DSH Plugin HubDSH 插件市场
Zhangbo-cn/dsh-voice-input-plugin 预览 preview

Zhangbo-cn/dsh-voice-input-plugin

Plugin插件 Native原生 ⭐ 6 MIT Vision & Media视觉与多媒体

DeepSeek Harness Web 的 Composer 麦克风：点击即可监听实时转录，按住即可讲话，同时支持主机 Edge TTS 回复朗读，在模型生成时流式播放，朗读时回声暂停，点击即可停止。

Project Overview项目介绍

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

This is a native voice input plugin built exclusively for DeepSeek Harness (DSH), which adds a small microphone button to the DSH composer toolbar. It converts speech to text directly in the user’s browser using the Web Speech API, so no external API key is required for transcription. It offers two operational modes: tap-to-monitor for live word-by-word streaming input, and hold-to-talk for voice chat that sends your message when you release the button. You can install it with one command via the DSH CLI: dsh plugin add @zhangbo-cn/dsh-client-ui-voice-input.

This plugin is designed for developers who prefer voice interaction, or for moments when your hands are occupied while using DSH. For tap-to-monitor mode, once you tap the mic button, it will keep listening even through silences, and speech streams directly into the draft input. You can send your message at any time, or configure an auto-send timer that triggers after a set period of silence, letting you use the plugin entirely hands-free.

The plugin is released under the open source MIT license. Speech recognition requires a browser that supports the Web Speech API, which works on Chrome, Edge, and Safari, but not Firefox due to that browser’s lack of support for the API. To get natural-sounding reply reading, you will need to install the separate DSH Edge TTS plugin; without it, the plugin falls back to your browser’s built-in speech synthesis, which is less natural and occasionally unreliable on idle Chrome.

这是专为 DeepSeek Harness (DSH) 开发的原生语音输入插件，会在DSH的输入工具栏添加一个微型麦克风按钮，通过浏览器 Web Speech API 实现本地语音转文字，不需要额外申请外部 API 密钥。它支持两种工作模式：点击开启监听的逐字实时流式输入，以及按住说话松手发送的语音聊天模式，可配置识别语言、静音自动发送等选项。用户可以通过 DSH 命令行执行 dsh plugin add @zhangbo-cn/dsh-client-ui-voice-input 一键安装。

适合偏好语音交互的开发者使用，在需要口述代码注释、长文本需求、或者双手不便时可以快速完成输入。点击监听模式下，开启后麦克风会持续监听，语音逐字出现在输入框中，随时可以发送，也支持设置静音一段时间后自动发送，完全解放双手。按住说话模式下，松手即发送消息，还会自动朗读大模型的回复内容。

本插件采用 MIT 许可证开源，语音识别依赖浏览器支持 Web Speech API，Chrome、Edge、Safari 都可以正常使用，Firefox 因浏览器本身限制不支持语音输入。要获得更自然的回复朗读效果，需要额外安装 DSH 的 Edge TTS 宿主插件，否则会降级到浏览器自带的语音合成，效果稍差。开发版本可以从 GitHub 仓库直接安装，也支持挂载到 DSH 源码仓库本地构建。

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-voice-input-plugin（Zhangbo-cn/dsh-voice-input-plugin）
仓库：https://github.com/Zhangbo-cn/dsh-voice-input-plugin
本站详情页：https://www.yhbd.top/plugins/zhangbo-cn-dsh-voice-input-plugin/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 6 · 最近提交 2026-08-25 · 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 6 stars - very few users, little community feedback星标只有 6，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 add @zhangbo-cn/dsh-client-ui-voice-input

把 Zhangbo-cn/dsh-voice-input-plugin 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

9.1 KB · 缓存于 2026-08-26 05:40:08 · 9.1 KB

dsh-client-ui-voice-input

Composer voice control for DeepSeek Harness: a minimal linear mic button in the composer tool row that turns your speech into text — with a tap-to-monitor mode (continuous, live 逐字 streaming, send-anytime) and a hold-to-talk voice-chat mode (release to send, reply read aloud). Zero API key: recognition runs in the browser via the Web Speech API; reply reading uses the host's Edge TTS (/api/tts) with a browser speechSynthesis fallback.

dsh-plugin · TypeScript · React

Features

  • Tap to monitor: click the mic, speak — text streams into the draft live (逐字输入), the mic keeps listening even in silence, and you can send or keep adding speech anytime. Tap again to stop.
  • Auto-send on silence (optional): with autoSendOnSilenceMs configured, tap-to-monitor becomes hands-free — once you stop talking for the configured window, the message sends itself ("tap, speak, walk away"). Continued speech cancels the pending send.
  • Hold to talk: press-and-hold to record a voice-chat message, release to send it; the assistant's reply is read aloud — host Edge neural TTS (/api/tts) first, browser speechSynthesis as fallback.
  • Continuous across silences: each recognition segment auto-restarts so monitoring never drops.
  • Respects the composer: speech appends to the draft (base preserved); a send clears the draft cleanly without re-filling old text; monitoring continues after a send on a fresh recognizer.
  • DeepSeek-blue listening state: the icon pulses in DeepSeek brand blue while listening; borderless linear icon, no clutter.
  • Configurable: recognition language (default zh-CN) and interim results.

Install

The package is a dsh.bundle installable, published on npm as @zhangbo-cn/dsh-client-ui-voice-input. One command:

dsh plugin add @zhangbo-cn/dsh-client-ui-voice-input

0.1.1+ required. 0.1.0 registered the browser bundle under the wrong ModuleLoader id (@deepseek-ai/...), so Harness failed with loaded without registering "@zhangbo-cn/dsh-client-ui-voice-input". Upgrade / reinstall, then hard-refresh the Web UI.

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 Zhangbo-cn/dsh-voice-input-plugin 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev dsh-ui-tools 下一个 Next dsh-plan-switch →