Plugins

Offline voice input for the DSH Web UI: mic to local FunASR (SenseVoiceSmall), one-click install, no cloud.

基于 SenseVoiceSmall（iic/SenseVoiceSmall）多语言语音理解模型的 DSH Desktop 本地语音输入插件。

Parse Chinese e-invoice PDFs (XML attachment first, text-layer regex fallback) into structured JSON with amount cross-check, and generate expense reports (Markdown / xlsx).

语音输入插件 for Deepseek Harness

Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.

Screen-reader guidance and in-app accessibility diagnostics for DeepSeek Harness

Entrada de voz pronta para a China para o compositor. Requer uma ponte local em Python (pip install dashscope websockets, executar bridge/voice-bridge.py) — o plugin sozinho não funciona. O microfone do navegador transmite PCM de 16 kHz à ponte, que executa o Alibaba Cloud DashScope ASR (paraformer-realtime-v2); o texto intermediário preenche o rascunho no cursor, parada automática por silêncio, envio automático opcional.

Audio Copilot for DeepSeek Harness: transcribe audio (ASR) and synthesize speech (TTS) — gives text-only agents ears and a voice. Windows-local SAPI TTS out of the box; OpenAI-compatible ASR/TTS endpoints configurable. Includes an in-composer voice-input

Um bichinho de mesa estilo Kun que vive no canto da interface web do DSH; alterna as animações conforme o estado do agente e reproduz uma fala de voz na conclusão da tarefa.

Entrada de voz (Web Speech API) e leitura em voz alta (speechSynthesis) para a interface web do DeepSeek Harness — kit de entrada de voz + leitura de respostas para o DSH.

Sons de eventos para o DSH: toca um som escolhido ao fim da sessão, ao abrir opções, em pedido de permissão e ao parar, com falas de personagem geradas por IA e uma biblioteca de sons gerenciável.

Voz para o DeepSeek Harness (dsh) — entrada por fala para texto + leitura em voz alta via TTS para o DeepSeek somente de texto, sem necessidade de chave de API

Servidor de ferramentas hospedado via MCP: extração de faturas e extratos bancários com verificações aritméticas no código, conciliação de livro-razão em centavos inteiros, conversão de PDF e tabelas, transpilação de dialetos SQL e sondas de alcance da China continental a partir do ponto de vista da rede da China Mobile.

Entrada de voz via Web Speech API do navegador: sem servidor, sem chaves, sem downloads de modelo (Edge=Azure, Chrome=Google speech)

这是dsh的插件，语音发送弹幕。在玩游戏时通过语音输入在b站发弹幕，不切出游戏可以正常操作

Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weaving 35 DSH Web endpoints into 16 voice-friendly tools for workspaces, sessions, chat, models, settings and files — outbound WebSocket to the Xiaozhi MCP access point by default (no public IP or port forwarding needed), several devices bound at once, plus a DSH settings page with live status.

Speaker button beside the composer microphone — one click scrolls to the start of your newest question, marks it with a blinking caret and reads from there through the newest agent reply (dsh-tts, browser voice as fallback); press-and-drag-right picks any other reading start position on the page, press-and-drag-up opens a vertical mixer for in-page media volume and system output volume.

Speaks a short status line when DSH changes state — turn done, turn error, job done, job failed, goal complete, goal blocked, an approval waiting, or the agent needs your answer — using eight pre-recorded clips in Chinese (default) and English. The audio is played by the host process through ffplay, or through the Windows PowerShell player that ships with the OS, so it does not depend on a Web Audio tab. Windows only.

Speaks your agent's reports in a voice you choose, compressing long reports before speaking. Character voices need no training - a 3-10 second reference clip clones one, and community-trained models work too - and no 6.4 GB GPT-SoVITS install: the plugin installs its own runtime and voice. An existing GPT-SoVITS can be used instead, and it is the same voice model.

Adds a speaker button immediately right of the Like button on every finalized assistant reply; click it to hear the reply through the browser speech engine, and hover it for a speed and voice panel.

Speaks or plays a sound at the end of every turn and plays a failure cue when a tool call or a turn errors. Ships 20 built-in effects (10 alert chimes + 10 nature sounds) and defaults to effect mode, so it needs no API key and no audio files; an optional Volcengine voice-clone route generates the three announcement clips in one click. Plays through winmm/waveOut as-is, never changing the system volume or mute state. Windows only.

A speech-to-text (voice input) plugin for DeepSeek Harness.

开口即成文 · Speak-to-prompt for DeepSeek Harness：云端 ASR 语音识别 + 提示词优化 + 填入草稿/自动发送，跨平台 macOS / Windows。