Plugins

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.

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

Local OCR fallback for text-only routes: when the session model declares it cannot accept images, the attached image is cached locally and its path injected so the model can call ocr_image — PP-OCRv5 + ONNX Runtime on CPU, no API key, images never leave the machine. Silent when the model can see images.

Local OCR for DeepSeek Harness: paste/attach an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline. TUI (cc-tui) and Web. / DeepSeek Harness 本地 OCR 插件：图片转文字，PP-OCRv5 + ONNX Runtime，完全离线，支持 TUI 与 Web。

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 assistant for dsh web: say the wake phrase (e.g. "小鲸") to activate hands-free dictation — what you say is transcribed and typed into the chat box automatically. Supports spoken edit commands (send, clear, new line, stop reading) and reads assistant replies aloud in Chinese. Speech recognition runs locally in-browser via sherpa-onnx WASM, so it works offline without an API key.

Image and video production toolkit for DeepSeek Harness - background removal with quality tiers, local inpainting retouch, headline and logo compositing, batch platform-size exports and image QA reports; for video, AI subject matting with background replacement (RVM ONNX, plus a chroma-key path), animated titles with fade/slide/typewriter/karaoke presets, 53 transitions with stylized variants, and light-effect and grading presets with LUT support, alongside footage inventory, accurate cutting, subtitle burn-in, music mixing and platform-spec exports; it provisions its own local Python runtime through a bundled bootstrap script.

Registers one `doc_ocr_sign_fix` tool for DeepSeek Harness: on macOS it diagnoses and repairs the condition where the bundled Python cannot load native extensions (onnxruntime, cv2, pypdfium2) because of the hardened runtime and library validation, by injecting the disable-library-validation entitlement and re-signing the interpreter, then verifying the imports. Operations are idempotent and the original binary is backed up first. It never touches the enclosing application bundle.

Inspects ONNX models (inputs/outputs, shapes, opset, operators, size) and benchmarks them with ONNX Runtime on the local machine or on a remote target over SSH, reporting average/P50/P95/P99 latency, FPS and the execution provider actually used, with PASS/FAIL gates for FPS, P95 latency and model size. Requires Python 3.10+ with numpy, onnx, onnxruntime, and psutil installed (pip install numpy onnx onnxruntime psutil); remote targets need python3, numpy, and onnxruntime.

Registers two tools for DeepSeek Harness. `doc_ocr` turns scanned PDFs and images into structured text (per-page text, financial tables with a balance-sheet tie-out check, contract-clause hits) through a local RapidOCR engine or a Zhipu GLM-OCR cloud engine, and `doc_preprocess` turns a directory of raw files into an Obsidian-ready knowledge base through a seven-stage pipeline with backend routing and sha256-based incremental skipping. Numbers that fail the tie-out are reported, not invented. The local engine needs Python 3 with rapidocr-onnxruntime, pypdfium2 and Pillow (pip install -r requirements.txt); the GLM engine needs ZHIPU_API_KEY.

Local OCR with nothing sent to a cloud: mounts the PP-OCRv6 Medium stdio MCP server (PaddleOCR on ONNX Runtime, CPU) as mcp__ppocr__ocr_image and mcp__ppocr__ocr_pdf for images and multi-page PDFs.

Full-duplex voice mode for DeepSeek Harness 0.2 desktop: streaming ASR to draft, sentence read-aloud, barge-in, live captions, plus an in-app settings page. An unofficial compatibility fork of dsh-voice-mode 0.7.15.

Full-duplex voice mode for DeepSeek Harness: zipformer2 streaming ASR → editable draft, Edge TTS sentence-by-sentence read-aloud with live captions, true barge-in — on-device ASR, no API key. · DSH 语音双工对话：流式识别入草稿、按句朗读+实时字幕、开口即打断，识别本地推理、无需 API Key