screen, speaker, micphone and battery

Similar projects worth following
This is a pocket-sized AI chatbot device built using a Raspberry Pi Zero 2w. Just press the button, speak, and it talks back like a futuristic walkie-talkie with a mind of its own.

Built-in screen, RGB led, microphone & speaker. Push-to-talk button. Fully portable and USB rechargeable.

AI responses generated using OpenAI’s API or other cloud services, configurable. A TypeScript server handles the logic and message flow on RPI, and it's extendable: run your own tools or scripts in response to AI commands.

Subsequent Goals:

* ✅ [Hardware] Use mouse buttons instead to improve button comfort
* ✅ [Hardware] Optimize the HAT and enclosure structure, with the speaker outlet facing upward
* ✅ [Hardware] PCB layout redesign and logo for the HAT
* [Hardware] Support RPI camera input
* ✅ [Software] Integrate the tool with the API
* ✅ [Software] Enable the AI assistant to adjust the volume autonomously
* ✅ [Software] Reset the conversation history if there is no speech for five minutes
* ✅ [Software] Support custom tools (open light demo)
* [Software] Support third party MCP server
* ✅ [Software] Support Local LLM (ollama)
* ✅ [Software] Support LLM Thinking
* ✅ [Software] Support ASR and TTS locally
* [Software] Support speaker identity recognition

  • 1 × Raspberry Pi zero 2w
  • 1 × Whisplay HAT (released on Oct 9, 2025) 1.69inch LCD screen, wm8960 sound chip with on-board speaker and mic, RGB led, GPIO Button
  • 1 × PiSugar 3 1200mAh, battery, UPS
  • 1 × 3D resin printed enclosure

View all 9 project logs

Enjoy this project?

Share

Discussions

shujun wrote 05/07/2026 at 16:43 point

Good project ! i am doing the same thing  !

  Are you sure? yes | no

Shteef-Ner wrote 03/09/2026 at 00:22 point

After a few hours i got it working (using chatGPT as the LLM) with much help from Grok. My speaker seems VERY quite for some reason. Are the STL files for the case available anywhere? Thanks for your hard work and posting.

  Are you sure? yes | no

aaaaaa wrote 10/13/2025 at 14:16 point

I would like to use gemma 3n or similar 8B models offline.

Why I must put my voide and my data to corporation? Please make offline model. I no need audio

  Are you sure? yes | no

Jdaie wrote 10/15/2025 at 01:23 point

You mean just the text-base LLM only? No need for audio recognition and synthesis?

  Are you sure? yes | no

Similar Projects

Does this project spark your interest?

Become a member to follow this project and never miss any updates