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 Voice — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins

dsh-plugin-voice

Plugin Voice

DeepSeek Harness plugin: voice + notification outputs—agents proactively contact users through cloud TTS (Volcano seed-tts / Xiaomi MiMo V2.5, with automatic fallback to SAPI on failure), desktop notifications, and alert sounds. Combines the native DSH integration of dsh-plugin-notify with the cloud

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

npx -y @deepseek-ai/dsh plugin --profile web add dsh-plugin-voice@0.2.5
READMECompatibilityVersions

Description

DeepSeek Harness plugin: voice + notification outputs—agents proactively contact users through cloud TTS (Volcano seed-tts / Xiaomi MiMo V2.5, with automatic fallback to SAPI on failure), desktop notifications, and alert sounds. Combines the native DSH integration of dsh-plugin-notify with the cloud TTS tuning of agent-voice-mcp-minus, with zero Python dependencies and native Windows support.

Compatibility and provenance

Plugin Voice is published as dsh-plugin-voice and currently resolves to version 0.2.5. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
9/1/2026

Versions

0.2.5stable
9/1/2026
0.2.4stable
9/1/2026
0.2.3stable
8/29/2026
Show 2 more versionsCollapse versions
0.2.2stable
8/29/2026
0.1.2stable
8/29/2026

Related plugins

Loading related plugins…

Latest
0.2.5
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
491 kB
Files
18
Surface
web
License
MIT
Source
npm
GitHub
★ 0
Weekly downloads
0
Last push
9/1/2026
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

Related plugins

More verified plugins in vision-media.

Tool Describe Image@linxin666/dsh-tool-describe-imageModel-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable — Modlens@liustack/modlensPlug-in vision for text-only LLMs, powered by the free Antigravity CLIDeepseek Ivideodeepseek-ivideoiPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.Image Gendsh-image-genBring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.

README

dsh-plugin-voice

DeepSeek Harness 插件：语音 + 通知出口——agent 通过云端 TTS（火山 seed-tts / 小米 MiMo V2.5，失败自动回退 SAPI）/ 桌面通知 / 提示音主动联系用户。Windows 原生，零 Python 依赖。

功能

  • 云端高质量 TTS：火山 seed-tts 大模型流式合成 + 小米 MiMo V2.5（OpenAI 兼容，预置音色），情绪声学/指令映射
  • 智能兜底：云端引擎失败（断网 / 额度 / Key 失效）自动回退 Windows SAPI 离线语音
  • 场景化提示音：5 场景各配一个内置 WAV 音效，播完立即接语音
  • 智能呼叫：回合结束通知 → 60 秒确认窗口 → 超时且你离开 → 语音叫你回来；agent 提问等待过久也自动呼叫
  • 长文案优化：按句切分并行合成 + 文本清洗（不读代码块 / URL / Markdown 标记）
  • 设置面板：引擎 / 音色 / 音量 / 语速 / Key / 场景模板与提示音，实时生效，支持试听
  • 测试页：浏览器打开 /voice，选模式 / 场景 / 情绪点发送

安装

dsh plugin --profile web add dsh-plugin-voice
dsh web   # 重启生效

要求：Windows 10 / 11 + Node.js 22.5+（PowerShell 系统自带）。

pnpm 用户：推荐用上面的 registry 安装（npm 包自带构建产物，零配置秒装）。git 方式安装需克隆仓库（较慢），且 pnpm 的 allowBuilds 只认「包名@精确 tarball URL」（URL 含 commit hash，仓库每次更新都会变），供应链门禁还可能改写你的 pnpm-workspace.yaml。本仓库已提交 lib/，git 安装无需现场构建；若仍被 ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED 拦截，改用 registry 安装即可。

使用

模型主动播报（核心场景）——直接对话即可：

"查一下项目状态，完成后用语音叫我"

手动播报 / 通知：

/voice 任务完成了
/voice --scene=task_complete --emotion=happy 搞定了

配置

设置面板（DSH 设置 → 语音）即可完成全部常用配置，引擎可自选（默认 auto）。支持两个云端引擎（可同时配置 Key，auto 按 MiMo → 火山 → SAPI 顺序自动选择已配 Key 的引擎）：

  • 小米 MiMo：在 mimo.mi.com 控制台获取 API Key → 面板填入（或环境变量 MIMO_API_KEY），预置音色开箱即用（mimo_default / 冰糖 / 茉莉 / 苏打 / 白桦 / Mia / Chloe / Milo / Dean）
  • 火山：注册火山引擎 → 开通「语音合成大模型」→ 创建 X-Api-Key → 面板填入（或环境变量 VOLCANO_API_KEY）

未配置任何 Key 自动用 SAPI 离线语音（不报错）。

高级参数（角色 / 场景音色 / 云端音质微调）见 config.example.json。

致谢

  • dsh-plugin-notify by huguangyu666 —— DSH 原生集成骨架
  • agent-voice-mcp-minus —— 云端 TTS 引擎
  • 火山引擎 · 豆包语音合成大模型

License

MIT（继承两源项目协议，保留原作者署名）