DSH Plugins Marketplace

DSH Plugins

Plugins

/

Tools & Capabilities

/

dsh-fake-call

d

dsh-fake-call

Manifest valid

Give your agent a phone: a local incoming-call screen that really rings in the browser, speaks a preset opening line with the OS voice (no API key, fully offline), and can call again if nobody picks u

hasBundlePatch

dsh-fake-call

一页"有人打电话给你"的通话界面,对面是 DSH 里的 AI —— 声音在本机合成,零 API key。

打开 /fake-call 就是一个来电:头像在跳、有接听/挂断。点接听,对面真的会说话(Windows 自带的语音合成,离线、不花钱),你打字回它,它用一两句口语接你的话。

它和"AI 打电话"的区别

市面上那些"AI 主动打电话"要么走 Twilio / WhatsApp Business(要企业资质、按分钟计费),要么其实只是把来电界面做出来的演示。这个插件把"演示"这部分做扎实:

真不真
听见声音✅ 本机 SAPI 合成,真的出声
对话✅ 走 DSH 自己的会话,有上下文
打电话到你手机❌ 没有运营商通道,做不到
录音/上传音频❌ 不录音、不上传

装

dsh plugin --profile web add dsh-fake-call

目前只支持 Windows(依赖系统自带的 SAPI 语音合成)。

用

  1. 浏览器打开 http://127.0.0.1:61310/fake-call
  2. 点「接听」
  3. 打字说话(未来会接语音识别)

也可以让 AI 主动打过来 —— 它会调用 fake_call 工具让页面进入振铃状态:

fake_call { "caller": "小鱼" }

配置

键默认说明
caller小鱼来电显示的名字
voice空指定音色,空则自动挑系统里的中文音色
cwd宿主 cwd通话会话的工作目录
replyTimeoutMs120000一轮回复上限
maxRounds40一通电话最多几轮

实现要点

  • TTS 缓存:同一句话只合成一次(%TEMP%\dsh-fake-call\<md5>.wav),重复句子不再等 1 秒
  • 文本注入防护:拼进 PowerShell 的文本会做单引号转义,避免引号逃逸
  • 只取一句话:模型爱写长段落,oneLine() 会剥掉代码块/列表/链接并截断,保证像打电话
  • 业务内核与宿主解耦:路由逻辑在 lib/call.js,不 import 任何 DSH 内部模块,测试里注入假 agents 就能跑

已知限制

  • 只有 Windows 能用(macOS/Linux 需要换 TTS 后端)
  • 用户侧输入目前是打字;语音识别(ASR)还没接
  • 音色取决于系统装了什么(中文一般是 Microsoft Huihui)

License

MIT

Comments

Loading…

Similar plugins

dsh-plugin-call-me

by radres

Your DeepSeek Harness agent rings your actual phone: it asks out loud, you answer out loud, and what you said steers the run.

Tools & CapabilitiesManifest valid

★ 8

MIT

JavaScript

Nov 5, 2026

dsh plugin --profile web add dsh-plugin-call-me

A Phone tab in dsh-better-sidebar: SMS and calls over Twilio and SIP lines bridged through Asterisk, call audio through your server, Live, Voicemail and Do not disturb modes with live voicemail transc

Tools & CapabilitiesManifest valid

★ 0

dsh plugin --profile web add @lucagiftzek/dsh-phone

Sounds a chime and raises a desktop notification when the agent needs you — stage completion, approval requests, awaiting input, task completion, and errors, each with its own tone.

Notifications & IntegrationsManifest valid

★ 0

dsh plugin --profile web add dsh-ping

by ws1234567891011

Makes the agent narrate its process: every turn opens with how it reads the message and what it will do first, then short interim notes between tool-call batches, with in-app settings for style, sente

Development & InfrastructureManifest valid

★ 4

↓ 1.4k/wk

MIT

JavaScript

Nov 10, 2026

dsh plugin --profile web add dsh-interim-narration

by PandaPolo

Give a DeepSeek Harness agent a voice it owns — offer_call rings the human (接听/拒接/稍后); local-first TTS/STT via CrispASR + Qwen3-TTS (9 voices, 2 CN dialects). DSH 0.1.2-rc.1 compatible. Fork of dsh-vo

Tools & CapabilitiesVision & MultimodalSessions & MessagesManifest valid

★ 4

↓ 769/wk

MIT

TypeScript

Nov 6, 2026

dsh plugin --profile web add dsh-voice-call

Voice call assistant for the DSH Web GUI: a draggable floating call ball, browser-side VAD that sends each utterance after a pause, FunASR HTTP or streaming speech recognition, MiniMax or OpenAI-compa

Workflow & AutomationVision & MultimodalTerminal & ClientsManifest valid

★ 0

dsh plugin --profile web add @biliye/dsh-voice-call