DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Plugin Laile Laodi — DSH Plugin for DeepSeek Harness
← Plugins
P

dsh-plugin-laile-laodi

Plugin Laile Laodi

DeepSeek Harness completion sounds: eight generated voices, persistent selection, and bottom-right controls.

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:gkgy/dsh-plugin-laile-laodi#7833a088479c0d3bce7d08a93ce2eab107fff935
READMECompatibilityVersions

Compatibility and provenance

Plugin Laile Laodi is published as dsh-plugin-laile-laodi and currently resolves to version 1.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
10/7/2026

Versions

1.1.0stable
10/7/2026

Related plugins

Loading related plugins…

Latest
1.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
10/8/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in

Related plugins

More verified plugins in integrations-communication.

Remote Web Ui@linxin666/dsh-remote-web-uiScan-to-pair remote access for the dsh web GUI that shares one official interface: a QR beside the settings button pairs phones and PCs into the same Web GUI (a portrait-touch adaptation layer for phones, full desktop on PCs) through one-time tokens and rIm@xmanrui/dsh-im把微信、飞书、企微、钉钉、QQ、Telegram、WhatsApp、Slack、Discord、Matrix接入DSH。 Connect Telegram, WhatsApp, Slack, Discord, Matrix, WeChat, Feishu, WeCom, DingTalk, and QQ to DSH.Ds Botds-botDS Bot: a team of long-lived Bots for DeepSeek Harness, with Main Bots, Bot-to-Bot messages and group chatsFree Searchdsh-free-searchFree web search for DeepSeek Harness: 24 engines (Bing/DuckDuckGo/AnySearch/SearXNG/Exa/Tavily/Keenable/Firecrawl/Parallel keyless; Zhihu global/site via MCP and Perplexity/SerpBase/DeepSeek/You.com/Baidu/Kimi/Aliyun/Doubao with key; OpenAI/Gemini/Claude

README

来了老弟 · DeepSeek Harness 完成提示音

助手回复结束后播放“来了,老弟”。支持八种音色,右下角切换与试听,选择会自动保存。

v1.1.0 更新

  • 修复 DSH 0.2.1 会话快照接口变化后不触发声音的问题:使用 running → idle 状态变化,不再读取已移除的 turnEnds / nodes。
  • 不为历史回复、会话切换或失败请求播放完成提示音。
  • 右下角提供音色选择和“测试提示音”,播放失败时显示原因。
  • 默认使用试听中选定的 3 号·逗趣男声,保持该样本原样;提供另外七种音色。
  • 用本地生成音频替换此前捆绑的真人录音。音频来源、生成参数和哈希见 生成记录。

音色

音色类型
3号·逗趣男声(默认)Qwen3-TTS VoiceDesign
低沉男声Qwen3-TTS VoiceDesign
清亮男声Qwen3-TTS VoiceDesign
沙哑大叔Qwen3-TTS VoiceDesign
温柔女声Qwen3-TTS VoiceDesign
活泼女声Qwen3-TTS VoiceDesign
卡通高音3号样本变调
电子机器人3号样本调制和短回声

所有台词均为“来了,老弟”。这些音色是预先生成的文件,播放时无需加载语音模型,也无需外部语音 API。

安装:静态 Bundle(推荐)

先克隆本仓库到固定位置:

git clone https://github.com/gkgy/dsh-plugin-laile-laodi.git

在 DSH 桌面 profile 的 package.json 中,把本包加入 dependencies 和 dsh.profile.bundles。合并以下字段,保留已有插件和配置;将示例路径替换为克隆目录的绝对路径:

{
  "dependencies": {
    "dsh-plugin-laile-laodi": "link:/absolute/path/dsh-plugin-laile-laodi"
  },
  "dsh": {
    "profile": {
      "bundles": ["dsh-plugin-laile-laodi"]
    }
  }
}

在该 profile 目录使用其包管理器安装依赖(如 pnpm install),然后重启 Harness。桌面 profile 通常位于 ~/.dsh/profiles/desktop。

本包同时声明宿主和客户端入口,Bundle 会自动加载二者。不要再重复添加动态宿主,否则音频路由会冲突。

安装后,在 Harness 窗口右下角 选择音色,点击 测试提示音。用户手势可以启用浏览器声音播放。之后正常回复结束时自动播放所选声音。

动态加载(高级方式)

也可将 dynamic/host.js 和 dynamic/client.js 分别填入 cordis_define 的 code.host、code.client,再使用 cordis_run 激活。先修改宿主代码顶部的 ASSET_DIR,指向本仓库的 assets 目录。

动态代码使用与静态 Bundle 相同的音色和界面。不要同时启用两个宿主。动态加载的权限与生命周期由 Harness 管理;静态 Bundle 更适合重启后持续使用。

配置

宿主配置默认值说明
audioPath包内 assets/laile-laodi.mp3无音色参数时使用的默认文件
route/laile-laodi.mp3音频路由;修改时也需修改客户端 URL

客户端通过 ?voice=chosen-3 等参数选择捆绑音色。只有预定义 ID 会被用于查找文件,URL 参数不会直接作为磁盘路径。

浏览器的声音策略、系统静音和输出设备仍可能影响播放。“提示音已播放”表示播放器接受了请求,不能代替耳听确认。

测试与重新生成

npm test

测试覆盖静态/动态客户端的完成状态变化、历史和失败请求、重复播放,以及所有音频路由。

可选的生成工具位于 scripts/generate_audio.py,需要 Apple Silicon、Python、MLX 和 FFmpeg:

python3 -m venv .venv
.venv/bin/pip install -r scripts/requirements-tts.txt
.venv/bin/python scripts/generate_audio.py

输出默认保存在被 Git 忽略的 generated/,不会直接覆盖已发布音频。种子和模型版本相同也不保证不同硬件或依赖环境生成完全相同的波形。

English

A DeepSeek Harness completion-sound bundle with eight generated voice options, persistent selection, and compact bottom-right controls. It follows the DSH 0.2.1 Session lifecycle instead of removed conversation fields. Historical messages, session switches, and failed requests are silent.

Add this local repository as the dsh-plugin-laile-laodi dependency and a dsh.profile.bundles entry in your desktop profile, install dependencies, and restart Harness. Click 测试提示音 once to test playback. Audio is pre-generated; no TTS model runs during ordinary replies. See audio provenance for generation details.

Plugin code: MIT. Model source and license information are documented separately in the audio provenance record.