dsh-tts-reader：用小艺边写边念助手回答
lemonhall/dsh-tts-reader 是 DSH 联网工具插件，默认用 zh-CN-XiaoyiNeural 逐句朗读助手流式输出，Web Audio 连播；输入框喇叭控实时朗读，消息下喇叭可重读历史。宿主监听 agent/assistant-stream 与 snapshotEvents，零依赖 Edge TTS 客户端合成；页面 400ms 游标拉取 MP3。可通过 SkillHub 让 Harness 按安装计划安装，配置在 cordis.patch.yml。相对 SKILL 式整段 MP3，更贴合边生成边听。MIT v0.1.0。
Read MoreEdge TTS：在 Agent 里按需触发文字转语音
Edge TTS（@user_c9d52b8e/edge-tts-mf）是 SkillHub 社区版 1.0.0 语音合成 Skill，分类 design-media，标签 requires_api_key=false。当用户提出文字转语音、读出来、语音回答、播放音频或配置 TTS 时由 Agent 触发。安装需 SkillHub CLI，使用 skillhub install @user_c9d52b8e/edge-tts-mf --dir 指向 Cursor 等客户端的 skills 目录；亦可按 skillhub.cn/install/skillhub.md 让 AI 安装。公开页未给出具体合成命令，用法以 SKILL.md 为准。
Read Moredsh-voice: DeepSeek Harness Web Voice Message Plugin
`dsh-voice` is a voice plugin for DeepSeek Harness, designed to enhance the interactivity of the Web UI. It leverages the Microsoft Edge TTS engine to enable agents to proactively send voice messages and users to listen to audio. The plugin implements its core features by registering the `voice_say` tool and HTTP routes, and renders a player in the browser. During installation, its path must be added to the configuration and the Profile restarted. The plugin requires no API key, supports multiple neural voices, caches audio files locally, and is suitable for developers needing rich voice interaction scenarios.
Read Morexby-speech-synthesis: Edge TTS-Based Speech Synthesis Service Plugin
The `xby-speech-synthesis` plugin is an MCP server designed specifically for DeepSeek Harness (DSH), integrating Microsoft Edge's high-quality speech synthesis capabilities. It is open source (MIT license), supports multilingual, multi-role dialogue, and audio merging, and requires prior registration on the official Xiaoben Yang website to obtain an API key. Users can install it via CLI and use the `set_xby_apikey` and `generate_speech` commands in the DSH chat window to configure and generate speech.
Read Moredsh-tts: Voice broadcast plugin for dsh web final results
dsh-tts is a dsh web text-to-speech (TTS) plugin developed by vim0x3c (version 0.1.0, MIT license), designed to reduce the reading cost of long text through voice synthesis. Utilizing Edge TTS technology, this plugin reads only the final assistant response while ignoring intermediate steps. It supports segmented serial reading of long replies, speed adjustment ranging from 0.5x to 2x, and offers over 20 voice options. It provides built-in approval sounds or custom audio functionality and automatically falls back to the browser's local Web Speech API when Edge cloud synthesis fails. The plugin has no third-party dependencies, supports offline installation, and requires installation into the web profile via a local tarball combined with the `-w` flag. After installation, the local bridge service binds to 127.0.0.1 and occupies ports 8765-8780 to provide synthesis and health check interfaces, setting...
Read Moredsh-plugin-tts: Reading Assistant Replies in DeepSeek Harness
dsh-plugin-tts is a client-side plugin for the DeepSeek Harness web configuration file, maintained by 1624318455 (MIT, v0.3.0). Based on Microsoft Edge's free TTS, it requires no API Key and offers features such as a message reading button, an auto-read toggle, and a voice settings panel. Optionally, local RVC custom voices are supported. It supports seamless long-text chunked playback, selection reading, MP3 download, and voice notification approvals. Installation: dsh plugin --profile web add "github:1624318455/dsh-plugin-tts#main". Requires Node.js >= 22 and a restart of dsh web to take effect.
Read More