Dograh - Voice Assistant Workflow Builder

Introduction

Dograh is an open-source voice workflow builder designed to help users easily create and manage custom voice assistant workflows. Whether you are an individual developer, an enterprise team, or a voice technology enthusiast, Dograh provides a flexible and extensible platform that makes voice interaction simple and efficient. With a visual flow editor and powerful integration capabilities, you can quickly build a complete pipeline from speech recognition to task execution without writing complex code.

Key Features

• Visual Workflow Editor: Design voice interaction flows with a drag-and-drop interface, supporting conditional branches, loops, and parallel tasks.
• Multi-Engine Speech Recognition: Integrates multiple mainstream speech recognition engines (such as Google Speech, Whisper, etc.), allowing users to switch freely based on their needs.
• Custom Action Nodes: Supports HTTP requests, database queries, file operations, and other actions to easily connect with external systems.
• Real-Time Debugging and Logs: Provides live runtime logs and debugging tools to help quickly identify issues in your workflows.
• Plugin Extension System: Built on a plugin architecture, developers can write custom plugins to extend functionality.

Highlights

• Fully Open Source: Code is hosted on GitHub, community-driven development, with no risk of vendor lock-in.
• Lightweight Deployment: Supports one-click deployment via Docker, and can run on low-spec servers or Raspberry Pi.
• Highly Customizable: From speech models to output formats, every stage allows deep customization by the user.
• Multilingual Support: Built-in natural language processing support for Chinese, English, and multiple other languages.
• Active Community: A vibrant developer community provides abundant sample workflows and plugin resources.

Who It's For

Developers who need to quickly prototype voice interaction projects or want to integrate voice capabilities into existing applications. Enterprise teams looking to build internal voice assistants or automated customer service flows while reducing development costs. Voice technology enthusiasts interested in learning and experimenting with workflow design. Educators who want to use it for teaching demonstrations and help students understand how voice interaction systems are built.