Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
51 plugin trovati
dsh-doubao-video
fangqiuci/dsh-doubao-video
Doubao video workshop: a gated pipeline from storyboard to finished cut. Locked art direction, shot validation, character-card vs reference-image separation, first/last-frame continuity and clip dedup; model-aware duration caps (Mini/Fast 10s, 2.0 15s, 2.5 40s). Uses ffmpeg for frame extraction, concatenation and subtitles; speech synthesis calls a separately installed local TTS plugin, and ASR subtitles need Python with faster-whisper.
dsh-video-replica
limomss-dunang/dsh-video-replica
Six-step video-replica workbench: fetches a Douyin/Xiaohongshu/WeChat Channels/Kuaishou/Bilibili share link or a local file, breaks the source into shots with a vision model and optional ASR, writes three A/B/C storyboards, generates a first frame and a clip per shot, then stitches the final video with optional TTS narration, burned-in ASS subtitles and BGM. Needs Node 22.18+/24.11+, ffmpeg and ffprobe on PATH, and configured vision/chat/image/video model endpoints; share links go through a third-party parser service (or yt-dlp), or upload a local file.
dsh-bili-see
aba3345/dsh-bili-see
Autopilota Bilibili con Ollama locale: video entro quota tema, sottotitoli/commenti/keyframe, decisione e pubblicazione commento attraverso cinque livelli di sicurezza. Avvio dsh-schedule; disabilitato non registra tool di scrittura. v1.1 verifica permesso prima di ogni invio, pubblica atomicamente, mette in pausa errori rischio e ricontrolla stile persona. Richiede Python 3.10+ e requirements.txt.
dsh-bilibili
moxingovo/dsh-bilibili
Plugin DeepSeek Harness: ricerca video Bilibili per parola chiave, metadati video, trascrizioni dei sottotitoli, URL di riproduzione diretti e visualizzazione multimodale dei frame (bilibili_search / bilibili_video / bilibili_subtitles / bilibili_playurl / bilibili_frames). Anonimo per impostazione predefinita.
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-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-livestream-douyin (dsh-livestream)
tuoqie/dsh-livestream-douyin
Experimental read-only Douyin browser chat capture and an AI livestream host stage with subtitles and speech for DeepSeek Harness; platform broadcasting uses external livestream software. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-lingualab
tecfancy/dsh-lingualab
Intensive-listening practice for media already in the workspace: sentence-by-sentence drills with speed, looping, shadowing and recording, kept sentences with three grades, and a notes.md per episode written back to disk. 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-whale-glance
yan9690/dsh-whale-glance
Whale Glance (余光, "yu guang") — a screen companion for DeepSeek Harness on Windows. A background helper samples the screen, diffs it, and when the picture changes enough, wakes a one-shot subagent that looks at a stitched frame grid plus the on-screen text, and writes one line to a floating subtitle window. Game mode recognizes the running game and uses its slang library; video mode buffers recent subtitles so the subagent can follow a stretch of dialogue and keep a per-show episode archive. The subagent never writes back into your main session, so long use does not grow its context. Off by default, with cooldown, hourly cap and window-title filter.
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.
bilibili-note-plugin
3588834014-del/bilibili-note-plugin
Registers a skill that turns a Bilibili video link into a structured Obsidian note. It fetches subtitles only with yt-dlp and never downloads the video, merges multi-part anthologies onto one continuous timeline, and writes front matter, timestamped jump-link bullets, a summary and tags into the vault.
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-bili-creator
men-qingzheng/dsh-bili-creator
Bilibili companion for DSH, derived from c1overzz/dsh-bili-scroll (do not install both: they share the plugin entry id bili-scroll). Understand any video with AI summaries, chapters and subtitles; make your own with edge-tts voice-over, captions and ffmpeg; publish, post dynamics, reply to fans and read creator stats (publishing and dynamics stay off until Creator mode is enabled); plus an optional daily curated feed report. First run needs a one-time in-app install of Python dependencies (a uv venv plus PyPI packages such as bili-agent and edge-tts) and a Bilibili QR login.
