Plugins

Synthesises speech through Alibaba Bailian's WebSocket TTS and returns a WAV file plus a preview URL, with an optional per-turn hint that nudges the model towards voice. Needs a Bailian API key and ffmpeg, and the text is sent to Alibaba Cloud; the plugin does not send messages itself — delivery is left to the session's own transport.

Local video understanding for agents: extracts keyframes adaptively based on motion and pauses, inspects any timestamp at full resolution, and aligns visuals with dialogue from embedded subtitles or configured ASR. Requires ffmpeg and ffprobe; clips without subtitles also need a transcription engine for dialogue (a ~190 MB local whisper model, a cloud API key, or the official voice-input model).

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 112,175 dialogue lines — not written by hand, measured) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also opt-in voice playback through a local GPT-SoVITS engine, a skills library, and a sticker library that sends a fitting sticker at the right moment.

QQ (OneBot 11 / NapCat) channel for DeepSeek Harness: bridges QQ private chats and group chats into their own dsh sessions. Ships group guardrails (mention-only, quiet hours, cooldowns, daily quota, peak-hour mute), a tool gate with write-action audit, an outbound filter that stops the model from echoing input tags, voice transcription, media and forwarded-card support, dryRun and usage stats. Forked from dsh-onebot-qq 0.9.4. Cannot be installed alongside the upstream dsh-onebot-qq (two QQ channels on one NapCat crash-loop DSH). Private chats answer admins only (an empty admin list means nobody); group chats default to all groups and answer any @-mention, so set groupPolicy to allowlist to restrict who can drive the agent.

A desktop pet for DSH: a blue whale girl with 104 animations and built-in voice. It is standalone, but its pet runtime is a rework of dsh-dafeiyu — disable the upstream dsh-dafeiyu before installing, or both will run and fight over the control port. Windows x64 only, and the first launch downloads about 580 MB of assets.

Provider-agnostic text-to-speech for DeepSeek Harness: synthesize speech to local audio files, manage preset, cloned and designed voices, configure providers in a bilingual settings card, and read assistant replies aloud with optional auto-read.

Hold Alt (default; rebindable in the plugin page) to dictate and insert a cleaned-up transcript, plus a sparkle button that rewrites the composer draft into a clearer prompt. Dictation requires the Harness Voice Input plugin with its SenseVoice model enabled.

Adds lasting bots with their own name, photo, persona, memory, voice and model, a Bots panel in the sidebar, and a hidden helper subagent per bot that follows the conversation, searches ahead and leaves notes the bot reads; voice uses your own ElevenLabs, OpenAI, Groq, Mistral or Deepgram key. Interface and prompts in Brazilian Portuguese.

Dabaifan Arrival Voice Announcements speaks the estimated spend per turn with the bundled Dabaifan voice by default; Alipay is optional. Amounts come from dsh-cost-meter or model-price estimates, not payment records. No runtime TTS service. Code is MIT; the bundled Alipay clips come from Reathin/XVoice (no licence), the Dabaifan voice is a MiMo clone and the icon is a fan-made meme, all for personal, non-commercial use with this plugin only.

Whisper Local for DeepSeek Harness

BreezeBlue text-to-speech for DSH: three agent tools, a header toggle that reads assistant replies aloud (markdown and code blocks stripped), and local HTTP endpoints for audio playback, synthesis and long-poll delivery. Requires a BreezeBlue API key (BREEZE_API_KEY); synthesis is billed per character.

Connects DeepSeek Harness to Postel over MCP: search a library of X posts that went viral by topic, write posts and X threads in the user's saved voice, and save, schedule or publish them to X, LinkedIn, Bluesky and Mastodon; adds a postel-writing skill. Research works without an API key.

