esp_ai (fully offline ESP32-S3)
Speech-to-text, a tiny LLM and TTS all on one ESP32-S3.
- Freenove FNK0104B ESP32-S3
Talk-to-it devices: smart speakers, ESP32 voice bots, local Jarvis builds.
32 projects
Speech-to-text, a tiny LLM and TTS all on one ESP32-S3.
An ESP32 voice terminal for a home AI running OpenClaw.
Standalone full-duplex Gemini Live assistant on a XIAO.

A Pi smart speaker where nothing leaves your network unless you say so.
Push-to-talk ESP32-S3 companion backed by Claude.

Whisper + a small LLM + Piper, all on a Pi.
Offline vision-enabled voice assistant on a Pi 5 with an LLM accelerator.
Tiny truly-local voice LLM agent on a Pi.
Real-time offline voice assistant for Pi and Linux.
A HAL 9000 voice assistant on a Pi.
Open voice-agent server for the ESP32 EchoKit.
XiaoZhi on any computer, with MCP and IoT.
Chat with several custom AI friends on an ESP32.
ESP32 voice chat with 15 LLMs, wake word and live on-screen text.
ESP32 voice chat with large language models.
whisper.cpp voice assistant for the Pi 5.
ChatGPT on an ESP32 with spoken replies.
The most-starred open-source ESP32 AI voice bot.
Self-host the brain for your XiaoZhi device.
Realtime voice AI with 100+ models on an ESP32.
A Pi 5 voice assistant whose conversations never leave the room.
Offline tool-calling voice assistant on a Pi 5.
An Adventure Time BMO on a Raspberry Pi 5 that sees and talks.
A voice chatbot that gestures with a robot arm.
Low-latency local voice assistant with LEDs and gestures.
A vintage Siemens W48 that talks to Home Assistant.