Passer au contenu principal

Plugins

Parcourez, filtrez et installez des plugins DeepSeek-Harness.

214 plugins trouvés

C

dsh-read-aloud

cccc12138/dsh-read-aloud

Ajoute un bouton haut-parleur juste à droite de Like sur chaque réponse finale. Le clic lance la lecture via la synthèse vocale du navigateur ; le survol ouvre un panneau de vitesse et de voix. Le texte est envoyé à un endpoint Edge TTS non officiel.

1il y a 2 moisVision, voix et multimodalMIT
V

dsh-live-voice

victorwads/dsh-live-voice

Conversations vocales local-first pour DSH, avec reconnaissance et synthèse vocales locales et providers externes facultatifs.

1il y a 2 moisVision, voix et multimodalGPL-3.0
N

dsh-dictate

navneetset/dsh-dictate

Dictée vocale en texte en direct dans le compositeur Web dsh via OpenRouter STT.

1il y a 3 moisVision, voix et multimodalMIT
M

dsh-minimax-asr

moluyao/dsh-minimax-asr

Plugin vocal global MiniMax pour DeepSeek Harness : reconnaissance (`asr-1.0`) et synthèse (`speech-2.8-hd`), outil de transcription, annonce parlée à la fin d’une tâche, conversation mains libres en temps réel et 303 voix au choix.

1il y a 2 moisVision, voix et multimodalMIT
J

dsh-live-voice

jstn-1g/dsh-live-voice

Aperçu vocal d’un tour pour DSH Web avec consentement : démonstration synthétique locale sans identifiants, Qwen Audio facultatif, isolation exacte de Session et transfert explicite de la transcription vers le brouillon, sans envoi automatique.

1il y a 3 moisVision, voix et multimodalMIT
L

dsh-speech-input

liznee/dsh-speech-input

Un bouton microphone pour DeepSeek Harness qui écrit la reconnaissance vocale du navigateur dans le brouillon du compositeur.

1il y a 3 moisVision, voix et multimodalMIT
A

dsh-audio-copilot

ai-yucheng/dsh-audio-copilot

Audio Copilot pour DeepSeek Harness : transcription audio (ASR) et synthèse vocale (TTS) — donne des oreilles et une voix aux agents en texte seul. TTS SAPI local Windows prêt à l'emploi ; points d'accès ASR/TTS compatibles OpenAI configurables. Inclut une entrée vocale dans le compositeur.

1il y a 3 moisVision, voix et multimodalMIT
A

dsh-voice-kit

aaaadrop/dsh-voice-kit

Saisie vocale (Web Speech API) et lecture à voix haute (speechSynthesis) pour l'interface Web de DeepSeek Harness — kit de saisie vocale DSH + lecture des réponses

1il y a 3 moisVision, voix et multimodalMIT
T

dsh-deepseek-pet

txlznbzsdj-collab/dsh-deepseek-pet

Animal de bureau animé baleine bleue DeepSeek flottant sur la page Web DSH : déplaçable avec des bulles et des poses d'humeur, un outil pet_say pour que le modèle le fasse parler, et des états de réflexion et de célébration de début/fin.

1il y a 3 moisJuste pour le plaisirMIT
Z

dsh-voice

zhuiyueya/dsh-voice

Voix pour DeepSeek Harness (dsh) — saisie par reconnaissance vocale + lecture à voix haute (TTS) pour DeepSeek texte seul, sans clé API.

1il y a 3 moisVision, voix et multimodalMIT
A

dsh-voice-webspeech

anweat/dsh-voice-webspeech

Saisie vocale via la Web Speech API du navigateur : zéro serveur, zéro clé, zéro téléchargement de modèle (Edge=Azure, Chrome=Google speech).

1il y a 3 moisVision, voix et multimodalMIT
D

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.

0il y a 24 joursVision, voix et multimodalMIT
G

apipod-dsh-plugin

geniuspath/apipod-dsh-plugin

Seven APIPod tools for the agent: list image, video and speech models, read one model request schema, quote a generation price, read the account balance, and start image or video jobs that are polled to completion; calls that spend balance ask for approval first.

0avant-hierOutils et capacitésApache-2.0
Y

dsh-selection-translate

yyyl99/dsh-selection-translate

Select text in a conversation and click the 译 badge at the bottom-right corner of the selection. A card opens below it with the translation, and for a single word also phonetics, part-of-speech meanings and bilingual examples. The original text can be read aloud. No API key or configuration is needed.

0hierAméliorations UIMIT
I

dsh-onebot-genji

insanegenji/dsh-onebot-genji

Bridges QQ (OneBot 11) into DeepSeek Harness with in-chat tools and rich media, and ships its own speech-to-text bridge so voice messages transcribe without a whisper CLI.

0avant-hierIntégrations et accès distantBSD-3-Clause
C

dsh-jp-vocab

chuuu4536-gh/dsh-jp-vocab

Daily Japanese vocabulary digest: reads the JSONL of words starred with the companion Edge extension and writes a Markdown summary grouped by part of speech, with a configurable day boundary, template and output directory.

0hierOutils et capacitésMIT
O

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.

0il y a 4 joursOutils et capacitésMIT
T

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.

0il y a 6 joursJuste pour le plaisir
Y

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.

0avant-hierOutils et capacités
L

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.

0il y a 7 joursVision, voix et multimodalMIT
V

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.

0il y a 7 joursVision, voix et multimodalMIT
F

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.

0il y a 7 joursVision, voix et multimodalMIT
D

dsh-dafeiyu-voice-chat

dennisyang1986/dsh-dafeiyu-voice-chat

Voice chat inside DeepSeek Harness: a draggable fish launcher records from the microphone, transcribes with DeepSeek speech recognition, answers with deepseek-flash (images included), and speaks each sentence through DeepSeek speech synthesis as the answer streams. Two voices, a continuous-conversation switch, and the API key stays on the Host.

0il y a 6 joursVision, voix et multimodalMIT
B

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.

0il y a 5 joursVision, voix et multimodalMIT