Plugins
Durchsuche, filtere und installiere DeepSeek-Harness-Plugins.
82 Plugins gefunden
dsh-wsl-media
173787247/dsh-wsl-media
Lokale Medien-/Dokumentpipeline mit ffprobe, Extraktion, Vorschaubildern, PDF, ASR, pandoc, OCR und exif; allowRoots umfasst IM inbox.
dsh-wsl-im
173787247/dsh-wsl-im
Verbindet Feishu, WeCom, DingTalk, QQ, Slack, Discord, Telegram und Mattermost mit dsh-Agents (Ausgang über WS/Stream/Gateway/long-poll/webhook). Mit `im_status`, optionalem lokalem Whisper-ASR, Klartextversand für QQ/DingTalk/Telegram/Mattermost und CSV-Allowlist über `DSH_IM_*_ALLOWED_USER_IDS`. Ist `allowedUserIds` leer, kann jeder den Agent steuern — vor Veröffentlichung des Bots eine Allowlist setzen.
dsh-minimax-asr
moluyao/dsh-minimax-asr
Globales MiniMax-Sprach-Plugin für DeepSeek Harness: Spracherkennung (`asr-1.0`) und -synthese (`speech-2.8-hd`), Transkriptionstool, gesprochener Satz nach Aufgabenabschluss, freihändige Echtzeitgespräche und 303 auswählbare Stimmen.
dsh-funasr-voice
fenglin-ai/dsh-funasr-voice
Offline-Spracheingabe für die DSH-Web-UI: Mikrofon an lokales FunASR (SenseVoiceSmall), Ein-Klick-Installation, keine Cloud.
dsh-audio-copilot
ai-yucheng/dsh-audio-copilot
Audio Copilot für DeepSeek Harness: Audio-Transkription (ASR) und Sprachsynthese (TTS) – gibt textbasierten Agenten Ohren und eine Stimme. Windows-lokales SAPI-TTS ab Werk; OpenAI-kompatible ASR/TTS-Endpunkte konfigurierbar. Inklusive Spracheingabe im Composer.
dsh-video-localmodel
wth373737/dsh-video-localmodel
Local-first video screening: ffmpeg samples frames, local Qwen3-ASR writes timecoded subtitles, a local vision model captions and ranks sampled frames, and a local text model folds the transcript into chapters; the original candidate frames are then handed to the leading model. Every stage resumes from the workspace, and export writes SRT, a timeline and native-resolution key frames.
dsh-realtime-interview
liangshoux/dsh-realtime-interview
Mock interview room for DeepSeek Harness: a resume and a job JD become a tiered checklist, then a live round-by-round interview runs in the sidebar with camera view, microphone transcription and spoken questions, ending in a per-checkpoint post-interview report. Two skills (interview-prep, interview-conduct) drive the flow, and transcripts, recordings and reports stay on your own machine. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-tools-deepseek-media
oh-wang/dsh-tools-deepseek-media
Agent tools for DeepSeek OCR, ASR and TTS: recognize text in PDF and image files, transcribe WAV audio, and synthesize speech to a local file.
dsh-deepseek-tools
zaofan-make/dsh-deepseek-tools
DSH(deepseek-harness)上使用 DeepSeek 全家桶五件套(联网搜索 / 读链接 / OCR / ASR / TTS)!(DSH-Plugin&full suite of application APIs)
dsh-asr-openai
caiccc-a11y/dsh-asr-openai
可以直接本地调用DSH内置语转文模型的插件,支持openai标准格式。
dsh-meeting-memo
jqlong17/dsh-meeting-memo
Right-sidebar meeting minutes for DeepSeek Harness — local capture, on-device transcription, speaker labels, and structured minutes; audio never leaves the machine.
dsh-voice-input-wb-asr
baibiaowang/dsh-voice-input-wb-asr
Free speech-to-text for DeepSeek Harness. Hold the composer microphone (or Alt while the caret is in the composer) and the text is typed into the input box as you speak: the audio is cut at pauses, each phrase is recognized as it lands, and releasing the button recognizes the whole take once more and replaces the preview with the corrected transcript. Also ships wb_transcribe, which turns long audio or video into one timestamped Markdown document (an 82-minute recording in 47 seconds in a measured run). Recognition uses the WorkBuddy accounts already signed in; WorkBuddy does not bill speech input. International and domestic builds are separate settings, international by default.
dsh-bilibili_video-study_buddy (plugin)
aaarookie/dsh-bilibili_video-study_buddy
Bilibili course study buddy for DeepSeek Harness. Four tools: study_frame grabs a timestamped frame at 1080p with region cropping and a disk cache; study_scan samples a time range into one grid image for locating; study_subs extracts AI subtitles and scores three signals to detect contaminated subtitle tracks; study_asr transcribes a short window with surrounding context. Read-only; all data stays local.
dsh-podwave
watchcats211/dsh-podwave
Local-first podcast player and transcriber for DeepSeek Harness: plays audio files from your disk, transcribes with local ASR, shows bilingual subtitles and exports SRT or Markdown.