A self-hosted digital-life companion for DSH. Three slow-moving hormones (dopamine, cortisol, serotonin) set its mood and tone, a memory layer turns chats into events and facts with version chains and a forgetting curve, and it writes, hot-loads and unloads its own organs (tools) when a capability is missing. It handles text, images, stickers, voice notes with text to speech and speech recognition, and file uploads; the web space holds diary posts and guestbook comments, and it starts conversations on its own schedule. The built-in web server listens on 0.0.0.0:2332 by default, so create the owner account before exposing the port.

One-command install for dsh-einvoice, dsh-bankrec, dsh-ap-three-way and dsh-travel-recon.

A desktop companion for DSH: she lives on your real desktop, in the wallpaper or in dsh's own page, talks by voice, speaks first and remembers you. Several characters, each with her own look and scene rules.

A model-driven desktop pet, derived from PC2005-cloud/dsh-pet (MIT): an always-on-top companion that follows your agent sessions, races the Web UI to answer approvals and questions, keeps a per-pet affection ledger, speaks through pet_say/pet_do tools or an autonomous inner voice, and can read those lines aloud through BreezeBlue TTS with your own BreezeBlue API key. It uses its own /whale598 route and ~/.dsh/whale598 data directory, so it is a separate pet from dsh-pet rather than a replacement for it.

Travel expense reconciliation: ingest orders, invoices and card lines, deduplicate, run the three-way match and a read-only policy check, then export — 5 `travel.*` tools.

Chinese e-invoice (OFD/XML) inbox: ingest, parse, deduplicate, queue for review, record receipts and archive locally — 10 `invoice.*` tools, nothing uploaded.

Accounts-payable three-way match: import invoices, purchase orders and goods receipts, apply the tolerance policy and export the exception workpaper — 4 `ap.*` tools.

Read-aloud and dictation for the DSH web UI with 23 TTS and STT provider types configured side by side, per-language routing, in-text language markers, per-sentence language detection, word highlighting and a TTS Reader sidebar tab (the tab requires dsh-better-sidebar; everything else works without it).

Floating TTS speaker in each conversation corner: when an AI reply finishes, edge-tts reads the summary aloud in the background with no popup windows; the toggle is remembered per conversation. Requires Windows, Python 3.9+ with the edge-tts package installed, and network access to Microsoft's Edge TTS service; summary is the default mode.

A Phone tab in dsh-better-sidebar: SMS and calls over Twilio and SIP lines bridged through Asterisk, call audio through your server, Live, Voicemail and Do not disturb modes with live voicemail transcripts, a Telegram account with chats, voice messages and calls, and phone_* and telegram_* agent tools. Requires dsh-better-sidebar, Node 22.5+, a Twilio account with a voice and SMS number, a public HTTPS host for provider webhooks, and the bundled Go daemons built from a checkout (Telegram also needs your own api_id/api_hash).

Fairy III (Zenless Zone Zero) H.D.D skin for DeepSeek Harness: boot video, an eye-core dock that can be dragged vertically so it never covers text, and time-of-day greeting voices written by a model every day (5 lines, each <= 20 characters) and synthesized locally with GPT-SoVITS, with a fallback chain of today -> latest -> bundled audio so there is always something to hear. Replies can be spoken: a trailing marker line takes priority over length heuristics, and long replies can be compressed into one sentence first. The reader hashes the utterance it just played (MD5) so each reply is voiced exactly once, and switching sessions stays silent. Personal fork of dsh-fairy-zzz with its own package, route and storage namespace, plus a rate-limited summarize endpoint, POST-only engine control and bounded TTS and greeting caches. Two diagnostic logs (client revision, decision trace) are written next to the plugin and stay on the local machine. A personal fork of AssassinVIX/fairy-zzz-plugin (upstream package dsh-fairy-zzz): install this fork or the upstream, not both - both mount the full-screen skin on the same DSH surfaces. Dynamic greetings and spoken summaries need a DeepSeek-compatible API key in ~/.dsh/fairy-tts.json (or DEEPSEEK_API_KEY); without it only the bundled greeting audio plays.

Windows-only DSH plugin that stops SnowLuma and local voice services during Beijing weekday peak hours and starts them again off-peak.