{"install":"Install","market":"via dsh-market · recommended","marketHint":"copy the market install command","cli":"via CLI","copy":"copy install","copyLabel":"Copy install command","dlTitle":"Downloads (30d)","items":[{"cat":"voice","tag":"Voice & Audio","dl":8348,"stars":8,"added":"2026-08-26","npm":1,"name":"dsh-voice","owner":"GooDAnDReaDY","short":"dsh-voice","slug":"GooDAnDReaDY/dsh-voice","desc":"Voice input for the web UI: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, or an OpenAI-compatible endpoint).","cmd":"dsh plugin --profile web add @goodandready/dsh-voice","href":"/p/GooDAnDReaDY/dsh-voice/"},{"cat":"voice","tag":"Voice & Audio","dl":4824,"stars":2,"added":"2026-08-28","npm":1,"name":"dsh-tts","owner":"GooDAnDReaDY","short":"dsh-tts","slug":"GooDAnDReaDY/dsh-tts","desc":"Speaks agent replies in the DeepSeek Harness web UI through a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak), so a failing or rate-limited provider falls through to the next instead of going silent.","cmd":"dsh plugin --profile web add @goodandready/dsh-tts","href":"/p/GooDAnDReaDY/dsh-tts/"},{"cat":"voice","tag":"Voice & Audio","dl":4600,"stars":15,"added":"2026-08-24","npm":1,"name":"dsh-voice-mode#dsh-voice-mode","owner":"qishuilalala","short":"dsh-voice-mode#dsh-voice-mode","slug":"qishuilalala/dsh-voice-mode--plugin-dsh-voice-mode","desc":"Full-duplex voice mode for the DeepSeek Harness Web UI: toggle (2s-pause auto-send) or hold-to-talk dictation into an editable draft with zipformer2 streaming ASR, optional wake word; sentence-by-sentence Edge TTS read-aloud with live captions, and speaking interrupts playback and the running turn (true barge-in). On-device ASR, no API key.","cmd":"dsh plugin --profile web add dsh-voice-mode","href":"/p/qishuilalala/dsh-voice-mode--plugin-dsh-voice-mode/"},{"cat":"voice","tag":"Voice & Audio","dl":3649,"stars":15,"added":"2026-09-03","npm":1,"name":"dsh-talk","owner":"PerryLink","short":"dsh-talk","slug":"PerryLink/dsh-talk","desc":"Voice I/O for DeepSeek Harness — speech-to-text and text-to-speech over the microphone and audio output.","cmd":"dsh plugin --profile web add dsh-talk","href":"/p/PerryLink/dsh-talk/"},{"cat":"voice","tag":"Voice & Audio","dl":3023,"stars":34,"added":"2026-08-27","npm":1,"name":"dsh-voice-scribe","owner":"PensiveFei","short":"dsh-voice-scribe","slug":"PensiveFei/dsh-voice-scribe","desc":"Voice input for the web UI: tap Alt (or Alt+Space) to start/stop dictation, browser Web Speech (zero-config) or OpenAI-compatible cloud ASR, optional polish through DSH-configured LLM, settings UI.","cmd":"dsh plugin --profile web add dsh-voice-scribe","href":"/p/PensiveFei/dsh-voice-scribe/"},{"cat":"voice","tag":"Voice & Audio","dl":2925,"stars":21,"added":"2026-08-19","npm":1,"name":"dsh-ears","owner":"WizisCool","short":"dsh-ears","slug":"WizisCool/dsh-ears","desc":"Voice input plugin for DeepSeek Harness (dsh): a microphone button in the composer turns speech into a draft transcript, with a choice of speech-recognition backends, optional polish through dsh own LLM routes, and a native settings page.","cmd":"dsh plugin --profile web add dsh-ears","href":"/p/WizisCool/dsh-ears/"},{"cat":"voice","tag":"Voice & Audio","dl":2862,"stars":11,"added":"2026-08-23","npm":1,"name":"dsh-plugin-xiaomi-mimo-tts","owner":"ppy-web","short":"dsh-plugin-xiaomi-mimo-tts","slug":"ppy-web/dsh-plugin-xiaomi-mimo-tts","desc":"Adds Xiaomi MiMo text-to-speech to DSH Web with assistant-message read-aloud, PCM streaming, preset and custom voice design, browser speech fallback, playback controls, and optional UI sounds.","cmd":"dsh plugin --profile web add dsh-xiaomi-tts","href":"/p/ppy-web/dsh-plugin-xiaomi-mimo-tts/"},{"cat":"voice","tag":"Voice & Audio","dl":2497,"stars":3,"added":"2026-08-29","npm":1,"name":"dsh-audiogen","owner":"shimingming520","short":"dsh-audiogen","slug":"shimingming520/dsh-audiogen","desc":"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.","cmd":"dsh