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

A

dsh-speak

alan2z/dsh-speak

Zero-dependency, event-driven voice announcement plugin: no extra model, no token cost. Speaks with the system's built-in natural voice, supporting both Windows and macOS; final-reply announcements, approval & question alerts, optional event announcements (turn end, command done, goal change, tool errors, todo updates), replayable final replies, and a bilingual visual settings page.

2026 days agoVision, Voice & MultimodalMIT
N

dsh-read-animation

neohotaru/dsh-read-animation

Reads animated GIF and WebP as animations: a pasted one keeps playing in the UI while the model gets a labelled sheet of frames sampled across it, and the read_animation tool samples a file on demand.

1814 days agoVision, Voice & MultimodalMIT
D

dsh-aigc-canvas

dsh-external/dsh-aigc-canvas

AIGC canvas plugin (cordis).

172 months agoVision, Voice & Multimodal
G

dsh-voice

goodandready/dsh-voice

Voice input for the web UI: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, or an OpenAI-compatible endpoint).

17yesterdayVision, Voice & MultimodalMIT
F

dsh-vision-proxy

flyvhidbwo/dsh-vision-proxy

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.

1723 days agoVision, Voice & MultimodalMIT
S

see-on-phone

saos-3624/see-on-phone

鱼眼 · See on Phone — 让 AI 住进手机:在手机上直接和模型聊天,需要时用它自己的摄像头看世界(手机端取帧、挑帧、拼宫格,电脑只收一张图)。导盲只是其中一个可选读者。

163 days agoVision, Voice & MultimodalApache-2.0
Y

dsh-duet

yums/dsh-duet

Full-duplex Chinese voice interaction for DSH Web: dictate and edit tasks, submit requests, manage sessions, answer DSH questions, and hear concise task-completion announcements.

1623 hours agoVision, Voice & MultimodalApache-2.0
C

dsh-mo-image

cm-silence/dsh-mo-image

DSH plugin: generate and edit images with model-aware prompt guidance over an OpenAI-compatible image model

157 days agoVision, Voice & MultimodalMIT
P

dsh-draw

perrylink/dsh-draw

Multi-engine text-to-image generation (OpenAI Images and Zhipu CogView presets) with per-session quota tracking, engine failover, credential-safe config, and a result card with regenerate.

14yesterdayVision, Voice & MultimodalApache-2.0
C

Gemini-Eyes

consolesun/gemini-eyes

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.

143 months agoVision, Voice & Multimodal
D

dsh-video-lens

dundunhan/dsh-video-lens

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件(场景感知抽帧 + VLM + 可选语音转录)

133 months agoVision, Voice & MultimodalMIT
Q

dsh-bili-eyes

qiuyedx/dsh-bili-eyes

Lets the model watch Bilibili videos as storyboard images with timed subtitles, top comments and danmaku keywords, and search, browse and read comments on Bilibili. Like, favorite, comment, reply, DM, post and follow tools are off by default, with per-audience permission levels and quotas. Includes a Settings page; ffmpeg is needed for frames and can be downloaded from Settings. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

1213 days agoVision, Voice & MultimodalMIT
P

dsh-vision-opencode

poiuyjie/dsh-vision-opencode

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.

122 months agoVision, Voice & MultimodalMIT
A

dsh-localtts

abbccdd/dsh-localtts

Reads Harness replies aloud through an existing local TTS runtime: built-in IndexTTS and GPT-SoVITS launchers, a protocol-based local HTTP/JSONL entry, and model-folder loading for Kokoro, F5-TTS, VoxCPM, Qwen3-TTS and CosyVoice SDK environments. Ships no models. Derived from 1624318455/dsh-plugin-tts; it isolates its row id and settings, so both can be installed side by side with duplicate features deactivated.

1124 days agoVision, Voice & MultimodalMIT
N

dsh-hos-scrcpy

ns-zzj/dsh-hos-scrcpy

Control a HarmonyOS phone from the DSH web UI with AI: live H.264 screen mirroring, mouse touch and system keys, hilog streaming, and agentic tools that let the model read the screen, locate UI controls, then tap, long-press, press keys, or type.

