Awesome Voice Agents

Awesome Voice Agents [](https://awesome.re)

A curated list of voice AI agent frameworks, tools, resources, and best practices | 精选的语音 AI Agent 框架、工具、资源和最佳实践

Welcome to **Awesome Voice Agents**! This is a carefully curated collection of resources related to voice AI agents, covering core technologies such as endpoint detection, turn-taking management, real-time speech recognition, and speech synthesis.

本项目精心收录语音 AI Agent 相关的优质资源，涵盖端点检测、话轮管理、实时语音识别、语音合成等核心技术。

**Maintainer | 维护者: 云中江树**

💬 **Join Voice Agent Community | 加入 Voice Agent 交流群** Add WeChat | 添加微信: **1796060717** 欢迎 Voice Agent 从业者和爱好者加入交流！

---

Contents | 目录

• Frameworks & Platforms | 框架与平台
• VAD (Voice Activity Detection) | 语音活动检测
• Turn Detection & Endpointing | 话轮检测与端点检测
• STT (Speech-to-Text) | 语音转文本
• TTS (Text-to-Speech) | 文本转语音
• Developer Communities & Resources | 开发者社区与资源
• Learning Resources | 学习资源
• Contributing | 贡献指南

---

Frameworks & Platforms | 框架与平台

Comprehensive Frameworks | 综合性框架

Name	Stars	Description	Notes
TEN Framework		Open-source framework for conversational voice AI agents with multimodal capabilities (voice, vision, avatar). Low-latency, high-quality real-time assistant.	支持多模态，低延迟高质量。Demo
Pipecat		Open Source framework for voice and multimodal conversational AI. Modular design with support for multiple STT, LLM, TT