DeepSeek Harness plugins — Page 396

Eyes 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 tool-calling turns.

Image routing for text-only models in DeepSeek Harness: a global analyze_image tool (Kimi vision) plus automatic rewriting of pasted images into attachment references when the active model cannot see images.

dsh plugin: vision capability proxy. Routes image understanding for text-only main models to a small multimodal model, and backs off entirely when the active model declares multimodal support (inputModalities includes 'image').

DeepSeek Harness 视觉能力全家桶：vision_understand 工具（OpenAI 兼容视觉 API，默认免费智谱 GLM-4V-Flash）+ 粘贴/拖拽/按钮三入口识图

Optional, provenance-preserving public image search for DSH Vibeify.

对话结束语音播报：会话名+轮数+结果（edge-tts 流式 / SAPI）

Voice assistant plugin for dsh web: hands-free wake phrase, dictation, voice edit commands, and Chinese TTS.

豆包式语音对话客户端插件：聊天框麦克风按钮（按住说话）→ 语音转文字发送 → 回复自动朗读。

Voice dictation and transcript cleanup for DeepSeek Harness, using the current session model.

Voice Input plugin for DeepSeek Harness with real-time recording, pause, playback review, and OpenAI-compatible proxy transcription

Voice input for the DSH Web composer: browser Web Speech with a Windows offline (System.Speech) fallback.

DSH 语音输入插件：在 dsh web 界面按住快捷键说话，语音识别后自动作为用户消息发送给 agent

Voice input plugin for DeepSeek Harness web (China-ready): Alibaba Cloud DashScope ASR via a local bridge. Mic button in the composer, streaming recognition, cursor-aware insertion, silence auto-stop.

Voice input (Web Speech API) and read-aloud (speechSynthesis) for the DeepSeek Harness web GUI — DSH 语音输入 + 回复朗读套件

Voice input plugin for DeepSeek Harness

Push-to-talk dictation for DeepSeek Harness: hold a single key in the composer, release, and the transcript is inserted into your draft.

Voice conversation mode for the DeepSeek Harness Web GUI: mic input with auto-submit, streaming spoken readout of replies, and a hands-free multi-turn loop with barge-in.

DSH Web 语音输入插件：零服务端、零密钥、零模型下载，直接使用浏览器内置 Web Speech API（Edge=微软 Azure 语音，Chrome=Google 语音）。

Voice (speech-to-text) input for the DSH Web composer via the browser Web Speech API — tap the mic, speak, the transcript fills the input box. Zero server, zero API keys, nothing leaves the machine. · DSH Web 语音输入：点麦克风说话，识别文字回填输入框（Chrome/Edge，无需 API key）。

Ship DeepSeek Harness to your own VPS: one command (or a form in DSH Settings → VPS Deploy) installs a zero-dependency login gateway, automatic HTTPS through Caddy, systemd supervision and one-click DSH upgrades.

Ship DeepSeek Harness to your own VPS: one command (or a form in DSH Settings → VPS Deploy) installs a zero-dependency login gateway, automatic HTTPS through Caddy, systemd supervision and one-click DSH upgrades.

VPS Hub for DeepSeek Harness: manage your cloud-server SSH ledger, import hosts from ~/.ssh/config, and let agents discover, test, execute commands on, and transfer files to your servers. Private keys stay local as path references only. Optional Settings-page UI via the dynamic-plugin example.

Manage your VPS from DeepSeek Harness over SSH: zero-token commands, AI tools with risk-tiered confirmation, and a recipe library. · 在 DSH 里通过 SSH 管理 VPS：不花 token 的命令、按风险分级确认的 AI 工具、菜谱库。

%dsh.ext.description%