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

@opensquad/dsh-voice-input

Voice Input

SenseVoice voice input plugin for DeepSeek Harness: adds a microphone button next to the conversation input box, records audio, and uses the local SenseVoice service to convert it to text and fill the input box. On first use, it automatically downloads the model and displays progress; the backend is

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

npx -y @deepseek-ai/dsh plugin --profile web add @opensquad/dsh-voice-input@0.3.3
READMECompatibilityVersions

Description

SenseVoice voice input plugin for DeepSeek Harness: adds a microphone button next to the conversation input box, records audio, and uses the local SenseVoice service to convert it to text and fill the input box. On first use, it automatically downloads the model and displays progress; the backend is automatically started by the plugin.

Compatibility and provenance

Voice Input is published as @opensquad/dsh-voice-input and currently resolves to version 0.3.3. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
npm
Registry updated
9/22/2026

Versions

0.3.3stable
8/16/2026
0.3.2stable
8/16/2026
0.3.1stable
8/16/2026
Show 3 more versionsCollapse versions
0.3.0stable
8/16/2026
0.2.0stable
8/16/2026
0.1.0stable
8/16/2026

Related plugins

Loading related plugins…

Latest
0.3.3
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
67.6 kB
Files
14
Surface
web
License
MIT
Source
npm
GitHub
★ 0
Weekly downloads
58
Last push
8/16/2026
View source ↗Project homepage ↗
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 — Vision Routerdsh-vision-routerEyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary toolDeepseek Ivideodeepseek-ivideoiPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.Imagegen@dickpy/dsh-imagegenAI image generation plugin for the dsh web GUI: text-to-image and image-to-image through configurable provider channels (gpt-image-2 / grok-imagine-image / nanobanana series / seedream-5.0-pro / dall-e-3, with native xAI Grok Imagine, Google Nano Banana a

README

@opensquad/dsh-voice-input

DeepSeek Harness 语音输入插件:在 Web 对话输入框旁添加一个麦克风按钮,录音后调用本地 SenseVoice 服务转写成文本,自动填入输入框。首次使用会引导下载模型并显示实时进度。

英文版 / English: README_EN.md

功能

  • 🎤 输入框旁麦克风按钮,一键录音转文字
  • ⬇️ 首次使用自动下载模型(约 230MB),按钮上显示圆环进度 + 实时百分比
  • ⚙ 独立管理按钮:查看/卸载已安装的语音模型
  • 自动拉起本地 SenseVoice 服务(模型就绪时)

依赖

这是一个全自动插件:Python 后端(依赖安装 + 进程启动)由插件在 dsh 启动时自动完成,首次使用模型也自动下载。 你只需要:

前置说明
Python 3.10+唯一需要手动装的软依赖(插件会自动 pip install 其余依赖)
ffmpeg(可选/推荐)仅用于异常音频的兜底转码,正常使用不需要;winget install ffmpeg 或官网安装并加入 PATH

手动安装 Python 3.10+

插件会自动安装剩下的 Python 依赖(flask / onnxruntime 等),你只需装好 Python 本身。

  1. 打开 python.org/downloads,下载最新的 Python 3.10+(Windows 选 Windows installer (64-bit))。
  2. 运行安装程序,务必勾选底部的 Add python.exe to PATH,再点 Install Now。
  3. 安装完成后,重新打开一个终端(PowerShell / CMD),验证安装成功:
    python --version
    # 期望输出类似: Python 3.12.x(3.10 或更高即可)
    

手动安装 ffmpeg(可选)

浏览器端会把录音转成标准 WAV,正常使用不需要 ffmpeg。它仅在服务端收到异常/无法识别的音频时作为兜底转码使用,建议安装以免个别浏览器录音无法转写。

  • Windows:在 PowerShell 里执行
    winget install ffmpeg
    
    安装完成后重启终端,验证:
    ffmpeg -version
    
  • macOS(需先装 Homebrew):
    brew install ffmpeg
    
  • Linux (Debian/Ubuntu):
    sudo apt update && sudo apt install -y ffmpeg
    
  • 通用方式:也可访问 ffmpeg.org/download.html 下载,解压后把 bin 目录加入系统的 PATH 环境变量。

插件启动时自动完成:

  1. 探测 Python → 自动安装 flask / onnxruntime / librosa / soundfile / pyyaml 等依赖(首次较慢)
  2. 自动拉起下载网关(gateway.py :7102)
  3. 首次使用 → 自动下载模型(约 230MB)并启动转写服务(service.py :7101)

安装插件

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

重启 dsh 后,插件会在后台自动准备后端,输入框旁会出现麦克风按钮。

使用

  1. 重启 dsh 后稍等片刻(首次会自动装 Python 依赖并启动后端)。
  2. 点击麦克风 → 首次会确认下载模型 → 等待进度完成 → 自动启动服务。
  3. 再次点击麦克风开始录音,再点一次停止并转写,文字自动填入输入框。

模型已安装时,点旁边的 ⚙ 可卸载后重新下载。

兼容性

  • Node.js ≥ 22.19.0
  • Python 3.10+(且 python 在 PATH)
  • DeepSeek Harness(Web profile)
  • 浏览器需支持 MediaRecorder / getUserMedia

License

MIT