Plugins

Voice tools: free edge-tts neural speech synthesis, OpenAI-compatible ASR transcription, voice list, batch voice preview and health self-check.

Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language switching, and optional auto-send, zero dependencies.

MiniMax-powered multimodal plugin: real-time voice call mode (streaming conversation, floating dock UI), voice mode and mic voice input, plus image/video/music/speech generation and vision inspection tools.

Type /telleru in any conversation and an AI tutor teaches it on a whiteboard in the right sidebar: it clarifies your goal, checks your level with quick questions, has you confirm an outline, then writes structured board content (tables, flowcharts, formulas, code) step by step with optional voice, subtitles, quizzes and interruptible Q&A.

Started from AssassinVIX/fairy-zzz-plugin. The eye badge artwork and motion geometry come from Chengzhibense/Fairy-DSH. This plugin builds on that base with further changes and development, and delivers major performance optimizations. It repaints the DSH Web UI, adds an always-on fee dock, and supports one-click self-update after npm installation. It retains the H.D.D boot animation and voiced greeting, the dockable eye badge and usage bubble, optional local GPT-SoVITS narration, and titles using the bundled Anton font, among other features.

Breeze TTS for DeepSeek Harness: read replies aloud in full or as a short summary, one-click Breeze CLI login with automatic key import, voice search and design, smart companionship, and lunch/dinner reminders.

Breeze TTS client for DeepSeek Harness: connects to your own Breeze TTS server to read replies aloud and manage voice cloning (the server and its model must be deployed separately; hardware requirements are on the server side), with an optional cross-machine mode. Merges @dsh-external/dsh-plugin-local-ai-tts (abbccdd/dsh-localtts) and dsh-breeze-voices, carries code from 1624318455/dsh-plugin-tts, and must not be installed alongside the two upstream plugins it merges.

Hold-to-talk dictation in the composer that ships no recognizer of its own and reuses the speech service the official voice-input bundle already mounts - long-press the input box with mouse or touch, release to write the transcript into the draft, slide up to cancel, and it never sends.

Voice assistant for dsh web: say the wake phrase (e.g. "小鲸") to activate hands-free dictation — what you say is transcribed and typed into the chat box automatically. Supports spoken edit commands (send, clear, new line, stop reading) and reads assistant replies aloud in Chinese. Speech recognition runs locally in-browser via sherpa-onnx WASM, so it works offline without an API key.

AI audio generation for the DeepSeek Harness web GUI — multi-vendor TTS, music, sound effects and voice design with a sidebar panel, model comparison, resource library and Agent tools.

Agent-initiated voice calls: `offer_call` rings the human (接听/拒接/稍后再说); accepted calls synthesize and play locally via CrispASR + Qwen3-TTS (9 speakers, 2 Chinese dialects), rejected calls return the decision to the agent.

Free voice closed loop for the Web UI: browser SpeechRecognition mic input with live interim results plus read-aloud speaker buttons and auto-read for assistant replies, zero configuration and no API key.

Per-workspace completion ringtones plus attention sounds for approval, question, plan-review, goal-blocked, and task-failure events, with built-in synth, voice (TTS), and custom audio.

Windows QQ character integration kit for DSH with NapCatQQ/SnowLuma, Bilibili, local GPT-SoVITS voice, revisable memory and a dashboard; development preview requiring companion-service setup.

Adds a fish-ear microphone to DSH that transcribes speech locally, estimates tone and emotion, and lets BigFish reply with an emotion-aware prompt.

Windows desktop notifications for DSH that speak the turn result by default: Windows TTS needs no download, and 13 VOICEVOX voice packs can be installed from the settings page. A completed alert waits until running subagents and background jobs finish; approval, question and error alerts fire immediately. Voice packs are downloaded from GitHub after a terms confirmation.

Plays local video and audio inside the conversation. Media files the model writes during a turn - screen recordings, transcodes, voiceovers - get a player under its final reply automatically when their paths appear in its commands, the command output or the reply; the play_video tool plays any other file. Video shows as compact cards with a hover preview, audio as a slim seek bar, streamed over HTTP Range so long files seek instead of loading into memory. Also registers a sidebar media preview renderer, since the built-in previewer treats mp4 as unviewable. The look_video tool lets the model see a video itself: a hidden local Chrome or Edge grabs frames into a time-labelled contact sheet (or big frames at given times, or a short range frame by frame), checks the audio (silence, too quiet, clipping, one channel only) and the picture (black or frozen frames), and reads MP4 / MOV headers for phone compatibility (codec, HDR, faststart and more), with ffmpeg fixes.

DeepSeek Harness × Feishu/Lark bridge: chat, cards, approvals, task board, goals and schedules in Feishu — plus fully local (offline) voice transcription with a play bar in the Web GUI.

Two-way Telegram remote cockpit for DeepSeek Harness: live progress tracking, screenshot vision, git diffs, shell execution, and tool approvals. Unconfigured chatId automatically claims the first sender as owner; voice-to-text requires local ffmpeg and BeeRouter services.

Replaces the reasoning-effort dropdown with a draggable snapping slider, and draws 13 canvas effects across five style families (thrust, fluid, fantasy, tech, texture) with three tiers that unlock as the effort level rises. Custom mode combines 10 particle forms with 8 flow trajectories; 9 accent presets and a hex picker recolor every effect, and optional key sounds cover two voice clips, a synthesized duck squeak, a mechanical click and a local audio file.

One-handed, keyboard-free input for the composer: press and hold the mouse on the input box, speak, release — the text lands in the draft, and sliding up cancels without leaving a half sentence behind. No mic button to aim at and no shortcut to remember; the hand never has to leave the input area, which is the point when the other hand is busy. Recognition runs fully offline (SenseVoice via sherpa-onnx, no API key, audio never leaves the machine).

Voice call assistant for the DSH desktop app and the Web GUI (the same plugin, only the profile name differs): a draggable floating call ball, browser-side VAD that sends each utterance after a pause, speech recognition through the local SenseVoice model already downloaded by the official voice-input plugin (no second model), FunASR HTTP or streaming, or a cloud-compatible API, MiniMax / MiMo-V2.5-TTS (director mode and voice clone) / OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate sessions with progress, stop, and spoken completion reports.

Plays a chime and speaks a Chinese voice alert when an approval, question, or plan-review popup appears in the DSH web GUI, so you never miss a request.

Free lip-sync video generation plugin for DSH with 3000+ voices and 500+ languages.