기타 확장 · DeepSeek Harness 플러그인 — 178 페이지

Vim keybindings for the deepseek-harness Web GUI, mounted as an out-of-tree Cordis plugin.

Vim modal editing for the dsh Web GUI composer: NORMAL/INSERT/VISUAL modes, a block caret, motions, operators, and the mode indicator

Cross-surface plain-language trajectory visualization and review for DeepSeek Harness.

Secure Mermaid, data-table, Vega-Lite, and static dsh-svg visualization bundle for DeepSeek Harness Web.

Live hardware load panel for the DeepSeek Harness web GUI: a btop-style tab showing CPU load per core and overall, DRAM usage, CPU temperatures, and per-GPU temperature/load/power/VRAM. Reads /proc and nvidia-smi on the host and polls ~1s in the browser.

Voice input plugin for DeepSeek Harness: a mic button in the chat composer with real-time spectrum animation, 16kHz WAV recording, ASR via pluggable providers (Xiaomi MiMo, Volcengine Doubao live streaming), optional LLM polish, all proxied through same-origin host routes.

Master: the pack's deliberately BLANK base bundle for the DeepSeek Harness web GUI - one no-op 'master' host row and the bundle layer, installed last so it is the pack's final word on any row. It ships no browser half, provides no service and declares no inject edge, so the right bar's tab-type chain stays exactly where it is. Alpha.

Master: the pack's deliberately BLANK base bundle for the DeepSeek Harness web GUI - one no-op 'master' host row and the bundle layer, installed last so it is the pack's final word on any row. It ships no browser half, provides no service and declares no inject edge, so the right bar's tab-type chain stays exactly where it is. Alpha.

Voice for DeepSeek Harness: an AI voice-reply tool, a persistent voice bar, a Voice settings page, and a boot sound module — all backed by Alibaba Cloud Bailian TTS.

语音转文字插件（DeepSeek Harness / dsh）：输入框右下角麦克风按钮，三种识别引擎（浏览器自带 / 讯飞 / 本地 Whisper）可切换。

DeepSeek Harness 语音输入输出插件（Web 端）：长按空格键语音输入（Web Speech Recognition）+ 助手文章输出朗读（speechSynthesis）。

Voice dictation for the DeepSeek Harness composer — mic button + Web Speech API

ChatGPT-style voice input for the DeepSeek Harness Web GUI: mic button, recording pill with live waveform, transcription via transcribe.cpp (Handy model catalog), whisper.cpp, or an OpenAI-compatible API

Voice practice mode for the DSH web app: bilingual (中文 / English) conversation output plus read-aloud (TTS) and speech input (STT). Adds a 语音交流 dialog-mode toggle to the composer.

Voice control for DSH web: speech-to-text into the composer (with auto-send) and spoken playback of assistant replies via the Web Speech API

DSH 全局热键语音弹幕：游戏里按 F9 说话，识别结果浮在游戏上方，F10 确认发送到 B 站直播间，全程不切出游戏

Manual browser speech-to-text input for DeepSeek Harness Web

Voice-to-text for DSH, powered by Whisper. One click to record, speak, and text appears in the input box. Local-first (privacy), Simplified-Chinese output, anti-hallucination, works in China without a VPN. · DSH 语音输入插件：点一下麦克风说话，文字自动进输入框。本地优先、强制简体、防幻觉、国内网络直连可用。

DeepSeek Harness 输入框语音输入插件（单包双面）：宿主端 sherpa-onnx sidecar 生命周期管理 + 浏览器端麦克风按钮/实时字幕/断句回填/3 秒静音自动关闭

系统级语音输入（DSH 插件）：挂载后自动在后台启动，按全局热键说话，本地 Whisper 转写并粘贴到当前光标处——在电脑任何程序里都能用，不只是 DSH。纯本地运行，语音不出本机。

Offline local speech-to-text for the DeepSeek Harness composer: a microphone button that records, transcribes with faster-whisper on your own machine, and inserts the text into the chat draft.

Composer voice input for DeepSeek Harness using the browser Web Speech API.

dsh Web 语音输入插件：在输入框发送按钮一侧加一个麦克风按钮，点击开始录音并实时转写进待发送框，再点停止

Voice input for DeepSeek Harness: hold Space in any editable field to speak, release to insert the transcript at the caret. Zero dependencies, browser Web Speech API. / 语音输入：在输入框长按空格键说话，松开自动上屏。零依赖，基于浏览器 Web Speech API。