Plugins

Weather card once per session: remembers your home city so a VPN never moves it, inline city picker, theme presets, custom separators, optional TTS hook for third-party voices.

A draggable task-tree panel inside the chat page: capture tasks by voice or text, drag to reorder, edge-snapping collapse, and a plain-text queue file you can edit or version yourself.

Natural, human-sounding voice for the dsh harness: server-proxied neural TTS read-aloud and agent speech tools over OpenAI-compatible endpoints, browser-native or Whisper speech input, and a Voice settings section

DSH 右侧栏的媒体台：把抖音/YouTube 链接丢进来，本机 yt-dlp 下载、ffmpeg 转 16k 单声道 WAV、官方 speechToText（SenseVoice）转写，字幕进面板，Agent 一键总结。

Command DeepSeek Harness from Telegram and Feishu (Lark): one live progress message per turn, approvals and questions as buttons, files and voice, delivery that survives outages and restarts, QR setup for Feishu, and per-person roles.

The DSH app also doubles as a desktop pet: wake it with your voice, talk out loud, and give orders by speaking. Reach the DeepSeek Harness running on your own computer over LAN, your own domain, or a relay server — and chat with the little whale working in your project to put it to work. Travelling without your laptop is no longer a problem.

Connects a local Synthesizer V Studio 2 Pro to the agent through its own Lua script API, with five tools for discovery, a persistent bridge, voice composition, note editing and DAW (VST3/ARA + MIDI) integration. Windows 10/11 only; requires Synthesizer V Studio 2 Pro 2.1.2+ with a project open.

The composer predicts what you are about to type. Inline ghost text sits on the caret, measured against the editor's own font and line box, and Tab turns it into real text (Esc ignores it). The prediction is one short call through the session's own model router, seeded with your draft and the last few turns of the conversation, so an empty composer also gets a next-prompt guess written in the user's voice; suggestions that merely restate the assistant are dropped. Host side is one HTTP route with sub-path endpoints (loopback-only, 64 KB body cap, 2-minute result cache, 20-second miss cache, one in-flight call per session); client side is one 0-height overlay registered on conversation.input.overlay, with insertion guarded by the composer's draftRev CAS and a setDraft fallback. IME composition and slash commands are skipped. 16 node:test cases, zero runtime dependencies, real screenshots in docs/.

Local GPT-SoVITS text-to-speech for DSH: reads replies aloud, switches voices from the right sidebar, and trains a new voice from a dropped audio sample. First run downloads an 11.4 GB engine and needs an NVIDIA CUDA GPU.

Persona plugin: a slowly moving 0-100 emotion meter, its own worldview, a per-turn diary, a relationship network, proactive messages, and an inner-voice line beside the cost row.

A novel reader docked in the DSH right sidebar for office slacking, with an AI companion that roasts whatever you just read alongside you - import your own TXT three ways, five reading themes, and saved chapters, progress and annotations. The companion comments as you go, in one of four voices (sharp-tongued, warm, detective or slacker) at a pace you pick, off by default. 434 Chinese classics as a 44 KB catalogue, searchable by title or author, one click to download and read offline, four CDN edges as fallback.

Connects a QQ Bot to DeepSeek Harness with per-peer sessions, group mention and keyword triggers, image generation and voice replies. Access defaults to OPEN for both direct and group chats, and an empty allowlist means everyone — set access.c2cMode / access.groupMode to allowlist (or disabled) before exposing the bot; IM input can run tools on the host.

Native, instant region-screenshot button for the DeepSeek Harness composer: one click freezes the screen, a WeChat-style overlay (gray mask, green selection) appears, and the cropped PNG is inserted into the current draft. An optional eye toggle hides the whole DSH window before capturing, then restores it. No ms-screenclip, about 10 ms per drag frame, coexists with voice input. Windows 10/11 x64 only; the first capture compiles a helper with the built-in .NET Framework csc.exe.

Adds a lightweight follow-up row under each DSH answer: one anchor question plus 1-3 user-voice quick replies, so the next turn is one click away; supports always / balanced / conservative strategies and optional refusal or emotional-context skips.

Adds two Volcengine Doubao cloud speech recognizers to the DeepSeek Harness voice-input picker, optionally rewriting the transcript with an LLM.

Tsundere mesugaki persona pack: dialect replaces whole sentence skeletons instead of sprinkling dialect words, stays on as the default voice even through work talk and delivery reports, and ships a temper system, banter mode and silent file handling.

Realtime WebRTC voice using Codex OAuth, with task delegation to a DSH session.

Live2D session view with realtime voice: continuous voice input, streaming TTS, subtitle translation, multi-model catalog, standalone entry / Live2D 实时语音会话视图：连续语音输入、流式 TTS、字幕翻译、多模型目录、独立入口

Speaks your agent's reports in a voice you choose, compressing long reports before speaking. Character voices need no training - a 3-10 second reference clip clones one, and community-trained models work too - and no 6.4 GB GPT-SoVITS install: the plugin installs its own runtime and voice. An existing GPT-SoVITS can be used instead, and it is the same voice model.

Adds a speaker button immediately right of the Like button on every finalized assistant reply; click it to hear the reply through the browser speech engine, and hover it for a speed and voice panel. Text is sent to an unofficial Edge TTS endpoint.

Local-first voice conversations for DSH, with local speech recognition and synthesis and optional external providers.

MiniMax 语音识别（asr-1.0）+ 语音合成（speech-2.8-hd）的 DeepSeek Harness 全局插件：转写工具、任务结束后用喇叭念一句的播报、实时免手对话、303 个音色可选

Reads AI replies aloud as they stream, with voiced waiting phrases while the model thinks. Edge TTS built in, any OpenAI-compatible cloud engine supported.

Offline voice input for the DSH Web UI: mic to local FunASR (SenseVoiceSmall), one-click install, no cloud.