ESP32 AI LLM
ESP32 voice chat with 15 LLMs, wake word and live on-screen text.
By Explorerlowi
- Est. cost
- Cost unknown
- Posted
- GitHub stars
- 561 (GitHub)
Overview
An ESP32 voice assistant that can talk to 15 LLMs, including ChatGPT, Claude, Gemini, Grok, DeepSeek, Doubao and Ollama, with wake word, continuous conversation, music playback and live text on a screen. The README is in Chinese.
How it works
An ASRPRO module handles the offline wake word ('你好九歌' by default) and an interrupt word. An INMP441 microphone and MAX98357 amplifier connect to an ESP32 or ESP32-S3, and a 1.8-inch TFT shows the chat. iFlytek provides speech-to-text, and Wi-Fi and model settings are configured from a web page.
Hardware
- ESP32/ESP32-S3
- mic
- display
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 unknownRIO XIAO ESP32 S3 Gemini Live Voice Assistant
Standalone full-duplex Gemini Live assistant on a XIAO.
- XIAO ESP32-S3
IntermediateCost unknown2