plugin --profile web add dsh-audiogen","href":"/p/shimingming520/dsh-audiogen/"},{"cat":"voice","tag":"Voice & Audio","dl":2310,"stars":4,"added":"2026-08-15","npm":1,"name":"dsh-voice","owner":"STARDUSTLC666","short":"dsh-voice","slug":"STARDUSTLC666/dsh-voice","desc":"Voice tools: free edge-tts neural speech synthesis, OpenAI-compatible ASR transcription, voice list, batch voice preview and health self-check.","cmd":"dsh plugin --profile web add dsh-voice","href":"/p/STARDUSTLC666/dsh-voice/"},{"cat":"voice","tag":"Voice & Audio","dl":1918,"stars":2,"added":"2026-08-16","npm":1,"name":"dsh-voice-call","owner":"PandaPolo","short":"dsh-voice-call","slug":"PandaPolo/dsh-voice-call","desc":"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.","cmd":"dsh plugin --profile web add dsh-voice-call","href":"/p/PandaPolo/dsh-voice-call/"},{"cat":"voice","tag":"Voice & Audio","dl":1772,"stars":11,"added":"2026-08-16","npm":1,"name":"dsh-speak","owner":"Alan2Z","short":"dsh-speak","slug":"Alan2Z/dsh-speak","desc":"Zero-dependency, event-driven voice announcement plugin: no extra model, no token cost. Speaks with the system's built-in natural voice, supporting both Windows and macOS; final-reply announcements, approval & question alerts, optional event announcements (turn end, command done, goal change, tool errors, todo updates), replayable final replies, and a bilingual visual settings page.","cmd":"dsh plugin --profile web add dsh-speak","href":"/p/Alan2Z/dsh-speak/"},{"cat":"voice","tag":"Voice & Audio","dl":1733,"stars":6,"added":"2026-09-20","npm":1,"name":"dsh-duet","owner":"YuMS","short":"dsh-duet","slug":"YuMS/dsh-duet","desc":"Full-duplex Chinese voice interaction for DSH Web: dictate and edit tasks, submit requests, manage sessions, answer DSH questions, and hear concise task-completion announcements.","cmd":"dsh plugin --profile web add dsh-duet","href":"/p/YuMS/dsh-duet/"},{"cat":"voice","tag":"Voice & Audio","dl":1497,"stars":1,"added":"2026-09-11","npm":1,"name":"dsh-voice-talk","owner":"duoduoqian708","short":"dsh-voice-talk","slug":"duoduoqian708/dsh-voice-talk","desc":"Voice conversation mode for the DSH Web GUI: tap the mic to start a full-screen call, talk hands-free, and hear each reply read aloud as it streams. Bilingual (Chinese/English) UI, light and dark themes, adjustable speech rate, and switchable voices.","cmd":"dsh plugin --profile web add dsh-voice-talk","href":"/p/duoduoqian708/dsh-voice-talk/"},{"cat":"voice","tag":"Voice & Audio","dl":1486,"stars":3,"added":"2026-09-01","npm":1,"name":"dsh-voco","owner":"lgquan","short":"dsh-voco","slug":"lgquan/dsh-voco","desc":"Continuous voice conversations for DSH with hands-free listening, push-to-talk, speech recognition, TTS replies, and background Agent delegation.","cmd":"dsh plugin --profile web add @flowingspring/dsh-voco","href":"/p/lgquan/dsh-voco/"},{"cat":"voice","tag":"Voice & Audio","dl":1435,"stars":1,"added":"2026-08-15","npm":1,"name":"dsh-dingo","owner":"february2015","short":"dsh-dingo","slug":"february2015/dsh-dingo","desc":"Sound reminders with one-click jump for concurrent sessions: the current session gets crisp dang/dang-dang tones, other sessions a soft ding/ding-ding plus a top-right card that jumps straight to the replying conversation.","cmd":"dsh plugin --profile web add dsh-dingo","href":"/p/february2015/dsh-dingo/"},{"cat":"voice","tag":"Voice & Audio","dl":1271,"stars":0,"added":"2026-09-24","npm":1,"name":"sh-volume-knob","owner":"jianghu-lao-yao","short":"sh-volume-knob","slug":"jianghu-lao-yao/sh-volume-knob","desc":"Speaker button beside the composer microphone — one click scrolls to the start of your newest question, marks it with a blinking caret and reads from there through the newest agent reply (dsh-tts, browser voice as