The AI-Chatbox project utilizes the XIAO ESP32S3 Sense development board as the hardware core, combined with the Vosk speech recognition tool and the DeepSeek API big model, to build a complete voice interaction system. The project is developed in Rust language, optimized for embedded devices, with 512 max generated token configuration balancing performance and resource consumption. The main functions include voice wake-up recognition, Chinese speech to text, big model intelligent interaction, and cross-device REST service invocation, which is especially suitable for children, the elderly and the visually impaired and other people who are not convenient to use cell phone applications.
This answer comes from the articleAI-Chatbox: Speech-to-Text Intelligent Dialogue Project based on ESP32S3The
English 
简体中文 
日本語 
Deutsch 
Português do Brasil