Plugins

Fully local push-to-talk voice input for macOS: hold a global hotkey, speak, release — transcription is pasted at your cursor. Local-first STT (Qwen3-ASR 0.6B 4bit on MLX/Metal by default, SenseVoice and mlx-whisper fallbacks), zero external APIs, launchd self-healing service and an 8-point diagnose script. The bundled skill lets the agent install, configure (Karabiner hotkey wiring, launchd, engine switching) and troubleshoot the whole toolchain for you.

Character-chat memory layer that keeps persona, voice and relationship state separate from summaries, archives every raw message for retrieval, and ships a SillyTavern card importer plus an OpenAI-compatible gateway.

QQ Music karaoke + AI cover singing for DeepSeek Harness WeChat/QQ persona bots: search a song, split vocals with Demucs, convert the voice with RVC, mix and send a real voice bubble (WeChat SILK) or a QQ record.

Xiaomi MiMo TTS voice plugin for DeepSeek Harness: speak a line through the local speakers, with a system-prompt reminder so the model speaks every turn, plus API key / voice design / preview controls in settings.

Real-time speech-to-text inside the DeepSeek Harness composer: a live transcript while you speak, inserted at the caret when you stop, with a microphone picker. Local sherpa-onnx inference, so audio never leaves the machine.

Adds a voice to the agent: emotional speech synthesis (ChatTTS when available, falling back to edge-tts) and a singing mode, with mp3 output and local playback over ffplay. Requires Python 3.10+ with edge-tts installed (ChatTTS and its model cache are optional), ffmpeg/ffplay, and the pythonPath/ffmpegPath/ffplayPath values in cordis.patch.yml pointed at your own installs.

Connect DSH to a local BiliMemory backend for Bilibili search, collection, status and login tasks, A-Memorix shared memory health checks, plus QQ link status, QQ user allowlists and QQ watcher restart. The repository includes a Windows one-click installer that installs or repairs MaiBot A-Memorix when missing, then configures local-bge-small-zh, embedding and shared memory. It also provides install-memory.cmd for memory-only repair. Requires Windows, DSH Desktop 0.2.1-rc.2+, Node.js 22.19+, Python 3.12, Playwright/Edge, FFmpeg, a running BiliMemory API at 127.0.0.1:8765, a local embedding service at 127.0.0.1:11435, a Bilibili login, and MaiBot/NapCat for QQ. Voice, RVC and cover features are excluded.

DSH-elysia — shared Markdown memory for every DSH session: persona, requirements, corrections, lessons, methods, requests, sessions, a method library and ingested documents, mirrored to a second disk with version snapshots and a cross-process write lock; entries move between the main file and a searchable archive by hit frequency and repeated emphasis, and retrieval is keyword co-occurrence plus BM25. Ships a skills library (SKILL.md playbooks with optional guarded run.mjs execution), a sticker library that sends a fitting sticker at the right moment, and — new in 1.10 — Memory Packs: a bundled, opt-in character memory (packs/elysia: 61,903-char identity + 2,482-char persona distilled from 1,696 official voice lines and 112,175 dialogue lines). Packs are off by default, back up before writing, only touch identity/persona, and can be uninstalled to restore what was there.

Local English-to-Chinese simultaneous interpretation: on-device Qwen3-ASR bilingual captions with automatic language detection, crash-safe meeting records with minutes, and Obsidian export.

Transcribe local audio and video files offline with a composer panel, a CLI, and an agent skill, powered by SenseVoice int8.

Keyboard shortcut for the DSH voice input composer button: start recording, press again to stop and transcribe.

Local GPT-SoVITS voice for DeepSeek Harness: boots the engine with DSH and kills it on exit, speaks only the line marked for voice, and ships a default voice, so you only need to point runtimeDir at a local GPT-SoVITS install.

Dictation that ends up in the repository instead of the chat log: hold the button (or import a WAV), and the plugin archives voice-memos/<id>/ with audio.wav, a rendered waveform.png, memo.md (frontmatter, per-segment timestamps, ready-to-paste quote blocks) and meta.json. Audio is resampled to 16 kHz mono in the browser before it is sent. Transcription stays local — the harness speechToText service with silence-split windows, or a command worker such as faster-whisper — and when no engine is available the memo is still filed with an explicit status and reason rather than a fabricated transcript. Ships a conversation-view 口述 tab with click-to-seek playback and per-segment quote copy, three agent tools (voice_memo_save / voice_memo_list / voice_memo_read) and HTTP routes. Zero runtime dependencies, 52 node:test cases, real screenshots in docs/.

Calm monochrome UI with lavender accents, startup and switching motion, a thinking workspace, scoped skills, and optional local voice and pet connections.

Local wake-word voice input for DSH. Say the wake word, wait for the chime, then speak; text is sent to a DSH session. Audio is processed locally by default and not stored. Requires the DSH speech input service (speechToText) to be available.

Checks an invoice ledger for duplicates keyed on code + number, arithmetic consistency, payer mismatch, date anomalies and template placeholders, and emits an anomaly list plus a workbook.

Shows a character avatar and an editable ID beside every assistant reply, and reads the reply aloud with the system voice or a local TTS service you point it at; includes presets, a playback bar with pause and sentence skipping, tone and speed controls, and one-click launching of that service.

Mounts a per-channel speaking-rules file into the QQ preset's system prompt only, so that channel answers in one or two lines while every other channel stays untouched. Does nothing until home points at a folder with the rules file (default QQ线口径.md); meant for the QQ preset, not the global plugin list.

A greeting card that speaks — 156 prebuilt voice clips with a one-click mute — plus per-turn completion reports, long-run companionship notes and a takeover approval panel in the DSH conversation area.

Speaks a cue for DeepSeek Harness on Windows: a configurable phrase when an agent turn completes normally, a second phrase when the agent needs you to choose — a question, a plan approval, or a permission request — and a time-of-day greeting when a new conversation starts. A small bubble in the lower-left corner mutes and unmutes every cue with one click, with its own toggle chime. Phrases are synthesized with a Microsoft Edge neural voice (skipping aborted and errored turns, subagent turns, and rounds that a goal is still driving), cached under the DSH home directory and replayed locally, with the desktop SAPI voice as the offline fallback.

Move45clock: a health clock for DeepSeek Harness. A 45-minute work timer (5–120 minutes), 12 guided 12–15 minute seated/standing break plans, a visual plan editor, reminder cards scalable to 200%, night reminders at 21:30/22:00/22:30, and optional action-name voice coaching. Window wake is Windows-only.

Plays a voice alert and a browser notification when a turn finishes, asks for input, or fails, and can push the same summary to a Feishu bot webhook as a card.

Windows x64 translator with a dedicated sidebar entry and Workbench / Chat interface, side-by-side text and document translation, screen-region translation, recent history, and host model selection, voice input and preview. CUDA document OCR with CPU fallback; screen OCR uses CPU. Do not enable the CPU and CUDA packages at the same time.