fallback); press-and-drag-right picks any other reading start position on the page, press-and-drag-up opens a vertical mixer for in-page media volume and system output volume.","cmd":"dsh plugin --profile web add sh-volume-knob","href":"/p/jianghu-lao-yao/sh-volume-knob/"},{"cat":"voice","tag":"Voice & Audio","dl":1064,"stars":0,"added":"2026-08-29","npm":1,"name":"dsh-voice-announcer","owner":"flashyiyi","short":"dsh-voice-announcer","slug":"flashyiyi/dsh-voice-announcer","desc":"Voice announcements when a conversation ends (session title, round, outcome) plus live sentence-by-sentence reading of replies, via built-in edge-tts with zero third-party dependencies.","cmd":"dsh plugin --profile web add dsh-voice-announcer","href":"/p/flashyiyi/dsh-voice-announcer/"},{"cat":"voice","tag":"Voice & Audio","dl":1029,"stars":21,"added":"2026-08-15","npm":1,"name":"dsh-plugin-tts","owner":"1624318455","short":"dsh-plugin-tts","slug":"1624318455/dsh-plugin-tts","desc":"Reads assistant replies aloud via free Edge TTS or your own RVC voice models: read-aloud buttons + auto-read, adaptive chunked progressive playback (gapless long reads), one-click voice-pack installs from a registry, and a portable RVC runtime.","cmd":"dsh plugin --profile web add @memef1f1y/dsh-plugin-tts","href":"/p/1624318455/dsh-plugin-tts/"},{"cat":"voice","tag":"Voice & Audio","dl":985,"stars":3,"added":"2026-08-28","npm":1,"name":"dsh-gsv","owner":"TaoruiLiu19","short":"dsh-gsv","slug":"TaoruiLiu19/dsh-gsv","desc":"Real-time local TTS for DeepSeek Harness: voice presets, auto-read, engine setup assistant, a read-aloud button, and a settings panel for the GSV-TTS-Lite engine.","cmd":"dsh plugin --profile web add dsh-gsv-tts","href":"/p/TaoruiLiu19/dsh-gsv/"},{"cat":"voice","tag":"Voice & Audio","dl":879,"stars":2,"added":"2026-08-26","npm":1,"name":"dsh-voice-chat","owner":"maoyuching","short":"dsh-voice-chat","slug":"maoyuching/dsh-voice-chat","desc":"Doubao-style voice chat for DSH: press-and-hold mic in the composer converts speech to text and auto-sends, and AI replies are read aloud. Optional LLM condensing (long replies summarized into short spoken lines, following the current conversation model), TTS-friendly text cleaning, selectable Edge TTS voices, adjustable silence auto-stop, and settings embedded in DSH settings dialog.","cmd":"dsh plugin --profile web add dsh-voice-chat","href":"/p/maoyuching/dsh-voice-chat/"},{"cat":"voice","tag":"Voice & Audio","dl":834,"stars":3,"added":"2026-09-19","npm":1,"name":"dsh-hold-to-talk","owner":"wangzhanchao883","short":"dsh-hold-to-talk","slug":"wangzhanchao883/dsh-hold-to-talk","desc":"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).","cmd":"dsh plugin --profile web add dsh-hold-to-talk","href":"/p/wangzhanchao883/dsh-hold-to-talk/"},{"cat":"voice","tag":"Voice & Audio","dl":821,"stars":2,"added":"2026-09-13","npm":1,"name":"dsh-voice-call","owner":"biliye","short":"dsh-voice-call","slug":"biliye/dsh-voice-call","desc":"Voice call assistant for the DSH Web GUI: a draggable floating call ball, browser-side VAD that sends each utterance after a pause, FunASR HTTP or streaming speech recognition, MiniMax or OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate subagent sessions with progress, stop, and spoken completion reports.","cmd":"dsh plugin --profile web add @biliye/dsh-voice-call","href":"/p/biliye/dsh-voice-call/"},{"cat":"voice","tag":"Voice & Audio","dl":813,"stars":1,"added":"2026-08-14","npm":1,"name":"dsh-voice-webspeech","owner":"anweat","short":"dsh-voice-webspeech","slug":"anweat/dsh-voice-webspeech","desc":"Browser Web Speech API voice input: zero server, zero keys, zero model downloads (Edge=Azure, Chrome=Google speech).","cmd":"dsh plugin --profile web add dsh-voice-webspeech","href":"/p/anweat/dsh-voice-webspeech/"},{"cat":"voice","tag":"Voice & Audio","dl":775,"stars":5,"added":"2026-08-15","npm":1,"name":"dsh-plugin-uisfx","owner":"XanthanL","short":"dsh-plugin-uisfx","slug":"XanthanL/dsh-plugin-uisfx","desc":"Semantic UI sound effects powered by uisfx: task start/success/failure and per-button cues, settings UI with instant preview, 12 sound packs, Host-persisted preferences, and `ctx.uisfx` service for other plugins.","cmd":"dsh plugin --profile web add dsh-plugin-uisfx","href":"/p/XanthanL/dsh-plugin-uisfx/"},{"cat":"voice","tag":"Voice & Audio","dl":666,"stars":10,"added":"2026-08-16","npm":1,"name":"dsh-sound","owner":"AI-Galaxy-GPU","short":"dsh-sound","slug":"AI-Galaxy-GPU/dsh-sound","desc":"Per-event sound notifications: turn completion, approval, question, plan-review, goal-blocked, and task-failure each get their own sound and volume, configurable in the Web UI (built-in synth, mute, or local audio file).","cmd":"dsh plugin --profile web add @ai-galaxy/dsh-sound","href":"/p/AI-Galaxy-GPU/dsh-sound/"},{"cat":"voice","tag":"Voice & Audio","dl":652,"stars":4,"added":"2026-08-16","npm":1,"name":"dsh-chatvoice","owner":"FuzzySoul","short":"dsh-chatvoice","slug":"FuzzySoul/dsh-chatvoice","desc":"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.","cmd":"dsh plugin --profile web add dsh-chatvoice","href":"/p/FuzzySoul/dsh-chatvoice/"},{"cat":"voice","tag":"Voice & Audio","dl":629,"stars":2,"added":"2026-08-17","npm":1,"name":"dsh-fish-tts","owner":"MaRi23333","short":"dsh-fish-tts","slug":"MaRi23333/dsh-fish-tts","desc":"Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message read-aloud, auto-read toggle, and a settings page for model, voice reference_id, encrypted API key, and proxy.","cmd":"dsh plugin --profile web add dsh-fish-tts","href":"/p/MaRi23333/dsh-fish-tts/"},{"cat":"voice","tag":"Voice & Audio","dl":594,"stars":3,"added":"2026-08-30","npm":1,"name":"dsh-voice-assistant","owner":"supersyh-sss","short":"dsh-voice-assistant","slug":"supersyh-sss/dsh-voice-assistant","desc":"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.","cmd":"dsh plugin --profile web add dsh-voice-assistant","href":"/p/supersyh-sss/dsh-voice-assistant/"},{"cat":"voice","tag":"Voice & Audio","dl":517,"stars":3,"added":"2026-08-14","npm":1,"name":"dsh-plugin-notify","owner":"huguangyu666","short":"dsh-plugin-notify","slug":"huguangyu666/dsh-plugin-notify","desc":"Notification outbox: agent proactively notifies via toast / Chinese TTS voice / sound effects (explosion, victory, alarm), 60s confirmation window voice-calls you back, volume boost, settings panel.","cmd":"dsh plugin --profile web add dsh-plugin-notify","href":"/p/huguangyu666/dsh-plugin-notify/"},{"cat":"voice","tag":"Voice & Audio","dl":480,"stars":1,"added":"2026-08-25","npm":1,"name":"dsh-pianist","owner":"Laplace-bit","short":"dsh-pianist","slug":"Laplace-bit/dsh-pianist","desc":"Piano performance plugin: ask the agent to play a piece and it renders on a Canvas2D grand piano with real Salamander Grand samples, an immersive stage, and an interactive 88-key keyboard.","cmd":"dsh plugin --profile web add dsh-pianist","href":"/p/Laplace-bit/dsh-pianist/"},{"cat":"voice","tag":"Voice & Audio","dl":472,"stars":74,"added":"2026-08-28","npm":1,"name":"dsh-omi-voice","owner":"PolinniZhong","short":"dsh-omi-voice","slug":"PolinniZhong/dsh-omi-voice","desc":"In-chat read-aloud for DeepSeek Harness: tap to read, pause and resume AI replies with natural Doubao TTS voices (BYOK), reading only the final answer with code, tables and diagrams filtered; local engine, plugin keeps no API key.","cmd":"dsh plugin --profile web add dsh-omi-voice","href":"/p/PolinniZhong/dsh-omi-voice/"},{"cat":"voice","tag":"Voice & Audio","dl":418,"stars":0,"added":"2026-09-02","npm":1,"name":"dsh-voice-control","owner":"SuCriss","short":"dsh-voice-control","slug":"SuCriss/dsh-voice-control","desc":"Voice control for the DSH web composer: push-to-talk speech-to-text into the input box (with