Plugins

Rewrites a composer draft into a clearer, structured prompt (5 modes, model fallback chain, optional multi-round memory) and adds stop-on-silence, hotkey and filler-word cleanup to DSH voice input; transcription stays with the official speechToText, the plugin ships no engine.

Voice input for the DSH web UI: tap or hold Alt to dictate into the composer. Local SenseVoice ASR by default — offline, zero config, zero key; auto-fallback to browser Web Speech, optional OpenAI-compatible ASR chain, polish through DSH-configured models, settings UI.

Replaces the chat composer with an editor-style input panel on CodeMirror 6: line numbers, edit + markdown-preview split, a floating window mode and a full-height sidebar tab — one input surface at a time. Drafts ride the official input machine; the official voice-input button is rendered when the host provides one, and the stats row and context meter read the same data as the official dock.

Composer mic for the Web UI: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.

Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language switching, and optional auto-send, zero dependencies.

MiniMax-powered multimodal plugin: real-time voice call mode (streaming conversation, floating dock UI), voice mode and mic voice input, plus image/video/music/speech generation and vision inspection tools.

Hold-to-talk dictation in the composer that ships no recognizer of its own and reuses the speech service the official voice-input bundle already mounts - long-press the input box with mouse or touch, release to write the transcript into the draft, slide up to cancel, and it never sends.

One-handed, keyboard-free input for the composer: press and hold the mouse on the input box, speak, release — the text lands in the draft, and sliding up cancels without leaving a half sentence behind. No mic button to aim at and no shortcut to remember; the hand never has to leave the input area, which is the point when the other hand is busy. Recognition runs fully offline (SenseVoice via sherpa-onnx, no API key, audio never leaves the machine).

Voice call assistant for the DSH desktop app and the Web GUI (the same plugin, only the profile name differs): a draggable floating call ball, browser-side VAD that sends each utterance after a pause, speech recognition through the local SenseVoice model already downloaded by the official voice-input plugin (no second model), FunASR HTTP or streaming, or a cloud-compatible API, MiniMax / MiMo-V2.5-TTS (director mode and voice clone) / OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate sessions with progress, stop, and spoken completion reports.

Voice input for the Web UI: a mic button that drives local VocoType offline speech recognition and auto-inserts recognized text into the composer (auto-deploy, dedupe, continuous dictation).

Microphone voice input for the composer: browser Web Speech API live transcription, dedupe/auto-continue, smart punctuation, language and auto-send settings.

China-ready voice input for the composer. Requires a local Python bridge (pip install dashscope websockets, run bridge/voice-bridge.py) — the plugin alone does not work. Browser mic streams 16 kHz PCM to the bridge, which runs Alibaba Cloud DashScope ASR (paraformer-realtime-v2); interim text fills the draft at the cursor, silence auto-stop, optional auto-send.

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

Adds two Volcengine Doubao cloud speech recognizers to the DeepSeek Harness voice-input picker, optionally rewriting the transcript with an LLM.

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

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

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.

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.

Super input suite — model and effort picker, prompt enhancer, follow-up suggestion chips, a full cost engine with daily heatmap and Coding Plan quotas, voice-input light effects and transcript cleanup (needs the built-in voice-input bundle enabled), prompt templates, selection reference chips with comments, a compaction ring and a settings hub. Bundles the author's standalone dsh-cost, dsh-power-picker, dsh-prompt-enhancer, dsh-followup, dsh-siri-voice and dsh-compaction-control; uninstall those before installing.

Voice dictation scratchpad: realtime speech-to-text into timestamped, per-session blocks, with one-click insert into the conversation composer. Requires the official DSH voice-input bundle (@deepseek-ai/dsh-experimental-voice-input-bundle); the speech model downloads on first use.

Hold Space to record and release to transcribe and send, without focusing the composer first. Esc cancels and window blur auto-cancels. Requires the official voice-input bundle (`@deepseek-ai/dsh-experimental-voice-input-bundle`) enabled with its speech model downloaded; otherwise Space is left alone.

Local video understanding for agents: extracts keyframes adaptively based on motion and pauses, inspects any timestamp at full resolution, and aligns visuals with dialogue from embedded subtitles or configured ASR. Requires ffmpeg and ffprobe; clips without subtitles also need a transcription engine for dialogue (a ~190 MB local whisper model, a cloud API key, or the official voice-input model).