Plugins

One-click prompt enhancement (5 modes, memory chain, multi-model fallback) plus voice recognition (cloud Qwen3-ASR / offline SenseVoice, auto-stop on silence) for the composer, with one-click DSH service restart.

Voice input for the web UI: tap Alt (or Alt+Space) to start/stop dictation, browser Web Speech (zero-config) or OpenAI-compatible cloud ASR, optional polish through DSH-configured LLM, settings UI.

Voice input plugin for DeepSeek Harness (dsh): a microphone button in the composer turns speech into a draft transcript, with a choice of speech-recognition backends, optional polish through dsh own LLM routes, and a native settings page.

Full-duplex voice mode for the DeepSeek Harness Web UI: toggle (2s-pause auto-send) or hold-to-talk dictation into an editable draft with zipformer2 streaming ASR, optional wake word; sentence-by-sentence Edge TTS read-aloud with live captions, and speaking interrupts playback and the running turn (true barge-in). On-device ASR, no API key.

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion animation window, and two-way QQ chat (text/voice/image push) via NapCat.

Bilibili video analysis: metadata, transcript (ASR fallback via Bijian/sherpa-onnx/whisper.cpp), comments, danmaku, and sharp keyframes with optional local vision descriptions.

Low-cost video understanding tool: a video_understand tool turns a Bilibili link / BV / local video into an AVIS info layer (ASR + scene structure + object tracks + YOLO labels) and returns summary + Q&A. Question-driven dynamic routing across layers (L0 ASR / L1 object tracks / L2 key-frame VLM), semantic-layer reuse for repeat questions, per-question budget cap. Python engine: core layer needs faster-whisper / opencv / yt-dlp (~200-300MB); the optional semantic layer adds ~2GB of torch / transformers / ultralytics. A bundled doctor --fix sets up the venv and installs both.

Voice tools: free edge-tts neural speech synthesis, OpenAI-compatible ASR transcription, voice list, batch voice preview and health self-check.

Full-duplex voice mode for the Web UI: tap-to-toggle or hold-to-talk dictation (send key or `Ctrl`) with a live caption, host-side SenseVoice ASR via sherpa-onnx, sentence-by-sentence spoken replies, and speaking interrupts playback and the running turn (true barge-in). No API key.

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 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).

Voice call assistant for the DSH Web GUI: a draggable floating call ball, browser-side VAD that sends each utterance after a pause, FunASR HTTP or streaming speech recognition, MiniMax or OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate subagent sessions with progress, stop, and spoken completion reports.

Local-first, full-duplex voice for DeepSeek Harness, orchestrated by Muxiva

Agent-initiated voice calls: `offer_call` rings the human (接听/拒接/稍后再说); accepted calls synthesize and play locally via CrispASR + Qwen3-TTS (9 speakers, 2 Chinese dialects), rejected calls return the decision to the agent.

Local media/doc pipeline: ffprobe, extract, thumbnail, PDF, ASR, pandoc, OCR, exif (allowRoots include IM inbox).

Bridges Feishu, WeCom, DingTalk, QQ, Slack, Discord, Telegram and Mattermost into dsh agents (outbound WS/Stream/Gateway/long-poll/webhook), with im_status, optional local Whisper ASR, plain-text outbound for QQ/DingTalk/Telegram/Mattermost, and env CSV allowlists (DSH_IM_*_ALLOWED_USER_IDS). Empty allowedUserIds means EVERYONE can drive your agent — set a whitelist before exposing a bot.

MiniMax 语音识别（asr-1.0）+ 语音合成（speech-2.8-hd）的 DeepSeek Harness 全局插件：转写工具、任务结束后用喇叭念一句的播报、实时免手对话、303 个音色可选

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

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.

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

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。

DSH voice input plugin: browser realtime + VAD dictation + local/cloud ASR + DeepSeek AI polish

Voice input plugin (dual-face): mic button beside the composer send action, live recording bubble streaming PCM to a local Qwen3-ASR python service managed by the host, plus an ASR environment settings page (clone runtime/model repos, create venv, run ser