Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
171 plugin trovati
dsh-cloudflare-media
dmscode/dsh-cloudflare-media
Strumenti media Cloudflare Workers AI per dsh: text-to-image, text-to-speech e speech-to-text. Badge di prezzo per modello, scheda impostazioni nativa, riuso di un account Cloudflare esistente e file di output nominati in base al modello che li ha generati.
dsh-live2d-voice
john-walks-slow/dsh-live2d-voice
Vista sessione Live2D con voce in tempo reale: input vocale continuo, TTS in streaming, traduzione sottotitoli, catalogo multimodello e accesso indipendente.
dsh-say
fangqian616/dsh-say
Legge i report dell’agente con la voce scelta e comprime quelli lunghi prima di parlare. Bastano 3–10 secondi di riferimento per clonare una voce; funzionano anche modelli addestrati dalla community. Non serve installare GPT-SoVITS da 6,4 GB: il plugin installa runtime e voce propri. Si può usare un GPT-SoVITS esistente, con lo stesso modello vocale.
dsh-read-aloud
cccc12138/dsh-read-aloud
Aggiunge un pulsante altoparlante subito a destra di Like in ogni risposta completata. Al clic, legge tramite il motore vocale del browser; al passaggio del mouse apre un pannello per velocità e voce. Il testo viene inviato a un endpoint Edge TTS non ufficiale.
dsh-live-voice
victorwads/dsh-live-voice
Conversazioni vocali local-first per DSH, con riconoscimento e sintesi vocale locali e provider esterni facoltativi.
dsh-minimax-asr
moluyao/dsh-minimax-asr
Plugin vocale MiniMax globale per DeepSeek Harness: riconoscimento (`asr-1.0`) e sintesi (`speech-2.8-hd`), strumento di trascrizione, annuncio vocale a fine attività, conversazione hands-free in tempo reale e 303 voci selezionabili.
dsh-tts-flash
2021heei/dsh-tts-flash
Legge ad alta voce le risposte AI mentre arrivano e pronuncia frasi di attesa mentre il modello elabora. Include Edge TTS e supporta qualsiasi motore cloud compatibile con OpenAI.
dsh-voice-announcer
flashyiyi/dsh-voice-announcer
Annunci vocali alla fine della conversazione (titolo, turno, esito) e lettura in tempo reale delle risposte frase per frase. Usa edge-tts integrato, senza dipendenze di terze parti.
dsh-audio-copilot
ai-yucheng/dsh-audio-copilot
Audio Copilot per DeepSeek Harness: trascrivi audio (ASR) e sintetizza voce (TTS) — dà orecchie e voce agli agenti solo testo. TTS SAPI locale Windows pronto all'uso; endpoint ASR/TTS compatibili OpenAI configurabili. Include un input vocale nel composer
dsh-voice
zhuiyueya/dsh-voice
Voce per DeepSeek Harness (dsh) — input speech-to-text + lettura ad alta voce TTS per DeepSeek solo testo, senza chiave API
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.
everwith
istarrydust/everwith
Gives a chat persona a persistent inner state: 40 emotions with half-lives, nine drives, and memories that fade over days, re-rendered into the system prompt every turn. Replies can be split across several messages, spoken through DeepSeek TTS or Xiaomi MiMo, dictated by local speech recognition, and a background timer can glance at the screen. Exposes 4 tools. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
dsh-audio-reactive
ppy-web/dsh-audio-reactive
Audio-reactive visual background theme powered by audioMotion-analyzer for DSH Web and Desktop, driven by streaming TTS, dsh-music-panel, voice dictation, microphone, browser audio sharing, or Windows loopback capture, with 17 presets, custom preset import/export, and an idle immersive overlay. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.
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-yukkuli
odo-tech/dsh-yukkuli
Yukkuri voice for DeepSeek Harness: reads assistant replies aloud locally through AquesTalk, with no network calls.
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-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-ai-fastvideo
veillessrose/dsh-ai-fastvideo
Text-driven video generator for DSH: writes one Canvas page per scene from 341 bundled style prompts, renders frames with a headless browser, then adds TTS narration, music and sound effects with ffmpeg.
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_PlainRiceWhale (whale-aside)
zjdqtjs/dsh_plainricewhale
Whale-girl persona for DeepSeek Harness: a `whale_aside` tool turns one short inner monologue per new task into a chat bubble, with an optional mood sticker and Edge TTS voice line.
dsh-plugin-voice-alert
venompool888/dsh-plugin-voice-alert
Spoken alerts on macOS that name the source and project: announces approval requests automatically and adds a voice-alert skill the agent uses for verification codes, finished long tasks or when it is stuck. DeepSeek TTS via an API key (DeepSeek official, a third-party base URL, or the key already set in DSH Models), tested before saving and falling back to the macOS system voice; speaks only after 30 seconds without keyboard or mouse input and repeats until you return, with AI-written lines in a chosen tone (professional, tsundere, cute, clingy, cold or custom); a Settings → Voice page with instant previews, speech speed, 10 spoken languages and an away mode.
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-video-narrator
t1897/dsh-video-narrator
Turns a video, article, PDF, or text into a narrated video, with an in-app workbench for settings and project history, per-scene images, TTS, metadata, and ordered API fallback.