A lightweight, powerful framework for multi-agent workflows and voice agents

A powerful framework for building realtime voice AI agents 🤖🎙️📹

SIP to WebRTC bridge for LiveKit

Simple bidirectional audio protocol

wallabag is a self hostable application for saving web pages: Save and classify articles. Read them later. Freely.

基于Python的开源量化交易平台开发框架

Python Backtesting library for trading strategies

AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库

AKTools is an elegant and simple HTTP API library for AKShare, built for AKSharers!

Official implementation of "Sonic: Shifting Focus to Global Audio Perception in Portrait Animation"

🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

Step-by-step instructions to build a smartphone that is open-source, upgradeable, repairable, and Big Tech free.

End-to-end realtime stack for connecting humans and AI

Open Source framework for voice and multimodal conversational AI

SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime

实时交互数字人，可自定义形象与音色，支持音色克隆，对话延迟低至3s。Real-time voice interactive digital human, customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.

使用本地模型，实现实时AI语音对话，适用于中文环境。

《Agentic Design Patterns》中文翻译版

Sample Repository for the AlibabaCloud Bailian Speech SDK

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics rec…

GLM-4-Voice | 端到端中英语音对话模型

Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction…

Contexts Optical Compression

基于Fastrtc、Ollama、FunASR和MegaTTS的大模型中文语音实时对话应用

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

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 …