Pular para o conteúdo principal

Plugins

Navegue, filtre e instale plugins do DeepSeek-Harness.

211 plugins encontrados

F

deepseek-moonpet

femad-6/deepseek-moonpet

MoonPet (月伴), mascote de status e temporizador Pomodoro para DeepSeek Harness: expressões ligadas ao estado, registro do tempo de trabalho, legendas multilíngues e lembretes de descanso.

2há 25 diasMelhorias de UIMIT
N

dsh-gptsovits-tts

nuoyi207/dsh-gptsovits-tts

Conversão local de texto em fala com GPT-SoVITS para DSH: lê respostas em voz alta, permite trocar vozes pela barra lateral direita e treinar uma nova a partir de uma amostra de áudio. Na primeira execução baixa um mecanismo de 11,4 GB e exige GPU NVIDIA CUDA.

2há 27 diasVisão, voz e multimodal
F

dsh-voice-doubao

fyzb2020/dsh-voice-doubao

Adiciona dois reconhecedores de fala na nuvem Volcengine Doubao ao seletor de entrada de voz do DeepSeek Harness, com reescrita opcional da transcrição por um LLM.

2mês passadoVisão, voz e multimodal
T

dsh-stt

try-works/dsh-stt

Transcrição de voz local com vários modelos para o compositor DSH Web: o utilizador escolhe Whistle ou Voz e cada modelo é descarregado quando necessário. Distribuído como bundle DSH.

2mês passadoVisão, voz e multimodal
W

dsh-multi-tts

wyr-233/dsh-multi-tts

Lê cada resposta em voz alta com página de configurações para vários provedores: MiniMax ou qualquer endpoint `/audio/speech` compatível com OpenAI, seleção de voz, emoção, velocidade e modelo, além de opção de leitura automática.

2mês passadoVisão, voz e multimodal
L

dsh-voice-alert

loyalchiiina/dsh-voice-alert

Toca voz/som ao concluir um turno e alerta de falha quando chamada de ferramenta ou turno dá erro; abortos do usuário ficam silenciosos e sessões subagent são ignoradas por padrão. Três modos: voice (Volcengine TTS com voz clonada ou predefinida e reutilização de fingerprint para não sintetizar texto inalterado), effects (20 sons atribuíveis a done/fail/approval, prévia por linha, sem API key; approval não dispara automaticamente, só manualmente) e off. Usa winmm sem alterar volume do sistema. Só Windows; DSH kernel 0.2.2-rc.1.

2há 5 diasVisão, voz e multimodalMIT
D

dsh-voice-talk

duoduoqian708/dsh-voice-talk

Modo de conversa por voz na GUI Web do DSH: toque no microfone para iniciar uma chamada em tela cheia, fale sem usar as mãos e ouça cada resposta enquanto é gerada. UI em chinês/inglês, temas claro/escuro, velocidade ajustável e vozes selecionáveis.

2há 2 mesesVisão, voz e multimodalMIT
M

dsh-fish-tts

mari23333/dsh-fish-tts

Lê em voz alta as respostas do assistente apenas via a API Fish Audio (traga sua própria chave): leitura por mensagem, alternância de leitura automática e uma página de configurações para modelo, reference_id da voz, chave de API criptografada e proxy.

2há 15 diasVisão, voz e multimodalMIT
L

dsh-whale-live

lh1314-china/dsh-whale-live

Left-sidebar live console for DeepSeek Harness: stream log, Bilibili danmaku, edge-tts speech, optional VTube Studio/OBS/livehime helpers and a memory inbox. Windows only.

1há 7 diasVisão, voz e multimodalMIT
C

dsh-bibibobo

cxv117793-blip/dsh-bibibobo

Speaks DSH replies aloud with the bibibobo synthesizer: one sawtooth wave and two band-pass filters, no samples and no TTS model. The control sits in the answer's own action row beside Copy, with a progress bar and a scrolling subtitle while it plays. Each turn keeps its own control, but it reads only that turn's closing reply, so a multi-step answer never restarts mid-sentence and intermediate steps get no control. Deterministic by design: a character always yields the same pitch and mouth shape. Markdown is stripped before speaking, replies are capped at 1200 characters, and playback can be paused, resumed or stopped. Zero dependencies, MIT, no network access.

1há 4 diasVisão, voz e multimodal
P

dsh-voice

phoenixym0307/dsh-voice

Adds a mic button to the chat composer that turns speech into text in the input box, and optionally reads each assistant reply aloud. Speech recognition and synthesis call DeepSeek's official ASR and TTS endpoints, with the API key entered in the plugin settings page. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

1há 6 diasVisão, voz e multimodalMIT
2

dsh-go-fish-panel

27synthesis/dsh-go-fish-panel

Native panel for the dsh-fish companion on DSH Go: one observatory page showing what she has been up to, plus rhythm, browsing, and speech-and-memory settings pages that write 57 config keys in place.

1há 8 diasMelhorias de UIMIT
T

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.

1há 6 diasVisão, voz e multimodalMIT
C

dsh-live-speak

chaowei08/dsh-live-speak

Reads assistant replies aloud while they stream: sentence-by-sentence speech with highlighted lines in a sidebar player, pause, mute and stop controls, and automatic quieting for code blocks. The speech engine is switchable: Edge TTS online by default, or the operating system local voices. Its HTTP routes do not verify the caller, so any program that can reach the local DSH port can call them.

