dograh-hq / dograh

查看原文 / View Original 编辑 / Edit

dograh-hq / dograh

Dograh AI is the open-source, self-hostable alternative to Vapi & Retell — build production voice agents with a drag-and-drop workflow builder. From zero to a working bot in under 2 minutes. 📖 Docs · 📜 BSD 2-Clause Dograh AI 是 Vapi 和 Retell 的开源、可自托管替代方案——通过拖拽式工作流构建器打造生产级语音智能体。从零开始到运行机器人只需不到 2 分钟。📖 文档 · 📜 BSD 2-Clause 协议

100% open source, self-hostable — no vendor lock-in, unlike Vapi or Retell. Full control & transparency — every line of code is open, with flexible LLM / TTS / STT integration. Maintained by YC alumni and exit founders, committed to keeping voice AI open. 100% 开源，可自托管——与 Vapi 或 Retell 不同，没有供应商锁定。完全的控制权与透明度——每一行代码均开源，并支持灵活的 LLM / TTS / STT 集成。由 YC 校友及成功退出的创始人维护，致力于保持语音 AI 的开放性。

🎥 Featured: Featured by Better Stack — a hands-on look at Dograh. 📺 Prefer a 2-minute product walkthrough? Click here. 🎥 精选：Better Stack 专题报道——对 Dograh 的实操测评。📺 想看 2 分钟的产品演示？点击这里。

⚖️ Dograh vs Vapi vs Retell: An honest comparison on the axes that matter most to teams evaluating voice AI platforms. ⚖️ Dograh 与 Vapi 及 Retell 的对比：针对团队评估语音 AI 平台时最关心的维度进行的客观比较。

FeatureDograhVapiRetell
LicenseBSD 2-Clause (open source)ProprietaryProprietary
Self-hostable✅ Yes — one Docker command❌ SaaS only❌ SaaS only
PricingFree (self-host) · usage-based (cloud)Per-minute SaaSPer-minute SaaS
Bring your own LLM / STT / TTS✅ Any provider, or use Dograh’s stackConfigurable within their integrationsConfigurable within their integrations
Source-level customization✅ Every line is yours to modify❌ Closed source❌ Closed source
Data residencyYour infra, your rulesTheir cloudTheir cloud
Vendor lock-inNoneFullFull
功能DograhVapiRetell
许可证BSD 2-Clause (开源)专有专有
可自托管✅ 是 — 一条 Docker 命令❌ 仅限 SaaS❌ 仅限 SaaS
定价免费 (自托管) · 按用量付费 (云端)按分钟 SaaS按分钟 SaaS
自带 LLM / STT / TTS✅ 任意提供商，或使用 Dograh 技术栈在其集成内配置在其集成内配置
源码级定制✅ 每一行代码均可修改❌ 闭源❌ 闭源
数据驻留你的基础设施，你的规则他们的云端他们的云端
供应商锁定无完全锁定完全锁定

🚀 Get Started: Download and setup Dograh on your Local Machine. 🚀 开始使用：在本地机器上下载并设置 Dograh。

Note: We collect anonymous usage data to improve the product. You can opt out by setting the ENABLE_TELEMETRY to false in the below command. Note: If you wish to run the platform on a remote server instead, checkout our Documentation. 注意：我们会收集匿名使用数据以改进产品。你可以通过在下方命令中将 ENABLE_TELEMETRY 设置为 false 来选择退出。注意：如果你希望在远程服务器上运行该平台，请查看我们的文档。

curl -o docker-compose.yaml https://raw.githubusercontent.com/dograh-hq/dograh/main/docker-compose.yaml && REGISTRY=ghcr.io/dograh-hq ENABLE_TELEMETRY=true docker compose up --pull always

Note: First startup may take 2-3 minutes to download all images. Once running, open http://localhost:3010 to create your first AI voice assistant! For common issues and solutions, see 🔧 Troubleshooting. 注意：首次启动可能需要 2-3 分钟来下载所有镜像。运行后，打开 http://localhost:3010 创建你的第一个 AI 语音助手！常见问题及解决方案，请参阅 🔧 故障排除。

🎙️ Your First Voice Bot: Open http://localhost:3010 in your browser. Pick Inbound or Outbound, name your bot (e.g. Lead Qualification), and describe the use case in 5–10 words (e.g. Screen insurance form submissions for purchase intent). Click Web Call — you’re talking to your bot. 🎙️ 你的第一个语音机器人：在浏览器中打开 http://localhost:3010。选择呼入或呼出，为你的机器人命名（例如：线索资格审核），并用 5-10 个词描述用例（例如：筛选保险表单提交以确认购买意向）。点击“Web Call”——你就可以与你的机器人对话了。

🔑 No API keys needed. Dograh ships with auto-generated keys and its own LLM / TTS / STT stack. Connect your own keys for LLM, TTS, STT, or Telephony (e.g. Twilio, Vonage, Telnyx) anytime. 🔑 无需 API 密钥。Dograh 自带自动生成的密钥及其自身的 LLM / TTS / STT 技术栈。你可以随时连接自己的 LLM、TTS、STT 或电话服务（如 Twilio、Vonage、Telnyx）密钥。

Features (功能特性)

