비전, 음성 및 멀티모달

텍스트 전용 모델을 위한 비전 브리지: 이미지를 붙여넣으면 구조화된 JSON 증거(OCR, 레이아웃, 의미 분석)를 반환합니다.

텍스트 전용 에이전트를 위한 무료 비전 기능: 키 없이 사용 가능한 내장 비전 체인과 픽셀 도구(Q&A, 그라운딩, 자르기, 픽셀 비교, 색상, OCR, SVG 트레이스, 컷아웃, 스크린샷)를 제공하며, 이미지를 붙여넣기만 하면 됩니다.

텍스트 전용 모델을 위한 비전 작업 모음: 의도 인식 이미지 Q&A, 긴 스크린샷 OCR, UI 재현, 그라운딩, 픽셀 비교를 제공합니다.

Image "reading" for text-only models: downscale + reduce color depth + structure/color fingerprints into text grids fed back to the conversation, letting the model zoom, sample and OCR autonomously like a multimodal model; fully local with zero external model dependency, ships an image-reading methodology skill and optional PaddleOCR.

DeepSeek Harness용 외부 비전 플러그인: 고래 버튼 설정 패널, 자동 답변이 포함된 이미지 인식, 에이전트 스크린샷/인식 도구를 제공합니다.

Free vision bridge and image generation for text-only models: paste-image reading, GLM-4V-Flash and Gemini engine failover, ModLens-style structured evidence, and a seeded free vision model route.

DeepSeek 두뇌 + 자동 이미지 텍스트 변환: GUI에서 이미지를 첨부하면 텍스트 전용 DeepSeek에 전달되기 전에 OpenAI 호환 VLM이 각 이미지를 텍스트로 변환합니다 — 자체 키를 사용하는 키 기반 고속 경로(기본값 qwen3.7-flash; DashScope/Zhipu/OpenRouter 또는 OpenAI 호환 엔드포인트라면 모두 가능)나, 설정 없이 자동 감지되는 로컬 Ollama를 사용할 수 있습니다.

Adds a configurable vision model to text-only main models: a vision_read_image tool, a composer-bar vision-model selector, and automatic image-to-text conversion for text-only routes.

dsh-visual-plugin: 텍스트 전용 모델에 눈을 달아줍니다. 사용자 이미지를 OpenAI 호환 비전 모델로 전달하고 결과를 Web UI 우측 패널에서 확인할 수 있습니다.

MCP bridge to gemini.google.com: vision analysis of images and videos, Imagen image and Veo video generation, and conversation management using the logged-in browser session with no API key.

Reads assistant replies aloud via free Edge TTS or your own RVC voice models: read-aloud buttons + auto-read, adaptive chunked progressive playback (gapless long reads), one-click voice-pack installs from a registry, and a portable RVC runtime.

AI image generation for the DSH Web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / gpt-image-1 / dall-e-3), with an api_url/api_key settings card and a sidebar split-pane generation studio.

Automatically generates and displays images in the DSH chat via API channels or local CLIs (supports mmx / codex / agy).

Vision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.

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.

A vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.

Local OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Voice input for DeepSeek Harness: speak into the microphone and the recognized text is submitted as a normal chat message, via local or browser speech recognition.

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

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.

AI가 VLM(멀티모달 모델)을 자동으로 호출해 시각 분석을 수행할 수 있게 해주는 dsh 플러그인입니다.

Voice-announce the final reply on Windows (SAPI5 natural voices) and macOS (system voice); skips reasoning and tool calls, one-line npm install.

Advertise image paste on text-only DeepSeek routes, describe attachments with a vision sidecar, and leave native vision models untouched.

Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.