DSH Plugin HubDSH 插件市场

victorwads/dsh-live-voice

Plugin插件 Native原生 ⭐ 3 Apache-2.0 Vision & Media视觉与多媒体Models & Routing模型与路由Sessions & Context会话与上下文

Local-first voice conversations for DSH. Run speech recognition and speech synthesis on your own machine, with optional external providers.

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

dsh-live-voice is a native DSH plugin that adds local-first, hands-free voice conversation functionality to DeepSeek Harness. It enables users to speak prompts directly into the DSH composer, have DSH read aloud assistant responses and structured questions, and keep the conversation going without touching the keyboard or mouse. To install, users run npx dshpub add victorwads/dsh-live-voice --profile web to add the plugin to their DSH web profile. The installer resolves the repository to an exact commit for stability before adding the bundle, then users access its settings panel after restarting DSH.

When voice conversation mode is active, the plugin coordinates input and output to avoid overlapping speech, so the assistant won’t start speaking while the user is still talking. It offers two listening modes: gated listening for speaker users, which turns off the mic during assistant playback to avoid the assistant hearing its own voice, and open mic mode for headphone users that allows interrupting playback mid-response. It also supports configurable spoken commands for common controls like sending, clearing, muting, resuming, or ending conversations, making it ideal for users who want to keep their hands free for other tasks.

The plugin is released under the open-source GPL-3.0 license. It supports multiple speech recognition and synthesis engines, including browser SpeechRecognition, local whisper.cpp, and Qwen3-ASR/TTS running on Apple MLX. All speech processing can run fully locally for privacy, but the plugin does not install, manage, or start third-party speech engines or model weights; you need to have those set up and running before you can use them. The DSH language model itself may still connect to remote APIs even when all speech processing is local.

dsh-live-voice 是专为 DeepSeek Harness (DSH) 开发的原生语音插件，提供本地优先的免提语音对话功能，支持将语音输入直接转写到 DSH 编辑器，还能让 DSH 朗读助手回复和结构化提问，全程无需操作键盘鼠标。用户可以通过 dsh.pub 工具执行 npx dshpub add victorwads/dsh-live-voice --profile web 命令将其安装到 DSH 网页端配置文件，安装后可在 DSH 设置中找到插件配置面板。

开启语音对话模式后，插件会协调语音输入和输出，避免两者互相干扰，支持自动在你说话结束达到设定静默时长后发送消息，朗读完助手回复再继续倾听。针对不同使用场景，它提供了两种监听模式：给扬声器用户默认使用的门控监听模式，以及给耳机用户允许打断朗读的开麦模式。它还支持自定义语音指令控制对话流程，适合需要解放双手进行 AI 对话的用户使用。

插件本身采用 GPL-3.0 开源协议，支持多种语音识别和合成引擎，包括浏览器自带的 SpeechRecognition、本地运行的 whisper.cpp、苹果 MLX 框架上的 Qwen3-ASR 语音识别；输出支持浏览器语音合成、macOS 原生 say 命令、Qwen3-TTS。语音处理可完全本地运行，保护隐私，但依赖外部已搭建好的本地语音服务，插件本身不管理模型权重和服务进程。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-live-voice（victorwads/dsh-live-voice）
仓库：https://github.com/victorwads/dsh-live-voice
本站详情页：https://www.yhbd.top/plugins/victorwads-dsh-live-voice/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 Apache-2.0 · ⭐ 3 · 最近提交 2026-09-24 · 主语言 TypeScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 3 stars - very few users, little community feedback星标只有 3，几乎没人在用，遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装 

dsh plugin --profile web add github:victorwads/dsh-live-voice

把 victorwads/dsh-live-voice 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

5.1 KB · 缓存于 2026-09-22 19:42:30 · 5.1 KB

DSH Live Voice

npm version DSH License: Apache-2.0

A local-first, hands-free voice assistant plugin for DeepSeek Harness (DSH). Built in Brazil 🇧🇷 and tested daily with Brazilian Portuguese on macOS.

Speak, listen, answer prompts, and code without touching your keyboard. DSH Live Voice coordinates speech-to-text (STT) and text-to-speech (TTS) into a single, conflict-free conversational flow.

⚡ Quick Start

Install with npx dsh into your DSH web profile:

npx dsh plugin add --profile web dsh-live-voice

Open DSH Settings → Live Voice after your next DSH startup.

🌍 Interface Languages

DSH Live Voice’s plugin interface is translated into the following languages. This refers to the visible plugin UI—not speech-recognition or text-to-speech language support.

  • 🇺🇸 English
  • 🇧🇷 Portuguese (Brazil)
  • 🇪🇸 Spanish
  • 🇫🇷 French
  • 🇮🇳 Hindi
  • 🇨🇳 Chinese

📚 Documentation

Detailed guides for deep-diving into engines and configurations:

🎯 Which Speech Engine Should I Use?

Scenario Recommendation RAM Why
🇧🇷 Portuguese on macOS Qwen3 ASR (HTTP API) ~3 GB Best accuracy in daily maintainer use. Whisper is second choice.
🇺🇸 English on macOS Browser SpeechRecognition ~0 GB Built-in macOS/browser API. Fast, zero extra RAM.
🪟 Windows Qwen3 ASR or Whisper HTTP ~2–3 GB Recommended starting point; Windows browser STT varies.
🌐 Multilingual / Other Whisper HTTP (auto) ~2 GB Automatic language detection across dozens of languages.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 victorwads/dsh-live-voice 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev dsh-task-control 下一个 Next ClashTUNWithDSH →