optional auto-send), spoken playback of assistant replies via the Web Speech API, right-click settings popover, and a global Ctrl+M hotkey.","cmd":"dsh plugin --profile web add dsh-voice-control","href":"/p/SuCriss/dsh-voice-control/"},{"cat":"voice","tag":"Voice & Audio","dl":383,"stars":1,"added":"2026-08-24","npm":1,"name":"dsh-funasr-voice","owner":"fenglin-ai","short":"dsh-funasr-voice","slug":"fenglin-ai/dsh-funasr-voice","desc":"Offline voice input for the DSH Web UI: mic to local FunASR (SenseVoiceSmall), one-click install, no cloud.","cmd":"dsh plugin --profile web add dsh-funasr-voice","href":"/p/fenglin-ai/dsh-funasr-voice/"},{"cat":"voice","tag":"Voice & Audio","dl":372,"stars":4,"added":"2026-08-14","npm":1,"name":"dsh-plugin-notify-sound","owner":"ldchaowin","short":"dsh-plugin-notify-sound","slug":"ldchaowin/dsh-plugin-notify-sound","desc":"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.","cmd":"dsh plugin --profile web add dsh-plugin-notify-sound","href":"/p/ldchaowin/dsh-plugin-notify-sound/"},{"cat":"voice","tag":"Voice & Audio","dl":344,"stars":3,"added":"2026-08-27","npm":1,"name":"dsh-ximalaya","owner":"jerryqx","short":"dsh-ximalaya","slug":"jerryqx/dsh-ximalaya","desc":"Listen to Ximalaya podcasts and audiobooks inside the DSH web UI: search albums, browse paginated tracks, and play through a now-playing bar (prev/play/next, seek, volume, rate). After QR login the \"Mine\" page lists your liked tracks (click to play), subscribed albums with latest-episode hints, and followed anchors with their public albums; the host relays audio streams with Range support and registers an `ximalaya_play` tool so the agent can search and play on request.","cmd":"dsh plugin --profile web add dsh-ximalaya","href":"/p/jerryqx/dsh-ximalaya/"},{"cat":"voice","tag":"Voice & Audio","dl":309,"stars":0,"added":"2026-09-21","npm":1,"name":"dsh-read-aloud","owner":"cccc12138","short":"dsh-read-aloud","slug":"cccc12138/dsh-read-aloud","desc":"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.","cmd":"dsh plugin --profile web add dsh-read-aloud","href":"/p/cccc12138/dsh-read-aloud/"},{"cat":"voice","tag":"Voice & Audio","dl":296,"stars":0,"added":"2026-09-21","npm":1,"name":"dsh-say","owner":"fangqian616","short":"dsh-say","slug":"fangqian616/dsh-say","desc":"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.","cmd":"dsh plugin --profile web add dsh-say","href":"/p/fangqian616/dsh-say/"},{"cat":"voice","tag":"Voice & Audio","dl":254,"stars":6,"added":"2026-08-16","npm":1,"name":"dsh-voice-input-plugin","owner":"Zhangbo-cn","short":"dsh-voice-input-plugin","slug":"Zhangbo-cn/dsh-voice-input-plugin","desc":"Composer mic for the Web UI: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.","cmd":"dsh plugin --profile web add @zhangbo-cn/dsh-client-ui-voice-input","href":"/p/Zhangbo-cn/dsh-voice-input-plugin/"},{"cat":"voice","tag":"Voice & Audio","dl":237,"stars":2,"added":"2026-08-27","npm":1,"name":"dsh-voice-agent#voice-app","owner":"WayneYu430","short":"dsh-voice-agent#voice-app","slug":"WayneYu430/dsh-voice-agent--packages-voice-app","desc":"A conversational voice frontend Agent for dsh: speak naturally over ByteDance Duplex, delegate requests to background tasks, and hear their asynchronous results reported by voice.","cmd":"dsh plugin --profile web add @wayneyu430227/dsh-voice-agent","href":"/p/WayneYu430/dsh-voice-agent--packages-voice-app/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":12,"added":"2026-08-17","npm":0,"name":"dsh-voice-ai-girlfriend-plugin","owner":"beiyege-01","short":"dsh-voice-ai-girlfriend-plugin","slug":"beiyege-01/dsh-voice-ai-girlfriend-plugin","desc":"Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion animation window, and two-way QQ chat (text/voice/image push) via NapCat.","cmd":"dsh plugin --profile web add