RIO XIAO ESP32 S3 Gemini Live Voice Assistant
Standalone full-duplex Gemini Live assistant on a XIAO.
By mk14ray
- Est. cost
- Cost unknown
- Posted
- GitHub stars
- 2 (GitHub)
Overview
RIO is a fully standalone Gemini Live voice assistant on a Seeed XIAO ESP32-S3: no phone, PC or relay server, just Wi-Fi. You can interrupt it mid-sentence, and it speaks Hindi, English or Hinglish.
How it works
The board's PDM microphone streams straight to the Gemini Live API over a TLS WebSocket held by the ESP32 itself. Replies play through a MAX98357A amplifier with the mic always open, and echo cancellation removes RIO's own voice. It can also look through its camera after asking consent, play music, read the news and show a face on a 128×64 OLED.
Hardware
- XIAO ESP32-S3
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.
More in Voice Assistants & Companions
See all 32esp_ai (fully offline ESP32-S3)
Speech-to-text, a tiny LLM and TTS all on one ESP32-S3.
- Freenove FNK0104B ESP32-S3
AdvancedCost unknown40
Daedalus voice terminal
An ESP32 voice terminal for a home AI running OpenClaw.
- ESP32
- mic
- speaker
- +2 more
IntermediateCost unknown
Open-source bring-your-own-key smart speaker
A Pi smart speaker where nothing leaves your network unless you say so.
- Raspberry Pi
- mic
- speaker
BeginnerCost unknown