TEN-framework/ten-framework

GitHub: TEN-framework/ten-framework

一个开源的实时多模态对话 AI 框架，提供完整的语音交互开发工具链和丰富的 Agent 示例。

Stars: 10986 | Forks: 1339

![Image](https://github.com/user-attachments/assets/799584b2-61ff-4255-bdd1-2548d0fdba52) [![TEN Releases](https://img.shields.io/github/v/release/ten-framework/ten-framework?color=369eff&labelColor=gray&logo=github&style=flat-square)][ten-releases] [![Coverage Status](https://coveralls.io/repos/github/TEN-framework/ten-framework/badge.svg?branch=main)][coverage] [![Release Date](https://img.shields.io/github/release-date/ten-framework/ten-framework?labelColor=gray&style=flat-square)][ten-releases] [![Commits](https://img.shields.io/github/commit-activity/m/TEN-framework/ten-framework?labelColor=gray&color=pink)][commit-activity] [![Issues closed](https://img.shields.io/github/issues-search?query=repo%3ATEN-framework%2Ften-framework%20is%3Aclosed&label=issues%20closed&labelColor=gray&color=green)][issues-closed] [![Contributors](https://img.shields.io/github/contributors/ten-framework/ten-framework?color=c4f042&labelColor=gray&style=flat-square)][contributors] [![GitHub license](https://img.shields.io/badge/License-Apache_2.0_with_certain_conditions-blue.svg?labelColor=%20%23155EEF&color=%20%23528bff)][license] [![Ask DeepWiki](https://deepwiki.com/badge.svg)][deepwiki] [![ReadmeX](https://raw.githubusercontent.com/CodePhiliaX/resource-trusteeship/main/readmex.svg)][readmex] [![README in English](https://img.shields.io/badge/English-lightgrey)][lang-en-readme] [![简体中文操作指南](https://img.shields.io/badge/简体中文-lightgrey)][lang-zh-readme] [![日本語のREADME](https://img.shields.io/badge/日本語-lightgrey)][lang-jp-readme] [![README in 한국어](https://img.shields.io/badge/한국어-lightgrey)][lang-kr-readme] [![README en Español](https://img.shields.io/badge/Español-lightgrey)][lang-es-readme] [![README en Français](https://img.shields.io/badge/Français-lightgrey)][lang-fr-readme] [![README in Italiano](https://img.shields.io/badge/Italiano-lightgrey)][lang-it-readme] [![TEN-framework%2Ften_framework | Trendshift](https://trendshift.io/api/badge/repositories/11978)][trendshift] [官方网站][official-site] • [文档][documentation] • [博客][blog]

目录
- [欢迎来到 TEN][welcome-to-ten] - [Agent 示例][agent-examples-section] - [Agent 示例快速开始][quick-start] - [本地环境][localhost-section] - [Codespaces][codespaces-section] - [Agent 示例自托管][agent-examples-self-hosting] - [使用 Docker 部署][deploying-with-docker] - [使用其他云服务部署][deploying-with-other-cloud-services] - [关注我们][stay-tuned] - [TEN 生态系统][ten-ecosystem-anchor] - [常见问题][questions] - [贡献指南][contributing] - [代码贡献者][code-contributors] - [贡献规范][contribution-guidelines] - [许可证][license-section]
## 欢迎来到 TEN TEN 是一个用于实时多模态对话式 AI 的开源框架。 [TEN 生态系统][ten-ecosystem-anchor] 包括 [TEN Framework][ten-framework]、[Agent 示例][agent-examples-repo]、[VAD][ten-vad]、[Turn Detection][ten-turn-detection] 和 [Portal][ten-portal]。