github:beiyege-01/dsh-voice-ai-girlfriend-plugin","href":"/p/beiyege-01/dsh-voice-ai-girlfriend-plugin/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":9,"added":"2026-08-14","npm":1,"name":"dsh-ding","owner":"CAOGGL","short":"dsh-ding","slug":"CAOGGL/dsh-ding","desc":"Notifies you when a conversation finishes: plays a sound and shows a Windows notification when the agent goes idle (configurable sound file, volume, debounce/throttle).","cmd":"dsh plugin --profile web add dsh-ding","href":"/p/CAOGGL/dsh-ding/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":8,"added":"2026-08-16","npm":0,"name":"dsh-voice","owner":"3274375092","short":"dsh-voice","slug":"3274375092/dsh-voice","desc":"Voice input for DeepSeek Harness: speak into the microphone and the recognized text is submitted as a normal chat message, via local or browser speech recognition.","cmd":"dsh plugin --profile web add github:3274375092/dsh-voice","href":"/p/3274375092/dsh-voice/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":7,"added":"2026-08-14","npm":0,"name":"dsh-plugin-call-me","owner":"radres","short":"dsh-plugin-call-me","slug":"radres/dsh-plugin-call-me","desc":"Rings your phone over CallKit: `call_me` and `text_me` tools, plus optional turn-end and approval calls whose spoken answer is transcribed back into the session.","cmd":"dsh plugin --profile web add github:radres/dsh-plugin-call-me","href":"/p/radres/dsh-plugin-call-me/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":6,"added":"2026-08-16","npm":0,"name":"dsh-perlica-ding","owner":"117BS","short":"dsh-perlica-ding","slug":"117BS/dsh-perlica-ding","desc":"Perlica (Arknights: Endfield) themed tiered sound notifications: plan-ready, task-done, needs-your-input, and error tones; silent for plain chat, system-level playback (works in background), cross-platform (Windows/macOS/Linux), custom TTS sounds.","cmd":"dsh plugin --profile web add github:117BS/dsh-perlica-ding","href":"/p/117BS/dsh-perlica-ding/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":5,"added":"2026-08-16","npm":0,"name":"dsh-voice-input","owner":"0nt-one","short":"dsh-voice-input","slug":"0nt-one/dsh-voice-input","desc":"Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language switching, and optional auto-send, zero dependencies.","cmd":"dsh plugin --profile web add github:0nt-one/dsh-voice-input","href":"/p/0nt-one/dsh-voice-input/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":4,"added":"2026-08-15","npm":0,"name":"dsh-voice","owner":"haoku123","short":"dsh-voice","slug":"haoku123/dsh-voice","desc":"Full-duplex voice mode for the Web UI: tap-to-toggle or hold-to-talk dictation (send key or `Ctrl`) with a live caption, host-side SenseVoice ASR via sherpa-onnx, sentence-by-sentence spoken replies, and speaking interrupts playback and the running turn (true barge-in). No API key.","cmd":"dsh plugin --profile web add github:haoku123/dsh-voice","href":"/p/haoku123/dsh-voice/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":4,"added":"2026-09-20","npm":0,"name":"dsh-tts-bridge","owner":"Yuuyuko-uu","short":"dsh-tts-bridge","slug":"Yuuyuko-uu/dsh-tts-bridge","desc":"Reads DSH conversations aloud using the DeepSeek web page's built-in read-aloud, driven by a small browser extension.","cmd":"dsh plugin --profile web add github:Yuuyuko-uu/dsh-tts-bridge","href":"/p/Yuuyuko-uu/dsh-tts-bridge/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":3,"added":"2026-08-18","npm":0,"name":"dsh-stt-input","owner":"baisama-cloud","short":"dsh-stt-input","slug":"baisama-cloud/dsh-stt-input","desc":"Speech-to-text voice input for the web UI: a mic button in the composer transcribes speech into the draft via the browser Web Speech API (zero-config) or an OpenAI-compatible Whisper API (OpenAI / Groq), with a selectable model and language in Settings.","cmd":"dsh plugin --profile web add