The official Python SDK for Model Context Protocol servers and clients
用于构建模型上下文协议服务器和客户端的官方Python SDK
Patching for XiaoAi Speakers (小爱音箱), add custom binaries and open source software. Tested on LX06, LX01, LX05, L09A
为小爱音箱打补丁并添加自定义二进制文件，增强功能
plait-board/drawnix
13,942
开源白板工具（SaaS），一体化白板，包含思维导图、流程图、自由画等。All in one open-source whiteboard tool with mind, flowchart, freehand and etc.
开源一体化白板工具，支持思维导图、流程图和自由画
PaddlePaddle/PaddleSpeech
12,610
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.
易用的语音工具包，包含语音识别、语音合成、说话人验证和关键词检测
A library for real-time voice processing in web browsers
用于网页浏览器的实时语音处理库
zero-peak/ZeroOmega
7,468
Manage and switch between multiple proxies quickly & easily.
快速轻松地管理和切换多个代理
shivammehta25/Matcha-TTS
1,307
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
基于条件流匹配的快速语音合成架构，ICASSP 2024论文
FunAudioLLM/CosyVoice
21,401
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
多语言大模型语音生成，提供推理、训练和部署全栈能力
modelscope/3D-Speaker
2,966
A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
单模态和多模态说话人验证、识别与日志记录仓库
FunAudioLLM/SenseVoice
8,411
Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.
多语言语音理解，支持ASR、情感识别和音频事件检测，速度比Whisper快15倍