Plugins

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。

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.

Voice announcements when a conversation ends (session title, round, outcome) plus live sentence-by-sentence reading of replies, via built-in edge-tts with zero third-party dependencies.

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

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

A Kun-Like desktop pet living in the corner of the DSH web UI; switches animations with agent state and plays a voice line on task completion.

Voice input (Web Speech API) and read-aloud (speechSynthesis) for the DeepSeek Harness web GUI — DSH 语音输入 + 回复朗读套件

Event sounds for DSH: plays a chosen sound on session end, options popup, permission request and stop, with AI-generated character voice lines and a manageable sound library.

Voice for DeepSeek Harness（dsh） — speech-to-text input + read-aloud TTS for text-only DeepSeek, zero API key.

Hosted tool server over MCP: invoice and bank-statement extraction with in-code arithmetic checks, ledger reconciliation in integer cents, PDF and table conversion, SQL dialect transpiling, and mainland-China reachability probes run from a China Mobile network vantage point.

Browser Web Speech API voice input: zero server, zero keys, zero model downloads (Edge=Azure, Chrome=Google speech).

Reads DeepSeek Harness replies aloud with MiniMax voices, with a per-message speaker button, optional auto-read and barge-in when you send a new message.

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.

Hold right-Cmd and talk — local SenseVoice STT, a fixed DSH session with voice-triggered rotation, and streaming CosyVoice2 TTS with emotion voices and an optional Live2D overlay.

Subor-style CRT boot animation for DeepSeek Harness: the tube powers on, the pixel logo drops in with a "DeepSeek, endless fun" voice line, then 108 classic FC game windows fill the screen along a snake-like inward spiral, ending in a white flash that fades into the app. Auto-plays, skippable, zero configuration.

Sidebar badge showing the current DeepSeek peak/off-peak billing phase, the countdown to the next switch, the account balance and a 7-day CNY spend chart — with a voice alarm when off-peak starts.

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.

Surfaces the questions a model almost asks but never voices — bubbles above the whale widget pick them up from the reasoning stream in real time, and you can answer one in place so it is folded into the next step without interrupting the run. Supports a prompt-marker protocol that lets the model mark its own doubts, five languages, DSH light and dark themes, and depends on dsh-whale-widget for placement.

Continuous voice conversation for DSH: auto sentence splitting, a 2-second confirm window before sending, and spoken replies you can interrupt by speaking. Speech is recognised by DSH's own speech service by default (a local Whisper bridge or an OpenAI-compatible endpoint can be set instead), the recognised text is corrected by a DSH model call, and replies are read aloud through Microsoft Edge's online text-to-speech service, so reply text is sent to Microsoft. A daily check of PyPI and Hugging Face for faster-whisper updates is on by default; settings and any API keys are stored in plain text in ~/.dsh/voice-tutor-config.json. Its /voice-tutor routes require an authenticated DSH session (admission is checked per request), API keys are never returned, and applying an update needs a one-time confirmation token.

Offline voice input for the composer: records with the microphone, transcribes locally with SenseVoice, and sends the message automatically. A derivative of the official voice-input plugin that adds auto-submit; first use downloads the SenseVoice model (about 242 MB) to ~/.dsh/speech-to-text/sensevoice, and it registers the same speech provider rows as the built-in Voice Input, so disable that one first.

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.

Composer mic button that transcribes speech locally with SenseVoice, then tidies the spoken transcript into clean text with your configured DeepSeek route before inserting it into the draft.