github:baisama-cloud/dsh-stt-input","href":"/p/baisama-cloud/dsh-stt-input/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":3,"added":"2026-08-14","npm":0,"name":"dsh-voice","owner":"Jesse-njx","short":"dsh-voice","slug":"Jesse-njx/dsh-voice","desc":"Voice notes in, spoken answers out: dictate audio that becomes user messages (transcribe), have the agent read replies aloud (speak), local-first under ~/.dsh/voice.","cmd":"dsh plugin --profile web add github:Jesse-njx/dsh-voice","href":"/p/Jesse-njx/dsh-voice/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":3,"added":"2026-08-15","npm":0,"name":"voco-input-sh","owner":"Nothree-code","short":"voco-input-sh","slug":"Nothree-code/voco-input-sh","desc":"Voice input for the Web UI: a mic button that drives local VocoType offline speech recognition and auto-inserts recognized text into the composer (auto-deploy, dedupe, continuous dictation).","cmd":"dsh plugin --profile web add github:Nothree-code/voco-input-sh","href":"/p/Nothree-code/voco-input-sh/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":3,"added":"2026-08-14","npm":0,"name":"dsh-mic-input","owner":"QT-Chen","short":"dsh-mic-input","slug":"QT-Chen/dsh-mic-input","desc":"Microphone voice input for the composer: browser Web Speech API live transcription, dedupe/auto-continue, smart punctuation, language and auto-send settings.","cmd":"dsh plugin --profile web add github:QT-Chen/dsh-mic-input","href":"/p/QT-Chen/dsh-mic-input/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":2,"added":"2026-09-05","npm":0,"name":"dsh-tool-lipsync","owner":"yu-wenchao","short":"dsh-tool-lipsync","slug":"yu-wenchao/dsh-tool-lipsync","desc":"Free lip-sync video generation plugin for DSH with 3000+ voices and 500+ languages.","cmd":"dsh plugin --profile web add github:yu-wenchao/dsh-tool-lipsync","href":"/p/yu-wenchao/dsh-tool-lipsync/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":2,"added":"2026-08-27","npm":0,"name":"dsh-watch-video","owner":"zeshuochen","short":"dsh-watch-video","slug":"zeshuochen/dsh-watch-video","desc":"Subtitle-first video transcription with SRT export, cancellable job controls, and a faster-whisper large-v3 fallback when subtitles are unavailable.","cmd":"dsh plugin --profile web add github:zeshuochen/dsh-watch-video","href":"/p/zeshuochen/dsh-watch-video/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":1,"added":"2026-08-29","npm":0,"name":"dsh-live-voice","owner":"Jstn-1g","short":"dsh-live-voice","slug":"Jstn-1g/dsh-live-voice","desc":"Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.","cmd":"dsh plugin --profile web add github:Jstn-1g/dsh-live-voice","href":"/p/Jstn-1g/dsh-live-voice/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":1,"added":"2026-08-21","npm":0,"name":"dsh-voice-input-cn","owner":"Schumchanvi","short":"dsh-voice-input-cn","slug":"Schumchanvi/dsh-voice-input-cn","desc":"China-ready voice input for the composer. Requires a local Python bridge (pip install dashscope websockets, run bridge/voice-bridge.py) — the plugin alone does not work. Browser mic streams 16 kHz PCM to the bridge, which runs Alibaba Cloud DashScope ASR (paraformer-realtime-v2); interim text fills the draft at the cursor, silence auto-stop, optional auto-send.","cmd":"dsh plugin --profile web add github:Schumchanvi/dsh-voice-input-cn","href":"/p/Schumchanvi/dsh-voice-input-cn/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":1,"added":"2026-09-18","npm":0,"name":"dsh-multi-tts","owner":"WYR-233","short":"dsh-multi-tts","slug":"WYR-233/dsh-multi-tts","desc":"Per-reply read-aloud with a multi-provider settings page — MiniMax or any OpenAI-compatible /audio/speech endpoint, with voice, emotion, speed and model selection plus an auto-read toggle.","cmd":"dsh plugin --profile web add github:WYR-233/dsh-multi-tts","href":"/p/WYR-233/dsh-multi-tts/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":0,"added":"2026-09-11","npm":0,"name":"dsh-tts-flash","owner":"2021Heei","short":"dsh-tts-flash","slug":"2021Heei/dsh-tts-flash","desc":"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.","cmd":"dsh