esp32-thinks

What is esp32-thinks

A multi-model personal AI voice assistant for ESP32, supporting wake-word or knob activation. It allows any OpenAI-compatible STT, chat and TTS models to be freely combined for streaming responses and works out of the box. Built on muse-gadget-sdk.

Key features

• Supports wake-word or knob-triggered voice interaction
• Any OpenAI-compatible STT, chat and TTS models can be freely combined
• Delivers streaming, sentence-by-sentence replies and supports English, Chinese and Korean
• Built on muse-gadget-sdk for ESP32-S3 devices
• Offers preset configurations and fully custom model options

Who it is for

Developers and enthusiasts building personal AI voice assistants with chosen OpenAI-compatible models on ESP32 hardware, suitable for local voice interaction scenarios that avoid cloud vendor lock-in.

How to get started

1. Visit https://github.com/raullenchai/esp32-thinks
2. Build the firmware using muse-gadget-sdk according to the README
3. Set OpenAI-compatible STT, chat and TTS endpoints in the configuration file
4. Flash the firmware to the ESP32-S3 device to start using it

Compiled from public descriptions on the tool's official website / README / launch page. Pricing and user numbers have not been verified; please check the official website. Some sections were drafted with AI assistance. Written in Chinese and English; other languages are machine-translated.