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。

Experimental Voice Input Bundle — DeepSeek Harness 插件(DSH Plugin)
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

@deepseek-ai/dsh-experimental-voice-input-bundle

Experimental Voice Input Bundle

实验性语音输入,使用本地 SenseVoice;首次使用时下载其运行时

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add @deepseek-ai/dsh-experimental-voice-input-bundle@0.1.7-alpha.1
README兼容性版本

兼容性与来源证明

Experimental Voice Input Bundle 以 @deepseek-ai/dsh-experimental-voice-input-bundle 发布,当前版本为 0.1.7-alpha.1。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
any
发布来源
npm
Registry 更新时间
2026/10/9

版本

0.1.7-alpha.1prerelease
2026/9/22
查看其余 6 个版本收起版本
0.2.1-alpha.1prerelease
2026/10/3
0.2.0-rc.2prerelease
2026/9/29
0.2.0-rc.1prerelease
2026/9/28
0.1.7-rc.2prerelease
2026/9/24
0.1.7-rc.1prerelease
2026/9/23
0.1.7-alpha.2prerelease
2026/9/22

相关插件

正在加载相关插件…

最新版
0.1.7-alpha.1
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
10.7 kB
文件数
11
Surface
any
许可证
MIT
发布源
npm
GitHub
★ 245.8k
周下载
179,560
安全扫描
✓ v0.1.7-alpha.1 扫描通过
最近提交
2026/10/3
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


description: "Enable experimental speech input from the plugin manager." kind: "package-bundle"

@deepseek-ai/dsh-experimental-voice-input-bundle

English | 中文

Summary

This optional bundle composes a speech Service Definition, local SenseVoice provider, authenticated Remote and browser microphone control. Shipped profiles leave it disabled.

Table of Contents

  • Use this package
  • Understand the implementation
  • Further Exploration
  • Model Experience
  • Known Limitations and Deferred Work
  • Dev Note

Use this package

Open Plugins in the Web sidebar and enable Voice Input, marked by a blue waveform icon. If models need preparation, a dialog offers Go to setup or Later; Go to setup opens the bundle details. Complete caches need no setup prompt. In the details, choose Download and prepare; the collapsed current-step summary expands to the complete step list. Downloads report actual bytes; verification and loading show elapsed time. Once ready, click the microphone between the model selector and Send, then Stop to insert a transcript. Bundle details store the recognizer and language through the Settings service. Disabling the bundle cancels active work; cached assets remain on disk.


Understand the implementation

Maintainer details — click to expand

The static cordis.patch.yml adds the four voice rows, selects sensevoice-local as the default recognizer and supplies the provider cache directory with dshHomePath. Optional-bundle installation makes the package available to management without selecting it in default profiles. The browser contribution owns its generated Remote mount; stable API Remotes do not import experimental code. No runtime invariant companion is published because this configuration-only package has no independently mutable runtime state.


Further Exploration

Voice input subsystem


Model Experience

None, as recordings and preparation remain outside model requests; ordinary user submission owns any later text.

KV Cache effect

No direct effect; ordinary submission owns the message content.

Known Limitations and Deferred Work

  • The initial bundle supplies one local recognizer. Additional providers register with the same service under distinct ids; cloud recognition requires an explicit new provider and credential configuration. The bundle does not add a model tool or change the agent loop.
  • Installing dsh also installs sherpa-onnx-node and its platform-specific native runtime, including ONNX Runtime, even when this bundle is disabled. Runtime installation adds disk and download costs separate from the models downloaded by Download and prepare; the native package size varies by platform and version.

Dev Note

Maintainer details — click to expand

None.

相关插件

继续浏览 vision-media 分类下经过校验的插件。

Modlens@liustack/modlens面向仅支持文本的 LLM 的插件视觉能力,由免费的 Antigravity CLI 提供支持Tool Describe Image@linxin666/dsh-tool-describe-image面向模型的 describe_image 工具,用于 dsh Web GUI:通过在兼容 OpenAI 的端点调用视觉语言模型,为文本模型提供图像理解能力,以描述一张图像(本地路径、http(s) URL 或附件引用)。可热插拔 —Vision Toolkit@anionex/dsh-vision-toolkit面向 Harness 原生集成的 DeepSeek 与 agent-vision-toolkit:图像问答、OCR、定位、UI 还原、像素差异、Artifacts 和 Web UI。Deepseek Ivideodeepseek-ivideoiPolloWork HyperFrames Video Studio,以及 27 个可编辑视频模板,以原生 DeepSeek Harness 对话视图呈现。