Skip to main content

Vision, Voice & Multimodal

Vision, Voice & Multimodal plugins give the text-only DeepSeek models in DeepSeek-Harness (dsh) eyes, ears, and a voice. Find vision tools and provider routes that OCR and describe pasted screenshots via Zhipu GLM, Gemini, Doubao, or local Ollama, microphone voice input via the browser Web Speech API or Whisper-compatible APIs, read-aloud TTS with Edge TTS or custom voices, full-duplex voice modes, and generators for images, video, and music.

610 plugins found

D

dsh-video-storyboard-hp

dsh-raising-plan/dsh-video-storyboard-hp

High-performance fork of SAOS-3624/dsh-video-storyboard — install this or the upstream plugin, not both. Turns a video into addressable storyboard grids (numbered cells, a timestamp and transcript line per cell, audio envelope); needs Node 20+, ffmpeg/ffprobe on PATH, and a configured ASR endpoint when the file has no subtitle track.

825 days agoVision, Voice & MultimodalMIT
W

dsh-comfyui-image

wbb316/dsh-comfyui-image

Image generation through a local ComfyUI server: one generate_image tool covering text2img, img2img, inpaint and background removal.

82 months agoVision, Voice & MultimodalMIT
H

dsh-omni-workstation

huashenglian/dsh-omni-workstation

Omni-modal workstation for DSH: analyze_image over an ordered multi-card VLM failover chain, a six-tool vision toolkit (zoom, colour sampling, pixel diff, OCR, element detection, inline display) sharing the same image resolver, generate_image over OpenAI/DashScope/ComfyUI protocols, multi-card async generate_video with a /build-video-tool builder, and speak/clone_voice TTS over seven providers, all driven by one auto-saving settings page.

821 days agoVision, Voice & MultimodalMIT
W

dsh-appshots

wongyuye/dsh-appshots

Codex-style window capture for DSH Desktop on macOS and Windows: press both Command keys (macOS) or both Ctrl keys (Windows), or the camera button, to grab the frontmost window, attach it to the current chat, and inject a VoiceOver-style accessibility tree as hidden context.

82 months agoVision, Voice & MultimodalMIT
A

dsh-highres-vision

azwosile/dsh-highres-vision

For the DeepSeek Harness native vision model deepseek-v4-flash-vision-exp, raises image admission limits to 32 MiB / 8192 px / 600 images and adds a highres_read tool that tiles large images, then returns the whole image plus 800x800 tiles through the host read_image tool.

82 months agoVision, Voice & MultimodalMIT
A

dsh-pdf-reader

angeloszou/dsh-pdf-reader

A content-aware PDF reading plugin for vision models: profiles each page for figures (vector and raster), tables, formula risk and double-column layout, then applies content-aware hybrid extraction, rendering figure/table/formula pages as high-DPI region crops. Provides a low-resolution preview to understand the page layout, and renders a specified region at high resolution. Packaged as multiple tools for agents.

83 months agoVision, Voice & MultimodalMIT
3

dsh-voice

3274375092/dsh-voice

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.

82 months agoVision, Voice & MultimodalMIT
F

dsh-free-vision

fuzzysoul/dsh-free-vision

Free vision bridge for text-only models: image understanding, OCR, UI and debug analysis via free-tier providers (Qwen3-VL-Flash, Doubao, DeepSeek-OCR) with a settings GUI.

83 months agoVision, Voice & MultimodalMIT
C

dsh-chat-imagine

corrinehu/dsh-chat-imagine

Automatically generates and displays images in the DSH chat via API channels or local CLIs (mmx / codex / agy), and can also recognize images using the corresponding CLI.

83 months agoVision, Voice & MultimodalMIT
5

dsh-vision

54xkeee/dsh-vision

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.

83 months agoVision, Voice & MultimodalMIT
S

dsh-tool-vision

scorp1o117/dsh-tool-vision

Send local images or HTTP(S) image URLs to a configured OpenAI-compatible vision endpoint with the inspect_image tool and return its text response to the conversation.

88 days agoVision, Voice & Multimodal
L

dsh-vision

linenxi-ctrl/dsh-vision

External vision plugin for DeepSeek Harness: whale-button config panel, image recognition with auto-reply, and agent screenshot/recognize tools.

