by alaxrpg

Adds image input and recognition through configured DSH providers or an OpenAI-compatible endpoint.

Auto-discovery vision bridge for text-only DeepSeek Harness agents: automatically finds an image-capable model from your configured providers and returns picture descriptions as plain text via a visio

Native image attachments for text-only DeepSeek in the Web GUI: pasted or dropped images appear as thumbnails in the session, and before dispatch the host reads them with the free Zhipu GLM-4V-Flash v

Vision understanding + image generation/editing for DeepSeek Harness (read images with Qwen/OpenAI/Anthropic/Gemini, generate and edit with Qwen-Image). A rework of liustack/modlens (MIT). Remove @liu

by nsswkj

Turns a streaming assistant reply into short blips, one per character at a configurable minimum spacing, for the reply text only, and keeps sounding when the window is minimized, covered, or in a back

by Ssrs-Pro-Max

DeepSeek Harness plugin: shows oversized images to the model at readable resolution by tiling them before admission.

by fangqian616

Speaks your agent's reports in a voice you choose, compressing long reports before speaking. Character voices need no training - a 3-10 second reference clip clones one, and community-trained models w

by fotor-ai

Script-free Fotor plugin bundle for DeepSeek Harness, distributed from reviewed source snapshots.

by tangzheng202202

Real-time duplex voice over Volcengine streaming ASR/TTS: agent reply narration, barge-in, wake word, live captions, 30 Chinese voices and a reply-first acknowledgment; builds in the DSH monorepo.

Codex-style generated-image gallery and lightbox for DeepSeek Harness

by NewDaNew

DeepSeek Harness Voice Input Plugin: Adds a microphone button to the Web GUI input box, enabling speech-to-text input via the browser's Web Speech API, with optional auto-send support.

Vision bridge for text-only DeepSeek: send images (alone or mixed with text) and a fast tiny vision model describes them behind the scenes — the chat keeps the picture, DeepSeek sees only text. Pure p

Plays the audio of a Bilibili video from a floating bar in the DSH Web UI, with a queue, seek and speed controls, and a host-side reverse proxy for the CDN Referer check.

Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek m

by Junkrat9527

Vision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys o

by mhlywxl

Generative background music and notification chimes for DeepSeek Harness.

Local WeChat OCR tool for DSH: `wechat_ocr_recognize` returns recognized text and the engine structured result for a local image path.

by whiteS18

Configure multiple image providers in Settings and call image_generate with the one selected model; images save under generate/image and show inline in the conversation.

Adds an Omni-modal settings section to DeepSeek Harness: configure OpenAI-compatible image/video generation endpoints with switchable config profiles, plus generate_image / generate_video / check_video tools.

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

by cccc12138

A speaker button beside the Like button: read any DeepSeek Harness reply aloud with the browser's own speech engine. · Add a small speaker icon next to the Like button to read DSH's replies aloud.

Transparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.

MiMo voice for DeepSeek Harness: auto-read answers aloud, click-to-talk composer mic, voice cloning. Xiaomi MiMo voice plugin.

Configurable image recognition for text-only DSH models: image messages are first transcribed by an OpenAI-compatible vision model (Base URL, model ID and API key set in a Settings section) and then p