## Agent 示例
![Image](https://static.pigsec.cn/wp-content/uploads/repos/cas/e1/e1fa53f65afdda12a07ec44842c1e575cce61e11dc40fc52eca87a30ec1849dd.jpg) 多用途语音助手 — 这款低延迟、高质量的实时助手支持 RTC 和 [WebSocket][websocket-example] 连接，您可以使用 [Memory][memory-example]、[VAD][voice-assistant-vad-example]、[Turn Detection][voice-assistant-turn-detection-example] 及其他扩展来增强其功能。 有关更多详细信息，请查看[示例代码][voice-assistant-example]。
![divider](https://github.com/user-attachments/assets/aec54c94-ced9-4683-ae58-0a5a7ed803bd#gh-light-mode-only) ![divider](https://github.com/user-attachments/assets/d57fad08-4f49-4a1c-bdfc-f659a5d86150#gh-dark-mode-only)
![Image](https://github.com/user-attachments/assets/80c4eabd-de96-4971-8956-6b365d4fbd64) Doodler — 一个涂鸦板，可将语音或文本提示转换为简单的手绘草图，内置蜡笔调色板并支持实时绘制。 [示例代码][doodler-example]
![divider](https://github.com/user-attachments/assets/aec54c94-ced9-4683-ae58-0a5a7ed803bd#gh-light-mode-only) ![divider](https://github.com/user-attachments/assets/d57fad08-4f49-4a1c-bdfc-f659a5d86150#gh-dark-mode-only)
![Image](https://github.com/user-attachments/assets/f94b21b8-9dda-4efc-9274-b028cc01296a) 说话人分离 — 实时的分离功能，可检测并标记说话人，“Who Likes What”游戏展示了其交互式用例。 [示例代码][speechmatics-diarization-example]
![divider](https://github.com/user-attachments/assets/aec54c94-ced9-4683-ae58-0a5a7ed803bd#gh-light-mode-only) ![divider](https://github.com/user-attachments/assets/d57fad08-4f49-4a1c-bdfc-f659a5d86150#gh-dark-mode-only)
![Image](https://github.com/user-attachments/assets/51ab1504-b67c-49d4-8a7a-5582d9b254da) 口型同步虚拟形象 — 兼容多家虚拟形象供应商，主角“Kei”是一个由 MotionSync 驱动口型同步的动漫角色，同时还支持来自 Trulience、HeyGen 和 Tavus 的逼真形象。 如需查看不同 Live2D 角色的实现，请查看[示例代码][voice-assistant-live2d-example]。
![divider](https://github.com/user-attachments/assets/aec54c94-ced9-4683-ae58-0a5a7ed803bd#gh-light-mode-only) ![divider](https://github.com/user-attachments/assets/d57fad08-4f49-4a1c-bdfc-f659a5d86150#gh-dark-mode-only)
![Image](https://github.com/user-attachments/assets/6ed5b04d-945a-4a30-a1cc-f8014b602b38) SIP 通话 — 由 TEN 驱动的 SIP 扩展，可实现电话呼叫功能。 [示例代码][voice-assistant-sip-example]
![divider](https://github.com/user-attachments/assets/aec54c94-ced9-4683-ae58-0a5a7ed803bd#gh-light-mode-only) ![divider](https://github.com/user-attachments/assets/d57fad08-4f49-4a1c-bdfc-f659a5d86150#gh-dark-mode-only)
![Image](https://github.com/user-attachments/assets/d793bc6c-c8de-4996-bd85-9ce88c69dd8d) 语音转写 — 一款将音频转换为文本的转写工具。 [示例代码][transcription-example]
![divider](https://github.com/user-attachments/assets/aec54c94-ced9-4683-ae58-0a5a7ed803bd#gh-light-mode-only) ![divider](https://github.com/user-attachments/assets/d57fad08-4f49-4a1c-bdfc-f659a5d86150#gh-dark-mode-only)
![Image](https://github.com/user-attachments/assets/3d60f1ff-0f82-4fe7-b5c2-ac03d284f60c) ESP32-S3 Korvo V3 — 在 Espressif ESP32-S3 Korvo V3 开发板上运行 TEN agent 示例，实现 LLM 驱动的硬件通信集成。 有关更多详细信息，请查看[集成指南][esp32-guide]。
[![](https://img.shields.io/badge/-Back_to_top-gray?style=flat-square)][readme-top]
## Agent 示例快速开始 ### 本地环境 #### 步骤 ⓵ - 前置条件 | 类别 | 需求 | | --- | --- | | **密钥** | • Agora [App ID][agora-app-id] 和 [App Certificate][agora-app-certificate]
• [OpenAI][openai-api] API 密钥
• [Deepgram][deepgram] ASR
• [ElevenLabs][elevenlabs] TTS | | **安装** | • [Docker][docker] / [Docker Compose][docker-compose]
• [Node.js (LTS) v18][nodejs] | | **最低系统要求** | • CPU >= 2 核心
• RAM >= 4 GB |
![divider](https://github.com/user-attachments/assets/aec54c94-ced9-4683-ae58-0a5a7ed803bd#gh-light-mode-only) ![divider](https://github.com/user-attachments/assets/d57fad08-4f49-4a1c-bdfc-f659a5d86150#gh-dark-mode-only)
标签：人工智能, 多模态, 对话式AI, 开发框架, 用户模式Hook绕过, 语音AI