Плагины
Находите, фильтруйте и устанавливайте плагины DeepSeek-Harness.
Найдено плагинов: 256
dsh-audio-copilot
ai-yucheng/dsh-audio-copilot
Аудио-второй пилот для DeepSeek Harness: транскрибирует аудио (ASR) и синтезирует речь (TTS) — даёт текстовым агентам уши и голос. Из коробки локальный Windows SAPI TTS; настраиваются ASR/TTS-эндпоинты, совместимые с OpenAI. Включает голосовой ввод в композере.
dsh-video-tools
piedpiper911/dsh-video-tools
Локальный в браузере набор инструментов для аудио/видео в DSH — извлечение кадров, захват миниатюр, сжатие изображений и конвертация клипов в GIF с помощью FFmpeg.wasm.
dsh-multimodal
yauntyour/dsh-multimodal
Мультимодальные цепочки по типу файла: предустановленные модели обработки для каждого шаблона преобразуют изображения, видео и аудио в токены промпта до того, как они попадут в текстовую модель сессии, с цепочками отказов для каждого пресета и страницей настроек Multimodal.
dsh-notification-sounds
qq33357486/dsh-notification-sounds
Кросс-платформенные звуковые уведомления об ожидании пользователя и завершении для веб-интерфейса DeepSeek Harness.
beav-deepseek-harness
jamailar/beav-deepseek-harness
Подключает DSH к локальному Beav для работы с Xiaohongshu (RED/RedNote) и социальными медиа: исследование тем, знания, копирайтинг, изображения, аудио и короткие видео с подтверждениями и отслеживанием артефактов.
dsh-live-captions
flashvayne/dsh-live-captions
Real-time captions: recognise system audio and the microphone, bilingual subtitles, translation between many languages, and meeting minutes in one click.
dsh-ellen-voice
deek-234/dsh-ellen-voice
Speaks a short piece of text through a local TTS HTTP endpoint, caches the audio, and plays it on this machine's speakers.
dsh-pianochart (dsh-bundle)
regrevia/dsh-pianochart
Adds piano_score, which takes one audio link and writes a piano score: staff PNGs, numbered notation, MusicXML, MIDI. It transcribes the background music and drops the vocal; drums and non-melodic parts are folded into the left hand. Three tiers share one arrangement and differ only in key signature, so easy has the fewest black keys and playback restores the original pitch. Long audio can be previewed with seconds.
dsh-man-report
gongfpp/dsh-man-report
Shows a Kobe iced-tea side popup and reports per-turn costs or token counts with bundled offline audio. The voice switches between four emotion tiers by amount, and the ten most common amounts in both CNY and USD play as whole-sentence takes (400 takes in total). Uses dsh-cost-meter when present, otherwise estimates each request from native usage and public prices, labeled as an estimate. Includes twenty cost phrases, four token phrases, CNY/USD, two-decimal ceiling rounding and custom previews; no runtime TTS service or API key. The code is MIT-licensed; the bundled Kobe portrait, icons and pre-made voice clips are not redistributed under that MIT grant and are for personal, non-commercial use with this plugin only. When it has to estimate a cost itself it fetches a public price table from raw.githubusercontent.com (Han-1413141/dsh-cost-meter) and the USD/CNY rate from open.er-api.com, at most once a day, and sends no session data.
dsh-read-aloud-edge
hexiao160705-dev/dsh-read-aloud-edge
Speaker button on every assistant reply that synthesizes the reply with the locally installed edge-tts and plays it in a small player with 1x-4x speed control; audio is cached by content hash and the reply text never leaves the machine to a paid API.
dsh-ace-music
gladess1102/dsh-ace-music
ACE Music MCP server for DSH: sign in once with your own account over OAuth, then write full songs, continue a melody from a MusicXML or ABC score, upload audio for transcription, and inspect or download tracks as native acemusic_* tools. Ships a dependency-free MusicXML-to-ABC converter and ACE Music's published writing guides for offline use.
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-kumquat
adengou/dsh-kumquat
Media conversion panel for DSH: video and audio format conversion, clip trimming, and video-to-GIF, with every output checked for resolution, codec, framerate, duration, channels and sample rate.
dsh-sfx-pad
dingchenhui0618-arch/dsh-sfx-pad
Event sound pad for DeepSeek Harness: bind test pass/fail, build pass/fail, recording start/stop, publish done, pending approvals and turn end to ten local cue files, classified from real tool arguments plus exit code. The panel previews each pad, mutes everything in one click, and switches a mute profile (default / focus / silent) when you leave the harness or report a matching app name. Audio is read-only and local, the only file it writes is its own preferences, and no path outside the cue catalog is ever served.
dsh-gemini-antigravity-auth
battiatus/dsh-gemini-antigravity-auth
Gemini models from your Google Antigravity subscription inside DeepSeek Harness: Google OAuth, multi-account quotas, Google Search grounding, and image, audio, video and PDF understanding.
dsh-mac-notify
carbenelee/dsh-mac-notify
Native macOS notifications for DSH: task completion, failures, approval requests, questions and plan reviews. A small bundled helper app lets banners use the DSH icon and opens DSH on click; the notification tone can be any audio file.
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-duanju-slice
yanghangju/dsh-duanju-slice
Short-drama clipping workbench: given a drama folder, a script DOCX, an export folder and a content direction, it picks the matching lines, obtains their real time codes by streaming the episode audio to Doubao speech recognition (a Doubao voice API key is required), tightens the cut to the returned word timestamps, checks the boundary frames, and exports an editable Jianying draft plus an MP4 carrying the source dialogue, BGM and sound effects; trim points and volume can be revised in the same chat and every revision is kept as a new version.
dsh-audio-extract
chanchanxue/dsh-audio-extract
Adds an "Audio extraction" view to the session view switcher that stream-copies a video's audio track into m4a without re-encoding, optionally trims the start and end, and writes title, artist, cover art and lyrics tags. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-blender-preview
adithyanraj03/dsh-blender-preview
Files-tab previews for DeepSeek Harness: .blend (headless local Blender export to a cached GLB), .glb/.gltf/.obj in a WebGL viewport, plus .svg, video and audio; depends on dsh-blender with a read-only boot self-check; no network calls, no telemetry, no postinstall; uninstall removes the row. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-tts
leiboss/dsh-tts
Long-form voiceover pipeline for DeepSeek Harness: chapter planning, spoken-script adaptation, subtitles, manifest, and resumable jobs. Turns a document into a publishable audio set.
dsh-synthesizer
yishan/dsh-synthesizer
Multi-track Web Audio synthesizer and 8-piece drum machine with a piano-roll sequencer, scale and chord generators, four agent composition tools and a /synth command, background sidebar playback, and WAV/MIDI export.
dsh-ai-voice-cover
vamyane/dsh-ai-voice-cover
AI voice cover for DeepSeek Harness: give any song plus about 10 seconds of reference audio and get a cover sung in that voice — dry vocal and mixed final, with the melody aligned to the original because only timbre is swapped. Supports zero-shot covers and archived voice libraries, automatic semi-tone shift synced with the accompaniment, an isolated Python venv, and runs on GPU or CPU.
dsh-hear
flyingcharon/dsh-hear
Gives a text-only agent an ear: a local audio model says what was said and how it sounded, checked against measured pitch, energy and pauses, with optional QQ voice watching. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.