Plugins

Continuous dictation for the composer using a local SenseVoice ONNX model on CPU: recognised text appears while you speak, a pause ends the sentence and writes it into the input box, and audio never leaves the machine.

Add-on layer over the official QQ bot plugin @tencent-connect/dsh-qqbot: gates group messages before they reach the agent (probability, debounce with backlog, invalid-message filtering, admin approval before reading attachments), greets idle private chats, and adds emoji stickers via dsh-meme, TTS/ASR voice replies, image generation and one settings page. Needs the official QQ bot plugin installed (plus dsh-meme for stickers). Group gating defaults to a 25% chance and only applies when mentions are not required; the private-chat greeting is on by default (22:00-08:00, at most 3 a night, only to chats that wrote first); voice and image generation call endpoints you configure; with no admins configured nobody can approve attachments.

Paste a Douyin video link (easy to copy from the Douyin PC app) and the plugin downloads the video, transcribes the speech offline into timed Chinese text, and imports it into Obsidian as a Markdown note. Built for DeepSeek Harness and for beginners building a personal knowledge base. Needs Python 3.10+ with playwright (it drives Edge), PyAV, sherpa-onnx and numpy installed, plus a SenseVoice model placed under %USERPROFILE%\.dsh\douyin-kb\models.

Derivative of cheesehaqi/dsh-qq-onebot-bridge with the same package name, so the two cannot be installed together. Bridges a personal QQ account into DeepSeek Harness over OneBot 11: private and group messages become per-conversation agent sessions and replies are sent back to QQ. Ships a reverse WebSocket server, allowlists (empty = deny all), @ parsing, image and SILK voice handling, and a separate local console on 127.0.0.1:8880 with the decision trace, offline replay, event injection, a read-only preflight and host/Waylay start-stop controls. Needs a separate OneBot v11 implementation (a third-party unofficial QQ client): the default, Waylay, injects into the official Windows QQ.exe (Windows 10/11 x64 only) and is distributed as a separate release archive, not bundled in this repo. botQqAllowed and replayGuardEnabled are edited in DSH Settings > QQ助手, and the replay guard is armed automatically when the logged-in account changes.

Keyword-rule scan of a project directory for tax-industry compliance gaps ahead of regulatory audits: accounting voucher and ledger retention set under 30 years, invoice-title lines with no taxpayer ID, tax data leaving China with no security assessment or standard contract mentioned, and e-invoice lines with no verification or de-duplication mentioned, with rule sources kept in rules/.

Text-to-speech for DeepSeek Harness through Xiaomi MiMo TTS, needs a XIAOMI_API_KEY: a mimo_tts tool that writes audio to a local file, a read-aloud action on each finalized answer, auto-read, and a sidebar panel for built-in voices, voice design by description, or voice cloning from an mp3/wav sample. Same package name as lengmodkx/dsh-mimo-tts, so the two cannot be installed together.

Runs loudness normalization, silence trimming, format conversion and batch processing through local ffmpeg, with presets for game sound effects, music uploads and voice cleanup.

Offline CET-4 study panel: a built-in original starter set (426 words and one mock paper, listening read by the system voice) plus locally built practice from the user's own materials; answers are shown without explanations.

Bilibili companion for DSH, derived from c1overzz/dsh-bili-scroll (do not install both: they share the plugin entry id bili-scroll). Understand any video with AI summaries, chapters and subtitles; make your own with edge-tts voice-over, captions and ffmpeg; publish, post dynamics, reply to fans and read creator stats (publishing and dynamics stay off until Creator mode is enabled); plus an optional daily curated feed report. First run needs a one-time in-app install of Python dependencies (a uv venv plus PyPI packages such as bili-agent and edge-tts) and a Bilibili QR login.

macOS (Apple silicon) fork of aureth-labs/dsh-aurabot-qq: the same QQ persona bot (chat, voice notes, stickers, memory, song covers, modules) with the Windows-only code removed. It connects to a OneBot v11 gateway such as SnowLuma running in OrbStack or Docker, falls back to the macOS `say` voice, sends files over 30 MB to a containerised gateway through a loopback-only temporary download link, and installs the song-cover environment (Applio, audio-separator, uv, Rubber Band, separation models) at pinned versions. It keeps the upstream package name and plugin id (dsh-aurabot-qq), so it replaces upstream and cannot be installed alongside it; use upstream on Windows.