83 months agoVision, Voice & MultimodalMIT
O

dsh-xiaoai-bridge

omsociety/dsh-xiaoai-bridge

Plugin that turns a XiaoAI (Xiaomi) smart speaker into a voice assistant: hosts the local bridge process, listens for the wake word, runs speech recognition (ASR / STT) on what you say, keeps the conversation in the host session, and speaks the answer back through the speaker with text-to-speech (TTS) playback.

76 days agoVision, Voice & MultimodalMIT
Y

deepseek-harness-plugins (vision-bridge)

yinxe/deepseek-harness-plugins

Let text-only models see images: when a picture arrives with a placeholder like \[image omitted because this model accepts text only], the model calls the vision_describe tool and the plugin forwards the image reference plus the question to a multimodal model, retrying with a fallback model on failure. Configured in the settings page and persisted via the official settings API.

7last monthVision, Voice & MultimodalMIT
Z

dsh-voice-input-plugin

zhangbo-cn/dsh-voice-input-plugin

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.

73 months agoVision, Voice & MultimodalMIT
L

dsh-image-gen

leemancheung/dsh-image-gen

GPT Image 2 `image_gen` with Codex subscription OAuth by default or explicit API-key mode: developing card, up to three live API partials, durable attachment replay/lightbox/download, text-only model output, and bounded credential-safe requests.

715 days agoVision, Voice & MultimodalMIT
J

dsh-interpret

jinchezuo/dsh-interpret

A DeepSeek Harness plugin for live English-to-Chinese captions. Microphone or system audio is transcribed on-device by Parakeet; translation uses the configured DSH LLM route, with a 3,050-term, eight-domain terminology RAG pass and an in-panel picker for cheap, high-quality, or open-source models. Bilingual subtitles sit beside a built-in reader for PDF, DOC/DOCX, XLSX, PPTX, CSV and Markdown; sessions persist locally and export to bilingual SRT or Markdown. macOS arm64 and Windows x64.

63 days agoVision, Voice & MultimodalMIT
H

DSH-Video2Agent (dsh-video2agent)

harm0ny-ai/dsh-video2agent

Bilibili/Douyin favorites gathering dust? Want your agent to gain video retrieval and understanding? Choose Video2Agent! One-click install gives your agent top-tier video understanding and turns online video into an information source. Whether you are researching social trends or working in media, any task that requires watching videos can now be handed to Video2Agent. Local-first; optional cloud ASR/OCR; optional Bilibili/Douyin login to unlock favorites/history and CC/AI subtitles.

6yesterdayVision, Voice & MultimodalApache-2.0
W

dsh-live-voice

wads-dev/dsh-live-voice

Local-first hands-free AI voice assistant plugin for DeepSeek Harness (DSH), with speech-to-text, text-to-speech, voice commands, and local speech engines.

6last monthVision, Voice & MultimodalApache-2.0
G

dsh-ocr-local

grelvan/dsh-ocr-local

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.

6last monthVision, Voice & Multimodal
A

dsh-image-preview

algerkong/dsh-image-preview

Image previews for DSH sessions: read_image thumbnails plus user, assistant, Markdown and present images in a lightbox with zoom, rotate, pan, download, sidebar and native file actions.

6last monthVision, Voice & Multimodal
M

dsh-voice-chat

maoyuching/dsh-voice-chat

Doubao-style voice chat for DSH: press-and-hold mic in the composer converts speech to text and auto-sends, and AI replies are read aloud. Optional LLM condensing (long replies summarized into short spoken lines, following the current conversation model), TTS-friendly text cleaning, selectable Edge TTS voices, adjustable silence auto-stop, and settings embedded in DSH settings dialog.

628 days agoVision, Voice & MultimodalMIT
G

dsh-tts

goodandready/dsh-tts

Speaks agent replies in the DeepSeek Harness web UI through a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak), so a failing or rate-limited provider falls through to the next instead of going silent.

69 days agoVision, Voice & MultimodalMIT
S

dsh-voice

stardustlc666/dsh-voice

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

621 hours agoVision, Voice & MultimodalMIT