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.

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

@difimim/dsh-voice-input

Voice Input

DeepSeek Harness voice input plugin: adds a microphone button to the input field and uses the browser Web Speech API to transcribe speech into text in real time.

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

npx -y @deepseek-ai/dsh plugin --profile web add github:difimim/dsh-voice-input-npm#28ce76701d6d5f98f025fc925d3bee8a40ab7475
READMECompatibilityVersions

Compatibility and provenance

Voice Input is published as @difimim/dsh-voice-input and currently resolves to version 1.0.1. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
8/30/2026

Versions

1.0.1stable
8/30/2026

Related plugins

Loading related plugins…

Latest
1.0.1
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 1
Weekly downloads
0
Last push
8/30/2026
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 Voice Input · DeepSeek Harness 语音输入插件

在 DeepSeek Harness(DSH)输入框底部加入一个麦克风按钮:点击后用浏览器内置的 Web Speech API 把语音实时转成文字并填入输入框。零成本、零服务端部署。

A DeepSeek Harness plugin that adds a microphone button to the composer. Click it to transcribe speech into the input box using the browser's built-in Web Speech API — zero cost, zero server.


安装

这是一个标准的 DSH 插件 bundle,用一条命令安装:

dsh plugin --profile web add @difimim/dsh-voice-input

装完重启 DSH(dsh web),按钮就会出现在输入框工具行左侧。

其他 profile(如 tui)同理:dsh plugin --profile tui add @difimim/dsh-voice-input。

从本地 / 未发布源码安装

还没发布到 npm 时,可以按路径安装:

dsh plugin --profile web add file:/path/to/dsh-voice-input
# 或
dsh plugin --profile web add link:/path/to/dsh-voice-input

功能特性

  • 🎙️ 输入框工具行左侧新增麦克风按钮,点击开始 / 停止收音
  • ⚡ 实时识别:边说边把中间结果写进输入框草稿
  • ➕ 追加式写入:不清空已有文字,识别结果追加到当前草稿末尾
  • 🌐 零成本零服务端:直接复用浏览器内置 Web Speech API
  • 🎨 跟随主题:按钮颜色使用 DSH 主题变量,自动适配明暗色

使用

  1. 点麦克风图标 → 按钮变红并出现脉冲动画,开始收音;
  2. 直接说话,文字会实时出现在输入框里;
  3. 再点一下(图标变方块)→ 停止收音;
  4. 确认文字无误后,正常回车发送。

工作原理

部分说明
识别引擎浏览器内置 Web Speech API(SpeechRecognition / webkitSpeechRecognition)
识别语言默认 zh-CN(中文),可在 lib/client.js 里改 rec.lang
写入方式通过输入框 Slot 提供的 inputActions.setDraft() 写入草稿,与手打内容共存
按钮位置conversation.input.left(输入框工具行左侧,模型选择那一行)

浏览器兼容性

浏览器支持
Chrome / Edge✅(推荐)
Safari✅(较新版本,行为略有差异)
Firefox❌(不支持 Web Speech API)
  • 首次点击会弹出麦克风授权,请点「允许」。
  • 需联网:Web Speech API 会把音频交给浏览器厂商的识别服务器。

隐私说明

当前方案(Web Speech API)为了“零成本、零部署”,会把语音发到浏览器厂商的识别服务。若你在意隐私或需要完全离线,请参考下方 Roadmap 的 Vosk 接入计划。

目录结构

dsh-voice-input/
├── package.json      # dsh.client + dsh.bundle.patch 声明
├── cordis.patch.yml  # bundle patch:把本插件挂进 host 组合
├── lib/
│   ├── index.js      # Node 半(纯 UI 插件,空 apply)
│   └── client.js     # 浏览器半(麦克风按钮 + Web Speech 识别)
├── README.md
└── LICENSE

Roadmap

  • Web Speech API 实时语音输入
  • 语言切换(中文 / 英文 / 自动)
  • Vosk 离线识别接入(通过 host 侧 Remote 服务)
  • 语音输入过程中的可视化状态条

License

MIT