dsh-qwen-mcp
paysnatal/dsh-qwen-mcp
Connects all seven Qwen Token Plan Harness-entitlement MCP services (enhanced search, web fetch, code interpreter, vertical search, image, TTS, ASR) plus the decision-model-preview model (qwen_decide) as native tools, with a per-service on/off and live-status panel.
dsh-self-learn
jackheather/dsh-self-learn
Learn from Bilibili videos, web pages, local files and live streams: local ASR, on-screen OCR and extractive digests add up to about 1.5KB of text per source, so the model reads a summary instead of a full transcript.
dsh-team-workbench
narkco-kang/dsh-team-workbench
A named-agent-team chat workbench for DSH: per-member model routes with fallback and 3D mascot avatars; private and group chats with mention relay and bounded parallel lanes; a whole department as one agent whose lead dispatches sub-agents that run in parallel on their own models before the lead synthesizes; record search with hit highlighting and today/yesterday/earlier buckets; a four-layer memory system (raw chats → atomic facts → scene summary → user persona) recalled by hybrid BM25 + embedding RRF; plus an avatar library and local/cloud speech input. Hybrid recall needs an embedding endpoint (default: local Ollama qwen3-embedding:0.6b; otherwise BM25 only); speech input needs a local jianchang512/stt service or a cloud ASR key, otherwise it falls back to the browser speech API.
dsh-pf-stream
weilv-d/dsh-pf-stream
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).
dsh-video-learning
szuold8/dsh-video-learning
Video study toolkit for DeepSeek Harness: fetch a public Bilibili single part or YouTube video, sample every 3 seconds plus change-triggered frames, transcribe locally with faster-whisper, page through section grids, and render a 16:9 study deck. Windows only, and needs the DSH pwsh tool plus Python 3.12 x64 with Pillow and FFmpeg/FFprobe; fetching adds yt-dlp, transcription needs faster-whisper with your own local model files, and deck output needs python-pptx.
VoiceTranser
lumos-789/voicetranser
Vollständig lokale Push-to-talk-Spracheingabe für macOS: globale Taste halten, sprechen, loslassen; die Transkription wird am Cursor eingefügt. Local-first-STT (standardmäßig Qwen3-ASR 0.6B 4bit auf MLX/Metal, Ausweichmodelle SenseVoice und mlx-whisper), keine externen APIs, selbstheilender launchd-Dienst und 8-Punkte-Diagnoseskript. Der enthaltene Skill lässt den Agenten die gesamte Toolchain installieren, konfigurieren (Karabiner-Hotkey-Verknüpfung, launchd, Engine-Wechsel) und Fehler beheben.
dsh-voice
scarf1985566475-cloud/dsh-voice
Lokale simultane Englisch-Chinesisch-Dolmetschung: zweisprachige Untertitel auf dem Gerät mit Qwen3-ASR und automatischer Spracherkennung, absturzsichere Meeting-Aufzeichnungen mit Protokoll sowie Obsidian-Export.
dsh-voice-memo
dingchenhui0618-arch/dsh-voice-memo
Diktat, das im Repository statt im Chatlog landet. Taste halten oder WAV importieren; `voice-memos/<id>/` enthält `audio.wav`, gerendertes `waveform.png`, `memo.md` (Frontmatter, Zeitstempel je Segment, kopierfertige Zitatblöcke) und `meta.json`. Browser resampelt vor dem Senden auf 16 kHz mono. Transkription bleibt lokal: Harness `speechToText` mit nach Stille getrennten Fenstern oder ein Command-Worker wie `faster-whisper`. Ohne Engine wird die Notiz mit Status und Grund archiviert, ohne erfundenes Transkript. Gesprächstab „口述“ mit Klick-zum-Suchen, Zitatkopie je Segment, 3 Tools (voice_memo_save / voice_memo_list / voice_memo_read) und HTTP-Routen. Keine Runtime-Abhängigkeiten, 52 `node:test`-Fälle, echte Screenshots in docs.
dsh-bilibili-subtitles
chenfan2/dsh-bilibili-subtitles
Extrahiert Bilibili-Plattform-/KI-Untertitel oder nutzt externe/eingebettete Untertitel sowie ASR/OCR als Fallback und erzeugt Markdown, Word, PDF, TXT, SRT oder JSON mit Zeitstempeln, zweisprachiger Ausrichtung und Qualitätsbericht. Python 3.10+ erforderlich. Plattform-/KI-Untertitel benötigen ein Bilibili-SESSDATA-Cookie; OCR/ASR/PDF benötigen ffmpeg, faster-whisper und LibreOffice oder reportlab.
dsh-mimo-tts
lengmodkx/dsh-mimo-tts
MiMo-Stimme für DeepSeek Harness: Liest jede fertige Antwort vor, wandelt Composer-Diktat in Text um und bietet neun integrierte Stimmen sowie einen Slot für eine geklonte Stimme.