DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles，发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目，与 DeepSeek 官方无隶属、授权或背书关系。

DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins

dsh-live-voice

Live Voice

本地优先的免手操作 AI 语音助手插件，适用于 DeepSeek Harness (DSH)，支持语音转文字、文字转语音、语音命令和本地语音引擎。

插件会安装到这里；不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add dsh-live-voice@0.7.0
README兼容性版本

兼容性与来源证明

Live Voice 以 dsh-live-voice 发布，当前版本为 0.7.0。Plugin Hub 会校验它的 manifest，并保存精确安装来源，便于复现安装结果。

DSH 兼容范围
*
运行环境
web
发布来源
npm
Registry 更新时间
2026/11/5

版本

0.7.0stable
2026/10/28
0.6.2stable
2026/10/17
0.6.1stable
2026/10/15
查看其余 21 个版本收起版本
0.6.0stable
2026/10/15
0.5.2stable
2026/10/12
0.5.1stable
2026/10/11
0.5.0stable
2026/10/10
0.4.1stable
2026/10/9
0.4.0stable
2026/10/7
0.3.2stable
2026/10/4
0.3.1stable
2026/10/4
0.3.0stable
2026/9/24
0.2.3stable
2026/9/21
0.2.2stable
2026/9/20
0.2.1stable
2026/9/19
0.2.0stable
2026/9/18
0.1.0stable
2026/9/15
0.0.2stable
2026/9/15
0.0.1-alpha.1prerelease
2026/9/15
0.3.0-preview.5prerelease
2026/8/30
0.3.0-preview.4prerelease
2026/8/30
0.3.0-preview.3prerelease
2026/8/29
0.3.0-preview.2prerelease
2026/8/29
0.3.0-preview.1prerelease
2026/8/28
最新版
0.7.0
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
99.3 MB
文件数
245
Surface
web
许可证
Apache-2.0
发布源
npm
GitHub
★ 6
周下载
583
最近提交
2026/10/30
查看源码 ↗项目主页 ↗
README Badge

点击下方 Badge 复制 Markdown，粘贴到 README 即可。

这是你的 Plugin？认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库，即可管理这个公开页面。认领后，Hub 会优先安排当前版本的安全扫描，并在通过后公开展示结果。

认领这个 Plugin →
报告问题

README

DSH Live Voice

Local-first speech-to-text (STT), text-to-speech (TTS), and meeting audio transcription plugin for DeepSeek Harness (DSH). Local speech processing does not make DSH or its AI provider fully offline.

Installation

Tested with DeepSeek Harness v0.2.1-rc.2. The package manifest's dshTestedVersion field records the tested version.

Install the prebuilt package from npm; no source build is required. The Git repository contains source only.

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

Restart DSH, then open DSH Settings → Live Voice to configure recognition and speech engines.

Requirements and configuration

  • Microphone capture requires browser support, permission, and a secure context (HTTPS or localhost).
  • Recognition and synthesis engines have separate language, platform, and model requirements. See the engine guide before selecting a setup.
  • Meeting transcription uses Qwen HTTP or Whisper HTTP recognition. Shared-audio availability depends on the browser, system, and sharing surface; obtain appropriate participant consent.
  • Capturing meeting audio and sharing assistant playback require separate setup. This is not a native Google Meet or Teams integration.
  • The optional dsh-live-voice-debugger package is not required by the main plugin.

Documentation

  • Project overview — canonical presentation, screenshots, and use cases.
  • Configuration and conversation flow
  • Speech recognition engine selection
  • Architecture
  • Release notes
  • Issue tracker

License

Apache-2.0