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 Catgod Call — DSH Plugin for DeepSeek Harness
← Plugins
P

dsh-plugin-catgod-call

Plugin Catgod Call

小猫之神 · Voice-calling plugin: When the AI wants to call the user, it uses the catgod_call tool to convert text into speech and play it loudly through the system speakers.

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

npx -y @deepseek-ai/dsh plugin --profile web add github:2102638035-svg/dsh-plugin-catgod-call#407bc2a11d3890970c20c544f2fa11d0e1138cdd
READMECompatibilityVersions

Compatibility and provenance

Plugin Catgod Call is published as dsh-plugin-catgod-call and currently resolves to version 1.0.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

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

Versions

1.0.0
stable
10/10/2026

Related plugins

Loading related plugins…

Latest
1.0.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
10/10/2026
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.

Acp App@deepseek-ai/dsh-acp-appThe dsh ACP profile bundle: automation-only JSON-RPC stdio and process lifecycle over dsh-baseAb Publishdsh-ab-publishBrowser-automation publishing tool that logs into and posts to arbitrary websites, in one publishable plugin packageAb Wechat Scrapedsh-ab-wechat-scrape--- description: "The out-of-tree wechat_scrape tool: retrieves WeChat official-account articles, filters promotional blocks, and saves each as a Markdown file, for maintainers of this machine's dsh profiles." kind: "package-reference" ---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 r

README

dsh-plugin-catgod-call

给 AI 一个"喊话"工具:把文字合成语音,用扬声器大声喊出来。

一个 DSH (DeepSeek Harness) 插件,让 AI 在需要你回来的时候真的把你叫过来。


它解决什么问题

AI 在对话里说"请回来看一下"——但你不在屏幕前,看不到。

这个插件给 AI 一个工具 catgod_call。当它觉得该叫你时,直接调用: 合成语音 → 音量拉满 → 叮咚 → 大声播放 → 音量还给你。


特性

  • 双引擎:在线(硅基流动 CosyVoice2)/ 离线(Windows SAPI,零成本兜底)
  • 自动回退:在线失败自动切离线,保证一定喊出声
  • 叫醒模式:叮咚提示音 + 强制音量 100% + 可循环重喊
  • 音量三重保险:用完必定还回去,详见下文
  • 零依赖:不需要 @deepseek-ai/dsh-tools,手写 defineTool 等价物

安装

1. 放置插件

把本目录放到任意位置,然后建链接到 profile 的 node_modules:

mklink /J "%DSH_HOME%\profiles\<profile>\node_modules\dsh-plugin-catgod-call" "<本目录>"

2. 注册到 profile

编辑 $DSH_HOME/profiles/<profile>/package.json:

{
  "dependencies": {
    "dsh-plugin-catgod-call": "link:<本目录绝对路径>"
  },
  "dsh": {
    "profile": {
      "bundles": [
        "dsh-plugin-catgod-call"
      ]
    }
  }
}

3. 配置密钥

推荐用环境变量,别把密钥写进文件:

$env:SILICONFLOW_API_KEY = "sk-..."
$env:CATGOD_TTS_PROXY     = "http://127.0.0.1:7890"   # 可选

也可以直接写在 cordis.patch.yml 的 apiKey / proxy 字段里。

4. 重启 DSH

插件改动必须重启才生效。


配置项

编辑 cordis.patch.yml:

配置默认说明
engineonlineonline = 在线合成;offline = 仅离线 SAPI
fallbackToOfflinetrue在线失败是否回退离线
apiUrl硅基流动兼容 OpenAI /v1/audio/speech 的服务
apiKey空留空则读 SILICONFLOW_API_KEY 环境变量
modelFunAudioLLM/CosyVoice2-0.5B模型名
voice...:alex音色,见下方说明
proxy空HTTP 代理,留空直连
speed1.1语速 0.25 ~ 4.0
sapiVoiceMicrosoft Huihui Desktop离线音色
sapiRate2SAPI 语速 -10 ~ 10
wakeDingdongtrue叫醒模式是否播叮咚
forceMaxVolumetrue播放前拉满音量,播完恢复
repeatIntervalMs0循环重喊间隔(毫秒),0 = 不循环
repeatMax3最多喊几次
addressAs主人默认称呼
toolDescription—给 AI 看的工具说明

音色怎么填

官方内置音色

格式:FunAudioLLM/CosyVoice2-0.5B:<name>

可用的 name:alex benjamin charles david anna bella claire diana

voice: "FunAudioLLM/CosyVoice2-0.5B:alex"

克隆音色

先上传参考音频,再查自己的音色列表:

curl -X POST https://api.siliconflow.cn/v1/audio/voice/list \
  -H "Authorization: Bearer $SILICONFLOW_API_KEY"

返回的 uri 字段就是要填的值,格式为:

speech:<自定义名>:<音色ID>:<哈希>

⚠️ 这是三段结构,少一段会报 20047 Invalid voice。 这个 uri 与你的账号绑定,不要公开分享。


AI 能传的参数

参数类型说明
textstring必填,要喊的话
wakeboolean叫醒模式(叮咚 + 音量拉满 + 循环)
addressstring开头称呼
prefix_addressboolean是否自动加称呼
engineenumdefault / online / offline
repeat_maxnumber最多播几次
repeat_interval_msnumber间隔毫秒

音量安全:四重保险

播放前拉满音量,播放后必定恢复原值。 四层保障:

保险机制应对场景
一PowerShell try/finally播放中途崩溃
二Node 侧超时兜底PowerShell 进程被强杀
三恢复后校验 + 补恢复PowerShell 说恢复了但值不对
四看门狗(启动时 + 每次调用前)整个宿主被杀

状态文件机制

拉高音量之前把原音量写入状态文件:

%TEMP%\catgod-call-volume-state.json
  • 恢复并校验成功后才删除
  • 恢复失败时保留,留给下次补救
  • 看门狗在插件启动时和每次喊话前都会检查它,发现残留立刻补还

早期版本有个 bug:无论恢复成功与否都删除状态文件, 导致恢复失败后看门狗再也救不回来,音量永久卡在 100%。 现在只在确认恢复成功时才清除。

一个实现细节

Restore-Volume 函数内部整体 try/catch 且绝不外抛。 因为它在 finally 里调用,一旦抛出会覆盖真实错误、连结果输出都跳过, Node 侧将完全收不到诊断信息。

许可

MIT