Stars
百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,时延低至800ms,低配置也可运行,支持打断
本项目为xiaozhi-esp32提供后端服务,帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
A real-time speech-to-speech chatbot powered by Whisper Small, Llama 3.2, and Kokoro-82M.
Pseudo Streaming SenseVoice with Hotwords
Agent framework and applications built upon Qwen>=2.0, featuring Function Calling, Code Interpreter, RAG, and Chrome extension.
This is a speech interaction system built on an open-source model, integrating ASR, LLM, and TTS in sequence. The ASR model is SenceVoice, the LLM models are QWen2.5-0.5B/1.5B, and there are three …
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
AI桌宠2.2(网页端toklen白嫖国产大模型服务器(glm4,kimi,deepseekv2),语音识别,屏幕识别自动发送,live2d 2.0和3.0模型,gpt-sovits语音,coysvoice语音,edge-tts语音(支持多语言音色),本地ollama模型无限制聊天)(主流国产大模型api接口支持)
The simplest and lowest-cost AI integration solution. If you like this project, please give it a Star~ | 最简单、最低成本的AI接入方案。喜欢本项目的话点个 Star 吧~
An open source voice-enabled, compact, empathic AI hardware + software 🤖 framework for companionship, entertainment, education, healthcare, IoT applications, AI-enhanced robotics application servic…
本项目使用esp32、esp32s3接入Chatgpt、Claude、讯飞星火、豆包等15款大模型,实现语音对话聊天,支持语音唤醒、连续对话、音乐播放等功能,同时外接了一块显示屏实时显示对话的内容。
quick way to build a private large language model server and provide OpenAI-compatible interfaces | 快速搭建私有大语言模型(LLM)服务,提供OpenAI兼容接口
Data framework for your LLM applications. Focus on server side solution
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
一个基于云端语音识别的智能控制设备,类似于天猫精灵,小爱同学。采用的芯片为stm32f407,wm8978,esp8266。
esp32 based device, mainly used for voice chat with large language models
Espressif IoT Development Framework. Official development framework for Espressif SoCs.
Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.
A GPS bicycle speedometer that supports offline maps and track recording
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.
A community-maintained Python framework for creating mathematical animations.