Removes AI phrasing so replies and documents sound human: an always-on de-slop style section injected into every session (on by default, switch it off with deslop_mode), four deslop_* tools (0-100 slop scan, deterministic rewrite, intensity switch, voice profile) and four skills (rewriting, conversation, technical docs, Chinese reports), copied into the DSH skills folder at startup. The effect is measurable: a typical AI-flavoured Chinese paragraph scores 49 before deslop_rewrite and 6 after.

Give your agent a phone: a local incoming-call screen that really rings in the browser, speaks a preset opening line with the OS voice (no API key, fully offline), and can call again if nobody picks up. The first sentence is fixed text rather than model-improvised, because schedules, amounts and addresses are the kind of thing you cannot let a model paraphrase. Windows only.

Super input suite — model and effort picker, prompt enhancer, follow-up suggestion chips, a full cost engine with daily heatmap and Coding Plan quotas, voice-input light effects and transcript cleanup (needs the built-in voice-input bundle enabled), prompt templates, selection reference chips with comments, a compaction ring and a settings hub. Bundles the author's standalone dsh-cost, dsh-power-picker, dsh-prompt-enhancer, dsh-followup, dsh-siri-voice and dsh-compaction-control; uninstall those before installing.

Voice dictation scratchpad: realtime speech-to-text into timestamped, per-session blocks, with one-click insert into the conversation composer. Requires the official DSH voice-input bundle (@deepseek-ai/dsh-experimental-voice-input-bundle); the speech model downloads on first use.

Full-screen HAAVK-themed boot animation for DSH, rewritten from dsh-startup-secret 1.5.2 (which is listed separately): an intro video, a cold-blue console board and a five-step access sequence with recorded voice lines and a looping background track. Text and two accent colours are editable in DSH settings, and the intro video and BGM can be switched there; replacement media files go into lib/assets. Install it instead of dsh-startup-secret, not alongside it — the two share ~/.dsh/dsh-startup.json and the same settings section.

语音输入与对话朗读：点一下或按快捷键切换语音模式，边说边出字，离线本地识别（SenseVoice + Silero VAD），支持自定义词表、热词提示与多模型档位；回复可用 Edge 在线 / 本地神经模型 / 系统语音三种引擎朗读。

Windows-wide Bluetooth earbud shortcuts for AI work: a left-earbud volume-down gesture starts or stops Windows voice typing (Win+H), and a right-earbud volume-up gesture sends Backspace. The DSH settings page offers manual key mapping, test actions, Backspace count, volume-gesture detection, and a 1.6-second cooldown so one triple-tap performs one action. The helper is compiled locally from included C# source. The plugin itself does not record or upload audio; Windows voice typing processes speech under its own privacy settings.

Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and checked against a 112,175-line game-dialogue corpus) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also a skills library and a sticker library (you import your own images; none are bundled) that sends a fitting sticker at the right moment. On by default: a text bubble with her avatar after each reply, which costs one extra small model request unless the agent already announced (voice.bubble: false turns it off). Opt-in voice playback needs a local GPT-SoVITS engine (about 27 GB, installed separately, NVIDIA GPU required; the plugin downloads about 200 MB of weights) and is Windows-only; the automatic second-drive mirror is Windows-only too (elsewhere set mirrorPath, otherwise there is no mirror).

Yugan Huafang (语感花房) is a personal voice workshop for DeepSeek Harness: your own writing and corrections become explainable local style rules, optionally distilled by the current model, then compiled into a preset you pick per session; edits apply on the next message in that session.

DeepSeek Harness plugin: an agent-facing say tool that makes the agent speak one sentence out loud (local offline Xiaoxiao, Edge TTS, or Windows built-in), plus a desktop bubble and event-driven auto announcements.

Sayaka Miki desktop pet for the DeepSeek Harness Web UI: twelve hand-drawn sprites follow the live session state and swap instantly, with a tired slump after a turn, a furious second stage after ten pokes, and idle sword-polishing; repeated states change her line and a voice line plays every five to eight encounters.

A Feishu/Lark channel for DeepSeek Harness: WebSocket inbound messaging that steers a running turn instead of queueing behind it, Markdown tables rendered as native Feishu table components, code blocks kept on their own lines, 13 Feishu tools, voice input and output, media upload, a model fallback chain, and a web settings page split into six grouped tabs. Runs on a self-built Feishu app over the long connection, so no public endpoint is needed.

An on-demand Chinese editing skill that reduces formulaic phrasing while preserving facts, uncertainty, genre, and author voice.

Hold Space to record and release to transcribe and send, without focusing the composer first. Esc cancels and window blur auto-cancels. Requires the official voice-input bundle (`@deepseek-ai/dsh-experimental-voice-input-bundle`) enabled with its speech model downloaded; otherwise Space is left alone.