Плагины
Находите, фильтруйте и устанавливайте плагины DeepSeek-Harness.
Найдено плагинов: 256
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-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.
V-yovoice (tool-audio-transcription)
ictrektech/v-yovoice
Transcribe session audio through V-yovoice and display a waveform player and transcript. Needs a reachable V-yovoice service (its root URL is set in the plugin's configuration); audio files are sent to that service.
dsh-plugins (realtime-voice)
feahter/dsh-plugins
Continuous dictation for the composer using a local SenseVoice ONNX model on CPU: recognised text appears while you speak, a pause ends the sentence and writes it into the input box, and audio never leaves the machine.
sgen
qjy0128/sgen
Sidebar playground for SenseNova and Agnes image and video generation, per-provider API keys and default models, local result management, and sgen_* tools for conversations. Each request runs the bundled sgen command-line tool, any reference image or audio you give by local path is uploaded to the provider as base64, API keys live in ~/.sgen/config.json, and the sidebar saves results under ~/sgen unless you pick another folder.
connectors (deepseek-harness)
dotv-ai/connectors
Drive the DOTV infinite canvas from DeepSeek Harness: the agent lists your canvases and their nodes, adds text nodes, and runs image/video/audio generations — over DOTV's public API, with no runtime dependencies and no build step. It reuses the `dotv` CLI login on the machine, or takes an API key in the plugin settings. Generations consume credits on your account, exactly as they do in the app.
dsh-arknights-splash
18518182595-cell/dsh-arknights-splash
Arknights-style procedural opening film and silent looping chat backdrop for the DeepSeek Harness Web UI: Canvas-drawn visuals, synthesized WebAudio sound, click-anywhere skip, cross-dissolve into the interface, live-adjustable opacity; zero dependencies and no media files. By default the film (about 12 seconds, with sound) plays on every page load; a setting turns it off.
DSH-Translate
light-cheng/dsh-translate
Bilingual reasoning, selection translation, composer polish, an offline English–Chinese dictionary with IPA, pronunciation and a vocabulary notebook for DeepSeek Harness. Instant selection translation is on by default and, on the cloud engine, sends the selected text to the model; pronunciation audio is fetched from Youdao when clicked or hovered; the bundled dictionary data (ECDICT and ipa-dict) is GPL-3.0.
dsh-plugin-meeting-assistant
vianvio/dsh-plugin-meeting-assistant
DSH 会议助手:本机麦克风采集与 DashScope 流式转写、会前准备、会中发言建议与会后记录。独立插件,不依赖 Agent Mesh 或任何平台连接。
dsh-mimo-tts
hao0311/dsh-mimo-tts
Text-to-speech for DeepSeek Harness through Xiaomi MiMo TTS, needs a XIAOMI_API_KEY: a mimo_tts tool that writes audio to a local file, a read-aloud action on each finalized answer, auto-read, and a sidebar panel for built-in voices, voice design by description, or voice cloning from an mp3/wav sample. Same package name as lengmodkx/dsh-mimo-tts, so the two cannot be installed together.
dsh-kit (dsh-audio-post)
474885697-alt/dsh-kit
Runs loudness normalization, silence trimming, format conversion and batch processing through local ffmpeg, with presets for game sound effects, music uploads and voice cleanup.
dsh-audio-player
15060899827/dsh-audio-player
Inline audio player for generated clips and songs: the play_audio tool renders a player in the conversation (promoted into the transcript when the host supports it, otherwise inside the tool-call fold). Serves only allow-listed directories, supports Range seeking and HEAD, 512 MB cap per file.
dsh-media
dungcsnd1133/dsh-media
Adds three session tools — create_image and edit_image over GPT Image or Gemini through the TLPro gateway, and speak for text-to-speech through xAI — plus a viewer in the chat UI for the images and audio they produce. Needs your own TLPRO_API_KEY and XAI_API_KEY, and publicOrigin and mediaDir set in the profile config.
dsh-CET6-learn
mount9527/dsh-cet6-learn
CET-6 training panel with word drills (core and syllabus lists, three modes), 25-question listening in three sections, cloze, long reading, careful reading, partial and full translation, timed writing, a vocabulary notebook and a wrong-answer notebook. Ships only an original sample bank (345 words, one mock paper); the full ~2,500-word core list, ~6,000-word syllabus list, papers, transcripts and audio come from your own files, built locally from a data-pack folder and never uploaded.
dsh-video-watch
dungcsnd1133/dsh-video-watch
Downloads a video link, samples frames from it, and transcribes the speech with Groq Whisper so an agent can answer questions about what the video shows; long audio is split into 15-minute windows to stay under the upload limit, and frames still come back without a key, which only the transcript needs. Needs ffmpeg, ffprobe and yt-dlp on PATH.
dsh-media-kit
daphne999/dsh-media-kit
Pull frames and audio out of a local video with ffmpeg and hand back plain file paths, so the agent can look at the frames with its own vision. Five tools: probe, evenly spaced frames, one frame at a timestamp, scene-change frames (the practical version of frame-by-frame), and audio extraction. No models, no uploads, no routing guesswork.
dsh-bluetooth-earbuds
glowwan/dsh-bluetooth-earbuds
Windows-wide Bluetooth earbud shortcuts for AI work: a left-earbud volume-down gesture starts or stops Windows voice typing (Win+H), and a right-earbud volume-up gesture sends Backspace. The DSH settings page offers manual key mapping, test actions, Backspace count, volume-gesture detection, and a 1.6-second cooldown so one triple-tap performs one action. The helper is compiled locally from included C# source. The plugin itself does not record or upload audio; Windows voice typing processes speech under its own privacy settings.
dsh-duplicate-file-check
jediliu005/dsh-duplicate-file-check
File dedupe and unify toolkit, shown as "小视频整理" in the DSH sidebar: exact matches by head/middle/tail sampling or full byte compare; near-duplicate MP4s found by a prefix frame-level multi-candidate matcher (only the first N seconds, default 40, max 60; a frame-level index plus multiple candidate tracks handle shifted intros and repeated segments). The "ignore intro" scan maintains a SQLite fingerprint cache keyed by absolute path and size, with MAD-first frame lookup and dHash/pHash fallback; incomplete cache rows are removed and rebuilt automatically, and a full scan rebuilds the band index. A "quick file lookup" takes one file, uses the cache when present, generates its fingerprint on demand when missing, and reports a task with live logs, progress and cancellation without rescanning the source folder. Duration-bucket matching always probes and captures fresh, and does not use the fingerprint cache. Batch rename or move by extension, UUID, file size or video length; empty-folder cleanup; MOV/AVI/WMV detected by header and transcoded to MP4 keeping resolution, frame rate and audio. Requires ffmpeg and ffprobe. Scans run in a sidecar worker with live progress, A-B single-direction dedupe and asynchronous fingerprint writes; one task at a time; local-only API. Every task that moves files has one-click restore: per-group/target _dupfc_restore.json records, deleted files skipped and counted, files outside the record renamed to UUID and moved into resetFail.