Preface

In the development workflow of DeepSeek Harness (DSH), if voice output capability needs to be added to an agent, it usually requires integrating with a third-party speech synthesis service. The xby-speech-synthesis plugin provides an MCP (Model Context Protocol)-based solution and directly integrates the high-quality speech synthesis capabilities of Microsoft Edge.

Plugin Overview

This plugin is maintained by xby-skill and belongs to the model inference category. It is essentially an MCP server that integrates Microsoft Edge TTS, supporting multilingual speech generation, audio merging, and cloud storage. The plugin is open-sourced under the MIT License.

Core Features

The plugin provides the following two core capabilities:

  • set_xby_apikey: Sets the API key in the chat context. This operation is automatically persisted and remains valid after restarting DSH.
  • generate_speech: Uses Microsoft Edge TTS to convert text into speech audio. It supports multi-role conversation scenarios and has audio merging capabilities.

Installation and Configuration

Installing the plugin requires the DSH CLI tool. After installation, the plugin runs with the permissions of the current DSH process. It is recommended to review the source code and license before installation.

The installation command is as follows:

dsh plugin --profile web add github:xby_skill/xby-speech-synthesis

Before use, you need to visit the Xiao Ben Yang official website, register, and obtain an API key.

Usage Steps

After configuring the environment, perform the following steps in order:

  1. Use the set_xby_apikey command in the DSH chat window to set the key.
  2. Use the generate_speech command to generate speech.

Notes

  • The plugin depends on the API service of the Xiao Ben Yang official website. You must complete registration and obtain the key in advance.
  • Comply with the terms of the MIT License.
  • The plugin currently has 0 stars. Please evaluate its stability based on your actual needs.