Zhangbo-cn/dsh-voice-input-plugin
Composer mic for the Web UI: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.
$ dsh plugin --profile web add github:zhangbo-cn/dsh-voice-input-pluginHealth breakdown
40 / 100This plugin has not fully disclosed its data-collection behavior. Review the source and manifest before installing.
Security
Key metrics
Related
Related plugins
dsh Web GUI 社区插件市场：浏览 awesome-dsh-plugin.com 插件目录，一键安装/卸载到 profile。Community plugin market for the DeepSeek Harness (dsh) web GUI: browse, install and uninstall plugins into a profile.
AI image generation for the DSH Web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / gpt-image-1 / dall-e-3), with an api_url/api_key settings card and a sidebar split-pane generation studio.
A floating command deck that lists every slash command in DeepSeek Harness as runnable buttons, sorted by usage.
In-conversation generative UI: the model renders interactive HTML cards into the chat stream, with streaming preview and sandboxed rendering.
Codex Appshots for DSH: capture the frontmost active window via global shortcut and seamlessly mount it into the composer for agent queries.
Upload arbitrary local files from the DeepSeek Harness Web composer, attach their container paths to prompts, and manage stored uploads from Settings.