plugin --profile web add github:2021Heei/dsh-tts-flash","href":"/p/2021Heei/dsh-tts-flash/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":0,"added":"2026-08-29","npm":0,"name":"dsh-soundscape","owner":"berserk0501","short":"dsh-soundscape","slug":"berserk0501/dsh-soundscape","desc":"Dual-MediaPlayer daemon ($think loop + $fx one-shots) with volume ducking, mood-aware sounds (smooth/struggle/deep_think triggered by consecutive success/failure streaks and prolonged agent runtime), 15 built-in PCM WAV synthesised from sine/square waveforms, per-tool sound mapping with 51 categorised tools, custom WAV/MP3 drop-in with auto-conversion, and a full settings UI with dark-mode fix.","cmd":"dsh plugin --profile web add github:berserk0501/dsh-soundscape","href":"/p/berserk0501/dsh-soundscape/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":0,"added":"2026-09-18","npm":0,"name":"dsh-voice-alert","owner":"loyalchiiina","short":"dsh-voice-alert","slug":"loyalchiiina/dsh-voice-alert","desc":"Speaks or plays a sound at the end of every turn and plays a failure cue when a tool call or a turn errors. Ships 20 built-in effects (10 alert chimes + 10 nature sounds) and defaults to effect mode, so it needs no API key and no audio files; an optional Volcengine voice-clone route generates the three announcement clips in one click. Plays through winmm/waveOut as-is, never changing the system volume or mute state. Windows only.","cmd":"dsh plugin --profile web add github:loyalchiiina/dsh-voice-alert","href":"/p/loyalchiiina/dsh-voice-alert/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":0,"added":"2026-08-15","npm":0,"name":"dsh-voice-input","owner":"NewDaNew","short":"dsh-voice-input","slug":"NewDaNew/dsh-voice-input","desc":"Voice input for the web UI: a mic button in the composer that transcribes speech into the draft via the Web Speech API, with an optional auto-send toggle.","cmd":"dsh plugin --profile web add github:NewDaNew/dsh-voice-input","href":"/p/NewDaNew/dsh-voice-input/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":0,"added":"2026-08-17","npm":0,"name":"dsh-voice-live","owner":"tangzheng202202","short":"dsh-voice-live","slug":"tangzheng202202/dsh-voice-live","desc":"Real-time duplex voice over Volcengine streaming ASR/TTS: agent reply narration, barge-in, wake word, live captions, 30 Chinese voices and a reply-first acknowledgment; builds in the DSH monorepo.","cmd":"dsh plugin --profile web add github:tangzheng202202/dsh-voice-live","href":"/p/tangzheng202202/dsh-voice-live/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":0,"added":"2026-09-29","npm":0,"name":"dsh-xiaozhi","owner":"toddpan","short":"dsh-xiaozhi","slug":"toddpan/dsh-xiaozhi","desc":"Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weaving 35 DSH Web endpoints into 16 voice-friendly tools for workspaces, sessions, chat, models, settings and files — outbound WebSocket to the Xiaozhi MCP access point by default (no public IP or port forwarding needed), several devices bound at once, plus a DSH settings page with live status.","cmd":"dsh plugin --profile web add github:toddpan/dsh-xiaozhi","href":"/p/toddpan/dsh-xiaozhi/"},{"cat":"voice","tag":"Voice & Audio","dl":null,"stars":0,"added":"2026-09-08","npm":0,"name":"dsh-plugins#dsh-ding-sound","owner":"wwweljf","short":"dsh-plugins#dsh-ding-sound","slug":"wwweljf/dsh-plugins--plugins-dsh-ding-sound","desc":"Turn-end notification sound for DSH: built-in internet meme voices (ni gan ma ai yo, ji ni tai mei, shen ying ge, etc.), Settings panel with preview/switch/random, custom audio folder support.","cmd":"dsh plugin --profile web add github:wwweljf/dsh-plugins#path:/plugins/dsh-ding-sound","href":"/p/wwweljf/dsh-plugins--plugins-dsh-ding-sound/"}]}