1110 days agoVision, Voice & MultimodalMIT
L

yingliu-video-studio

lakeofsky347/yingliu-video-studio

Video creation studio for DSH: storyboards, editable animation and local MP4 export / 映流视频工作台

102 days agoVision, Voice & MultimodalGPL-3.0
T

tripo3d-plugin-dsh

tripo-developer/tripo3d-plugin-dsh

Tripo 3D skills for DeepSeek Harness — generate engine-ready 3D assets from a text prompt or a reference image via tripo-cli, with texturing, rigging, retopology and format conversion in one pass. Works with both Tripo regions (China mainland and internat

105 days agoVision, Voice & Multimodal
D

dsh-video-vision

destinhue/dsh-video-vision

Five tools for reading a video as raw material rather than as something to watch. video_outline maps a whole file as text and draws nothing at all: 4-60 equal windows, each with its cut count, speech share, intensity bar and tags, then the windows worth opening and the exact start/end for the call that follows -- zero image tokens. video_probe returns metadata and a reading plan without decoding frames. video_storyboard turns a window into one contact sheet plus a text index binding every cell to its timecode, cut count and frame time; cells whose text would be illegible at that scale are marked zoom, and dedupe global folds a picture that comes back after a cut. video_zoom re-renders 1-9 cells from a short window at a larger scale. video_read decodes only keyframes, OCRs each screen, and returns an outline plus \[mm:ss] text -- the path for lectures, slide decks and screen recordings, where the words are the content. It also reads a file with sound and no picture as a transcript (subtitle track, then DSH_ASR_CMD, then a transcript file you pass; long audio is cut at 45 s onto silence), composes six changed frames into one sheet when a file has no readable text at all, and can write the result out as SRT, WebVTT or text. Cuts, dissolves and one-frame flashes are found in a single ffmpeg pass; from ten minutes up a file is analysed on its keyframes only, 2.7x faster on a two-hour lecture; and a cell is never shrunk below a fifth of the source, so a 1440p sheet spends the same tokens on fewer, bigger cells. OCR is the engine Windows ships, tesseract with line boxes, or DSH_OCR_CMD. It takes a B station link (bilibili.com/video/BV..., a bare BV id, an av id or a b23.tv short link) wherever it takes a file: up to 300 seconds is read from the CDN in place with nothing written to disk, longer videos are downloaded once and cached within a 4 GB / 24 video budget, play URLs are cached for ten minutes, and a link that is not a single video says what it is. Needs ffmpeg, uses ffprobe when present, and has no other runtime dependencies. It is a wire-compatible reimplementation of SAOS-3624/dsh-video-storyboard: it registers the same video_probe / video_storyboard / video_zoom tool names, so the two cannot be enabled together.

107 days agoVision, Voice & MultimodalMIT
S

dsh-deepseek-vision

siegfly/dsh-deepseek-vision

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

102 months agoVision, Voice & MultimodalMIT
P

dsh-screenshot

paicat1/dsh-screenshot

Zero-dependency screen capture for DSH: Lightweight — zero deps, zero binaries; Stage & shoot — one-click full screen, window layout, hover-snap capture of occluded windows; Agent self-service — path-only delivery; paths are universal, pair with modlens (optional) for one-call structured evidence.

102 months agoVision, Voice & MultimodalMIT
Z

dsh-omni

ztr66/dsh-omni

One plugin for every modality: probe, transcribe, analyse and compose image, video and audio.

99 days agoVision, Voice & MultimodalMIT
D

img2img-studio

dogwind221/img2img-studio

img2img-studio 的 GUI 插件(一个包两个面):① 输入框里的图片编辑器(编号标记 / 移除背景 / 涂抹擦除 / 调整大小,支持键盘操作与裁切遮罩预览);② 设置页「识图与生图」供应商面板(供应商目录选择 + 脚本扫描标注、账号库驱动 chatgpt-web 通道、每行测试/试跑/复制命令、保存前预览、余额探测;中/英双语),保存即写回两个 skill 的 scripts/.env

922 days agoVision, Voice & MultimodalMIT
B

dsh-pet-voice-fishy

bbfang2025-cyber/dsh-pet-voice-fishy

Big Fish Voice: makes the DSH web desktop pet speak. Whisper bubbles are read aloud automatically, left-clicking a bubble reads it, right-click/long-press reads it again, and clicking the pet replies with lines like 「主人,小鱼在这呢」. Default voice is a local offline replica of 鱼鱼酱; 鱼鱼姐 (experimental) is also included — no API key needed, voice packs download on demand (~58MB, China-accessible mirrors). Auto-reading can be throttled (unlimited / 30s / 60s / 3min); within one DSH instance only one page plays audio. About 35KB package, inference in a worker thread, no dsh-pet files modified.

9yesterdayVision, Voice & MultimodalMIT
T

dsh-gsv

taoruiliu19/dsh-gsv

Real-time local TTS for DeepSeek Harness: voice presets, auto-read, engine setup assistant, a read-aloud button, and a settings panel for the GSV-TTS-Lite engine.

98 days agoVision, Voice & MultimodalMIT