1há 8 diasVisão, voz e multimodal
R

dsh-breeze-speak

rirtue/dsh-breeze-speak

Reads each reply aloud through the BreezeBlue / Breeze TTS 2 API. Synthesis starts as soon as the reply first sentence is complete rather than after the whole reply, and the audio is streamed as raw PCM into Web Audio so it plays continuously while it arrives. Needs a BreezeBlue API key, entered on the settings page or via BREEZE_API_KEY; a key saved on the settings page is stored as plain text in ~/.dsh/breeze-speak.json. By default only the first sentence of each reply (up to 120 characters) is spoken, and that text is sent to api.breeze.blue. The default voice is just an example, so pick one available to your account on the settings page.

1há 10 diasVisão, voz e multimodalMIT
O

dsh-gigaam-stt

oldschool686/dsh-gigaam-stt

Local Russian speech-to-text for DeepSeek Harness voice input: GigaAM v3 (ONNX int8) on CPU via sherpa-onnx

1há 27 diasVisão, voz e multimodalMIT
S

dsh-minimax-voice

sunshine334419520/dsh-minimax-voice

MiniMax voice studio for DeepSeek Harness: clone a voice from an audio sample, preview it from the audio returned by the clone request itself (no extra synthesis call, so the per-voice fee stays uncharged), synthesize text to local mp3 files, transcribe audio to text with asr-1.0, and manage the voice library, API key and these actions from a settings panel; four agent tools and a local HTTP API.

1há 14 diasVisão, voz e multimodalMIT
R

pocket-harness (pocket-harness)

regrevia/pocket-harness

Pocket Harness: the phone side of DSH. Continue the same DSH session from your phone, with the same history, projects, goal, queue and pending questions, connected over your LAN, your own domain or a relay you run (no author-run server, no account). Needs the Android companion app (APK from the repo's releases) paired by QR code; an optional pixel-whale desktop pet can talk and listen, and neural voice and local speech recognition are optional extras. Formerly dsh-pet-voice.

1há 13 diasVisão, voz e multimodalMIT
H

dsh-shortvideo-export

hangyesite/dsh-shortvideo-export

Download watermark-free Douyin and Xiaohongshu videos, transcribe them with local or cloud speech recognition, proofread the text against a term list, and export Markdown, DOCX, SRT, VTT and other formats from a settings panel or agent tools. Needs Python 3.10+ with pip packages (playwright, python-docx, numpy, and sherpa-onnx for the default local SenseVoice engine, which also downloads a ~228 MB model on first use), ffmpeg on PATH, and Chrome or Edge.

1há 11 diasVisão, voz e multimodalMIT
F

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.

1há 21 horasFluxos e automação
R

ai-voice

root-7-khx/ai-voice

A local AI voice studio for DeepSeek Harness with nine local TTS engines for voice design, voice cloning, emotional performance, a reference-audio library and audio export. It only registers /ai-voice/api routes; the UI lives in the companion-memory plugin's integrations page, and every engine needs its own Python virtualenv and downloaded model weights, which are not bundled.

1há 13 diasVisão, voz e multimodalMIT
I

dsh-live2d-stage

ikunua/dsh-live2d-stage

Renders a Live2D Cubism 4 model as the DSH web UI background: a transparent click-through canvas that covers the window without blocking any control. Eyes, head and body follow the pointer; expressions track the agent state (thinking, running a tool, turn finished, error, waiting) and the conversation (message arrives, reply ends, question asked); after an idle delay the character shows speech bubbles and plays motions and expressions drawn at random from pools you tick. Settings list the models under ~/.dsh/live2d-stage/models, expose position, scale, opacity, gaze strength and every interval and probability, and open a resizable live preview of the same canvas. Expressions and motions a model3.json omits are detected from the model folder; one sample model is included.

1há 14 diasTemas e aparência
C

dsh-jianxian-widget (plugin)

cococo1ng/dsh-jianxian-widget

Qingyun Jianxian (青云剑仙, Azure Cloud Sword Immortal) — a resident bottom-right widget for the DeepSeek Harness Web UI: a sword-cultivator character that reads your account balance and token spend, keeps a local ledger broken down by model, and has 10 switchable sound effects. Reminders cover low balance, a model waiting on your answer, a pending approval, and staying up too late. Ships 23 idle poses plus a 24-frame sword dance, 22 menu-icon skins, six panel tabs, a line-by-line speech-bubble editor, and black or white robes that follow the light or dark theme. Runs entirely locally and registers no agent tools.

1há 14 horasMelhorias de UI
2

dsh-go-local-voice

27synthesis/dsh-go-local-voice

Conversão de texto em fala para a interface móvel nativa do dsh-go: pressione e segure uma resposta do assistente para ouvi-la via Xiaomi MiMo TTS ou ByteDance Doubao Seed TTS. Após cada turno, a resposta é dividida e sintetizada em segundo plano, então um toque reproduz um único MP3 contínuo. Um lease estável permite parar; faixa de status e barra de progresso mostram o andamento, e o áudio pode ser exportado para o telefone. As chaves ficam no dispositivo com permissão 0600, nunca são exibidas, enviadas em commit ou encaminhadas ao modelo.

1há 16 diasVisão, voz e multimodalMIT