Raspberry Pi Llm Mcp Music Websearch Asr Tts Qa
What is Raspberry Pi Llm Mcp Music Websearch Asr Tts Qa
raspberry-pi-llm–mcp-music-websearch-asr-tts-qa is a Raspberry Pi-based project that integrates various functionalities including face recognition, speech input and output, music playback, and web search capabilities using advanced language models and APIs.
Use cases
Use cases include creating a smart home assistant that can recognize users, play music on command, and perform web searches, as well as developing educational applications that utilize voice interaction.
How to use
To use the system, first set up the face library and knowledge base by running ‘python mk_faiss.py’ and ‘python face_create.py’. Then, execute the main interactive program with ‘python main_stream.py’ for terminal UI or ‘python app.py’ for graphical UI.
Key features
Key features include face recognition using OpenCV, real-time speech recognition and output via Baidu Speech Recognition API and edge_tts, music playback controls, and a terminal UI for user interaction.
Where to use
This system can be utilized in various fields such as home automation, personal assistants, educational tools, and entertainment systems, where voice interaction and face recognition are beneficial.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Raspberry Pi Llm Mcp Music Websearch Asr Tts Qa
raspberry-pi-llm–mcp-music-websearch-asr-tts-qa is a Raspberry Pi-based project that integrates various functionalities including face recognition, speech input and output, music playback, and web search capabilities using advanced language models and APIs.
Use cases
Use cases include creating a smart home assistant that can recognize users, play music on command, and perform web searches, as well as developing educational applications that utilize voice interaction.
How to use
To use the system, first set up the face library and knowledge base by running ‘python mk_faiss.py’ and ‘python face_create.py’. Then, execute the main interactive program with ‘python main_stream.py’ for terminal UI or ‘python app.py’ for graphical UI.
Key features
Key features include face recognition using OpenCV, real-time speech recognition and output via Baidu Speech Recognition API and edge_tts, music playback controls, and a terminal UI for user interaction.
Where to use
This system can be utilized in various fields such as home automation, personal assistants, educational tools, and entertainment systems, where voice interaction and face recognition are beneficial.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
树梅派 LLM
目录
系统功能
-
自我设计
根据自己需要构建知识库成为量身定做的问答助手 -
人脸识别
opencv人脸识别 -
语音输入与输出
百度语音识别API和edge_tts实时语音识别、流式语音输出 -
大模型
qwenAPI和本地向量化模型text2vec_base_chinese_q8知识库检索配合大模型回答
mcp接入音乐播放和网络搜索和图像识别功能：
支持播放继续播放下一首上一首暂停
支持查看各地各时间点天气，各时间点的地区的事件
支持实时图像识别,并根据语义进行不同角度的识别，如颜色、品牌、数数等
终端ui界面
配置
langchain_community langchain langchain_core llama_cpp openai face_recognition openvcv2 pickle pyaudio webrtcvad baidu-aip mcp-server pyside6
首先构建人脸库和知识库 ```bash python mk_faiss.py python face_create.py
执行以下命令运行主交互程序：
终端 python main_stream.py UI显示 python app.py
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