dsh-vidi
cocosgt/dsh-vidi
A video tool for DeepSeek Harness: watch live streams, videos and podcasts with real-time subtitles in any language, then clip and download
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-subtitle-remover
lijianbin2/dsh-subtitle-remover
Sidebar page that removes burned-in subtitles from a video with a local video-subtitle-remover checkout: frame preview with a start/end range, drag-drawn regions (up to six), automatic region detection reviewed by a DSH chat model, live before/after comparison, and open-file/open-folder on the result. Requires the video-subtitle-remover checkout with its models and a Python environment with torch, paddle and OpenCV.
dsh-media-converter
a1121611810/dsh-media-converter
Local media toolbox for DeepSeek Harness: converts files between 27 video, audio and image formats, trims clips, extracts audio or video tracks without re-encoding, exports embedded subtitles to .srt, compresses images with a before/after preview, reads and rewrites metadata, and encodes or decodes Base64 — all through the ffmpeg already installed on the machine, so files never leave it. The same engine is registered as a media_toolbox tool agents can call.
dsh-clipforge
avenyq/dsh-clipforge
Video workbench for DeepSeek Harness that parses a link, downloads the source, transcribes it, trims or merges clips and exports GIFs. Requires ffmpeg/ffprobe and yt-dlp; whisper.cpp plus a model is optional for videos without subtitles.
dsh-bili-whale-safever-by-jediliu
jediliu005/dsh-bili-whale-safever-by-jediliu
Bilibili companion for DSH (MIT fork of Alterssss/dsh-bili-whale; do not install alongside the upstream — both register the same `/dsh-bili/` settings routes and share `~/.dsh/bili-whale.config.json`): wakes on a schedule, reads videos through subtitles, danmaku, hot comments and covers, writes two diaries, and shares at most one pick per wake by commenting on the video and @-mentioning the owner (daily quota 3; DM when `share.via=dm`). Inbound DMs, commenter names, summary requests and live danmaku are normalized and scanned for injected instructions before they reach the model; only the owner DM channel can carry an authorization prefix.
delivery-video-plugin
lumos-789/delivery-video-plugin
Trasforma una funzionalità realmente funzionante in un video demo di consegna affidabile: registrazioni reali dello schermo, narrazione edge-tts con sottotitoli sincronizzati parola per parola, pipeline ffmpeg autonoma e controllo qualità deterministico (specifiche, audio, loudness, scansioni di schermate nere, blocchi e silenzi) che rifiuta demo false o guaste. Include preflight e verifica degli artefatti. Richiede Python 3.9+, ffmpeg/ffprobe nel PATH e `pip install edge-tts Pillow`; la narrazione chiama l'endpoint pubblico edge-tts.
dsh-video-to-knowledge
yayuqianhuang/dsh-video-to-knowledge
Trasforma un link video in schede di conoscenza Markdown con timestamp e backlink al momento esatto. Richiede Python 3.10+ e yt-dlp forniti dall’utente. ffmpeg e faster-whisper servono solo per video senza sottotitoli; i sottotitoli per i membri richiedono cookie di accesso Bilibili.
dsh-video-reader
ck99998888/dsh-video-reader
Legge file video/audio ricavando metadati, fotogrammi fissi campionati, sottotitoli e trascrizione multilingue con etichette dei parlanti. Acquisisce anche il desktop in tempo reale come fotogrammi o registrazione. Al primo uso installa ffmpeg/whisper.cpp/sherpa-onnx e verifica sha256 per file; tutta l’elaborazione resta locale. Installazione automatica e acquisizione desktop sono attualmente supportate solo su Windows x64; altrove occorre configurare manualmente i percorsi di ffmpeg e dei modelli.
dsh-bilibili-subtitles
chenfan2/dsh-bilibili-subtitles
Estrae sottotitoli di piattaforma/AI da Bilibili oppure usa come fallback sottotitoli esterni/incorporati, ASR o OCR e genera Markdown, Word, PDF, TXT, SRT o JSON con timestamp, allineamento bilingue e rapporto qualità. Richiede Python 3.10+. I sottotitoli piattaforma/AI richiedono il cookie SESSDATA di Bilibili; OCR/ASR/PDF richiedono ffmpeg, faster-whisper e LibreOffice o reportlab.