Voice Capabilities (语音能力)

  • Telephony: Built-in telephony integration like Twilio, Vonage, Vobiz, Cloudonix (easily add others), with support for transferring calls to human agents.
    • 电话服务： 内置 Twilio、Vonage、Vobiz、Cloudonix 等电话集成（可轻松添加其他），支持将通话转接给人工坐席。
  • Languages: English support (expandable to other languages).
    • 语言： 支持英语（可扩展至其他语言）。
  • Custom Models: Bring your own TTS/STT models.
    • 自定义模型： 支持使用你自己的 TTS/STT 模型。
  • Real-time Processing: Low-latency voice interactions.
    • 实时处理： 低延迟语音交互。

Developer Experience (开发者体验)

  • Zero Config Start: Auto-generated API keys for instant testing.
    • 零配置启动： 自动生成 API 密钥，实现即时测试。
  • Python-Based: Built on Python for easy customization.
    • 基于 Python： 基于 Python 构建，易于定制。
  • Docker-First: Containerized for consistent deployments.
    • Docker 优先： 容器化部署，确保环境一致性。
  • Modular Architecture: Swap components as needed.
    • 模块化架构： 可根据需要更换组件。

Testing & Quality (测试与质量)

  • Test Mode: Try your agent end-to-end before publishing, with no production calls or data affected.
    • 测试模式： 在发布前进行端到端测试，不会影响生产环境的通话或数据。
  • In-Dashboard Web Calls: Talk to your bot directly while building — no telephony setup required.
    • 仪表盘内 Web 通话： 在构建过程中直接与机器人对话——无需设置电话服务。
  • QA Node: A built-in workflow node that analyzes prompt quality across your other nodes.
    • QA 节点： 内置工作流节点，用于分析其他节点中的提示词（Prompt）质量。

Deployment Options (部署选项)

  • Local Development: Refer Local Setup.
    • 本地开发： 请参考本地设置。
  • Self-Hosted Deployment: For detailed deployment instructions including remote server setup with HTTPS, see our Docker Deployment Guide.
    • 自托管部署： 有关详细部署说明（包括带 HTTPS 的远程服务器设置），请参阅我们的 Docker 部署指南。
  • Cloud Version: Visit https://www.dograh.com for our managed cloud offering.

📚 Documentation: You can go to https://docs.dograh.com for our documentation. 📚 文档： 你可以访问 https://docs.dograh.com 查看我们的文档。

🤝 Community & Support (社区与支持)

  • 👋 Coming from the Better Stack video? Drop your use case in our pinned GitHub Discussion — we read every reply and the founders personally onboard early adopters.
    • 👋 是从 Better Stack 视频过来的吗？请在我们的 GitHub 置顶讨论区留下你的用例——我们会阅读每一条回复，创始人也会亲自引导早期用户。
  • Slack — the cornerstone of Dograh AI contributions. Connect with maintainers, discuss features before coding, get help with setup, and stay current on contribution sprints.
    • Slack — Dograh AI 贡献的核心。与维护者交流，在编码前讨论功能，获取设置帮助，并随时了解贡献冲刺活动。
  • GitHub Discussions — share use cases, ask questions, swap workflow recipes.
    • GitHub Discussions — 分享用例、提问、交流工作流方案。
  • GitHub Issues — report bugs or request features.
    • GitHub Issues — 报告 Bug 或提交功能需求。
  • 👉 Join us → Dograh Community Slack

🙌 Contributing (贡献) We love contributions! Dograh AI is 100% open source and we intend to keep it that way. 我们热爱贡献！Dograh AI 是 100% 开源的，我们打算一直保持下去。

Getting Started (开始贡献)

  1. Fork the repository

  2. Create your feature branch (git checkout -b feature/AmazingFeature)

  3. Commit your changes (git commit -m 'Add some AmazingFeature')

  4. Push to the branch (git push origin feature/AmazingFeature)

  5. Open a Pull Request

  6. Fork 本仓库

  7. 创建你的功能分支 (git checkout -b feature/AmazingFeature)

  8. 提交你的更改 (git commit -m 'Add some AmazingFeature')

  9. 推送到分支 (git push origin feature/AmazingFeature)

  10. 开启一个 Pull Request

⭐ Star History 📄 License: Dograh AI is licensed under the BSD 2-Clause License- the same license as projects that were used in building Dograh AI, ensuring compatibility and freedom to use, modify, and distribute. 📄 许可证： Dograh AI 采用 BSD 2-Clause 许可证——这与构建 Dograh AI 时所使用的项目许可证相同，确保了兼容性以及使用、修改和分发的自由。

🏢 About: Built with ❤️ by Dograh (Zansat Technologies Private Limited). Founded by YC alumni and exit founders committed to keeping voice AI open and accessible to everyone. 🏢 关于： 由 Dograh (Zansat Technologies Private Limited) 用 ❤️ 构建。由 YC 校友及成功退出的创始人创立，致力于让语音 AI 保持开放并惠及每一个人。

⭐ Star us on GitHub | ☁️ Try Cloud Version | 💬 Join Slack ⭐ 在 GitHub 上为我们点赞 | ☁️ 试用云版本 | 💬 加入 Slack

← 返回新闻列表 / Back to news list