by MicroHEROX

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle manag

by tenglongbohai

DSH plugin: Add PaddleOCR vision capability to Agnes-2.5-Flash free model

by 2021Heei

Voice-reading plugin for DeepSeek Harness: streams TTS narration of AI replies, and provides fun voice phrases during thinking and waiting periods. Edge TTS is ready out of the box, and supports any OpenAI-compatible cloud-based engine.

Speaker button beside the composer microphone — one click reads the newest agent reply aloud through dsh-tts (browser voice as fallback), the next click stops, and a press-then-drag-up opens a vertica

Browser Web Speech API voice input: zero server, zero keys, zero model downloads (Edge=Azure, Chrome=Google speech).

by br1nosense

Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can ci

Local Windows 11 OneOCR tool for DSH: `oneocr_recognize` returns OCR text and structured line/word polygons, confidence, rotation, and handwriting style.

by toddpan

Connect the Xiaozhi (Xiaozhi.me) voice assistant to DSH Web: DSH acts as the MCP tool provider, wrapping 35 DSH Web endpoints into 16 voice-friendly tools, complete with a built-in DSH Web settings page. · Connect the Xiaozhi voice assistant to DSH Web as an MCP tool provider: 35 DSH Web endpoints woven into

by vitas

Local OCR for DeepSeek Harness: Apple Vision on macOS, no install, no network, no capability claims

by ShaineDemo

Vision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.

Removes the model-capability gate that blocks image prompts: patches llm.resolveModelInfo results and adapter model tables to declare image input, so routes with no declared input modality can send an

by SuCriss

Voice control for DeepSeek Harness web: speech-to-text into the composer and spoken playback of assistant replies, zero dependencies

Meeting notes for dsh: one meeting per conversation, transcribed and speaker-separated on the machine itself, with points, assignments, handwritten notes, reviews and monthly scores in the same panel.

Transparent multimodal routing for text-only models: every image in every model call is fully transcribed (verbatim OCR, data, uncertainty zones, injection-hardened) by your own multimodal understande

Control the logged-in web version of ChatGPT to generate images and download them locally — DSH bundle plugin.

Lets the model actually see a video: local ffmpeg samples timestamped stills and faster-whisper transcribes the audio track, so the agent reads real pixels frame by frame instead of trusting a text su

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

Cloudflare Workers AI media tools for dsh - text-to-image, text-to-speech and speech-to-text. Per-model price badges, a native settings card, reuse of an existing Cloudflare account, and output files

by Elohia

Image-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).

Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; syst

by AndyYang12345

A hotkey binder plugin for dsh, allows user to bind specific keys to trigger dictation.

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

Local offline prosody analysis for DeepSeek Harness: reports how something was said — speed, pitch, pauses, energy — alongside the transcript.