Plugins
Durchsuche, filtere und installiere DeepSeek-Harness-Plugins.
251 Plugins gefunden
dsh-interaction
philomelcc/dsh-interaction
Branching multi-step questions with back-navigation, cross-session messaging, and audio and image previews in the file sidebar.
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-sidebar-media-player
loyalchiiina/dsh-sidebar-media-player
Audio and video player that lives in the DSH sidebar: video (mp4/webm/mov/m4v/ogv) and audio (mp3/wav/flac/ogg/opus/m4a/aac) open in a sidebar tab with same-name subtitles and a draggable seek bar, while a panel with QQ Music and local music tabs adds a turntable, a live spectrum (bars or wave), a pitch readout (note name, Hz, cents) and lyrics with word-by-word timing, five effects and two layouts. One control row in a single style holds 18 candidate buttons (at most 17 on screen) for favourites, loop (order, single, shuffle), rate 0.5-2, subtitles and a 6 to 10 column grid. The QQ Music side covers search, charts, playlists and new songs, and favourites are written to the same liked list the signed-in account sees instead of a local flag. The local side scans a folder, accepts drag and drop and reads items as whole files so seeking works. A capsule bar docks above the input box, sits at the bottom or hides, and its buttons map onto panel controls through one shared store. Defaults: capsule above the input box, 10 columns, rainbow lyrics, order loop, spectrum on, two-line lyrics, bars. The QQ Music interface is unofficial and only the desktop profile is verified. It is a third-party fan tool, not a Tencent product, plays only your own library, joins no official campaign, and is removed on an infringement notice. Adapts DSH kernel 0.2.2-rc.1. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
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. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
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.
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-voice-deepseek
asya903/dsh-voice-deepseek
Reads assistant replies aloud with DeepSeek official TTS: one speaker button in every reply action bar, stella (female) by default, tide (male) optional. Audio is cached per identical text, so replaying the same sentence costs nothing. Requires a DeepSeek API key - about CNY 1.5 per 10k characters at the current 50% discount.
dsh-montagex
royrao2007/dsh-montagex
Full-pipeline video production harness: brief triage, shot planning, storyboard, image/video/audio generation, an infinite shot canvas, local ffmpeg editing and deterministic QC across 161 tools, plus roles, shot claiming and signing gates for team review.
smart-dictation-dsh (smart-dictation-bundle)
triagmas/smart-dictation-dsh
Local Russian dictation for the DSH composer with GigaAM v3, English technical terms, punctuation, and a personal glossary that learns only after confirmation. Audio and transcripts never leave the machine.
dsh-voice-input
pandaman0759/dsh-voice-input
Doubao streaming speech-to-text button in the DSH composer — one API key and your words land in the draft. Needs a Doubao (Volcengine) speech-recognition API key, kept in the DSH credential store; recorded audio is sent to Volcengine, and its HTTP routes have no DSH access check.
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-tts-voice
pandaman0759/dsh-tts-voice
End-of-turn voice summary: the model calls voice_say once before finishing a reply so the conclusion is spoken through Breeze TTS, with Chinese bracket audio tags (laughter, sighs, pauses) and optional performance instructions. Audio is synthesized host-side and played from browser memory without ever touching disk; the character limit is a writing target for the model, not a cut-off, so long lines still play in full. The API key stays in the credential store, and an optional daily Breeze check-in is included. Needs a Breeze API key and sends the spoken text to the Breeze service; its HTTP routes (including the settings route that stores the key) have no DSH access check.
media-review-dsh
ww-cooooo/media-review-dsh
A Windows Harness adaptation of [Media Review Skill](https://github.com/Ww-Cooooo/media-review) for AI video feedback: annotate frame regions or time ranges and jump to recognized speech or imported subtitle cues; other Agents with local file and command access can use the original Skill. Windows only and built for DSH 0.2.2-rc.1 (a 0.1.0 release candidate). Waveforms use an existing FFmpeg/ffprobe and transcripts an existing Whisper; without them, manual annotation and subtitle import still work.
audio-transcript-skill
chengfeiai/audio-transcript-skill
Skill that transcribes local audio files into a timestamped transcript and an interactive two-column minutes page, with optional speaker separation. Transcription uses mlx-whisper in a Python 3.11 environment you set up yourself (the first run may download models); the renderer uses only the system python3. Given a public short-video share link, it can also drive a real browser through ego-browser and fetch the audio track with curl and ffmpeg, none of which ship with the package.
dsh-man-031
gongfpp/dsh-man-031
Shows a Kobe iced-tea side popup and reports per-turn costs or token counts with bundled offline audio. Uses dsh-cost-meter first, or estimates each request from native usage and public prices. Includes twenty cost phrases, four token phrases, CNY/USD, three-decimal rounding and custom previews; no runtime TTS service or API key. The bundled voice clips are pre-synthesized offline and the portrait is a fan-made image; the package declares UNLICENSED. 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.