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

P

dsh-plugin-xiaomi-mimo-tts

ppy-web/dsh-plugin-xiaomi-mimo-tts

Adds Xiaomi MiMo, Doubao, Breeze and browser speech to DSH, with external provider and local model adapters, text filtering, streaming read-aloud, audio downloads, sound effects, desktop pets, QQ Bot and AI Passport integration.

6623 hours agoVision, Voice & MultimodalMIT
1

dsh-plugin-tts

1624318455/dsh-plugin-tts

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.

649 hours agoVision, Voice & MultimodalMIT
B

dsh-voice-ai-girlfriend-plugin

beiyege-01/dsh-voice-ai-girlfriend-plugin

Voice AI girlfriend for the Web UI: FunASR mic input, Qwen3-TTS spoken replies, companion animation window, and two-way QQ chat (text/voice/image push) via NapCat.

615 days agoVision, Voice & Multimodal
S

dsh-watch-together

saos-3624/dsh-watch-together

Watch a video together with a text-only agent: with ffmpeg and the bundled browser extension reporting your real playback position (not a timer), it hands over one segment at a time just before that segment ends. It ships no TTS engine — it emits timed speech events, and speaking them aloud needs your own voice/TTS setup.

5517 hours agoVision, Voice & MultimodalApache-2.0
C

any-audio

cloudoyx/any-audio

DSH has its own audio workstation too: real recordings, multiple TTS engines, genuine sound effects and local singing synthesis, with every generated sound landing as its own clip on one visible timeline that you can audition, balance and fine-tune track by track. Use it for scoring animation, producing audiobooks and radio drama, composing and mixing on your own, making ASMR, and whatever else you come up with.

5221 hours agoVision, Voice & MultimodalMIT
S

dsh-design-qa

sunxin-ai/dsh-design-qa

Design-fidelity QA for text-only models: a `deepseek_vision` tool borrows an eye from any OpenAI-compatible vision route, so the model can judge whether an implementation matches its mock — shipped with the benchmark behind that judgement (four fixtures, 23 injected defects, raw transcripts) and the questioning discipline it depends on.

44last monthVision, Voice & MultimodalMIT
A

dsh-music-panel

aliboder/dsh-music-panel

A local + online music player for DeepSeek Harness: multi-root library, NetEase / QQ Music / KuGou / Bodian / Qishui / Navidrome, 14 Folia lyric stages, playlist and lyric translation, audio cache, EBU R128 leveling, 10-band EQ with AutoEQ, smart crossfade, in-list search, and tag / cover editing. Credentials and playback data stay on your machine. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

4120 hours agoVision, Voice & MultimodalAGPL-3.0
Y

dsh-qwen-paint

yanfei0725/dsh-qwen-paint

DSH 插件 / DeepSeek Harness:视频 / 生图 / TTS 全能 · 本机运行(QQ 交流群 454707710)。★ 0.34.0:SageAttention / Comfy-WaveSpeed 并入加速链并按真实 /object_info 探测、卡片常驻显示;GPT-SoVITS v5 / IndexTTS2 可选 TTS、拖音频零样本克隆、ACE-Step 1.5 / YuE2 音乐 BGM、手动超分、Worker 热温冷保活。★ 0.33.0 起许可改为 BSL 1.1(BUS

387 days agoVision, Voice & Multimodal
P

dsh-voice-scribe

pensivefei/dsh-voice-scribe

Voice input for the DSH web UI: tap or hold Alt to dictate into the composer. Local SenseVoice ASR by default — offline, zero config, zero key; auto-fallback to browser Web Speech, optional OpenAI-compatible ASR chain, polish through DSH-configured models, settings UI.

3621 days agoVision, Voice & MultimodalMIT
J

picturereader

jing-hy/picturereader

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.

3628 days agoVision, Voice & MultimodalMIT
Q

dsh-voice-mode (dsh-voice-mode)

qishuilalala/dsh-voice-mode

Full-duplex voice mode for the DeepSeek Harness Web UI: toggle (2s-pause auto-send) or hold-to-talk dictation into an editable draft with zipformer2 streaming ASR, optional wake word; sentence-by-sentence Edge TTS read-aloud with live captions, and speaking interrupts playback and the running turn (true barge-in). On-device ASR, no API key.

3519 hours agoVision, Voice & Multimodal
G

dsh-plugin-image-workbench

guohwa/dsh-plugin-image-workbench

DSH sidebar image-generation workbench with illustration and photography pipelines, a built-in local account pool, and any OpenAI-compatible endpoint.

344 days agoVision, Voice & MultimodalMIT
D

dsh-web-ui (dsh-tool-describe-image)

damonkoy/dsh-web-ui

Gives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.

343 months agoVision, Voice & MultimodalApache-2.0
A

dsh-soundcheck

alittlelov/dsh-soundcheck

Turns a local audio file into a short plain-language verdict on tempo, key, dynamics, clipping and arrangement shape, and keeps the raw measurements in a separate block; audio never leaves the machine.

317 days agoVision, Voice & MultimodalMIT
X

dsh-dania-voice

xcw520/dsh-dania-voice

Local GPT-SoVITS text-to-speech that reads DeepSeek Harness assistant replies aloud, with a draggable mascot toggle and a one-click installer. Requires Python 3.10–3.12 preinstalled (the installer only locates it, it does not install Python); about 5 GB of disk and a GPU are recommended.

3028 days agoVision, Voice & MultimodalMIT
Z

dsh-agnes-studio

zmm863-commits/dsh-agnes-studio

AI image and video studio as a floating DSH panel, so creation runs alongside the conversation instead of replacing it: text-to-image, image-to-image and multi-image composition at 1K-4K across eight aspect ratios; text-to-video and image-to-video with first-frame control at 4-12 seconds; short-drama mode that imports a script (.txt/.md/.json), breaks it into storyboard shots for preview and batch generation; and a prompt-expert workspace. Zero runtime dependencies.

302 days agoVision, Voice & MultimodalMIT
W

dsh-ears

wiziscool/dsh-ears

Voice input plugin for DeepSeek Harness (dsh): a microphone button in the composer turns speech into a draft transcript, with a choice of speech-recognition backends, optional polish through dsh own LLM routes, and a native settings page.

302 days agoVision, Voice & MultimodalMIT
A

dsh-image-studio

aa1355721445-lgtm/dsh-image-studio

Adds image_generate and image_library tools that pick reference images from four local libraries (characters, outfits, scenes, props), expand situation, expression, pose, shot and light keyword presets into the prompt, and call the 65535 async task API or any OpenAI-compatible images API, showing the result in the conversation; a settings page manages the libraries and turns an uploaded image or a text description into a three-view reference sheet. With dsh-daily-schedule installed, an image without a specified outfit uses what the character is wearing in the current schedule entry.

2921 days agoVision, Voice & MultimodalMIT
M

dsh-media-skills

mjorgin/dsh-media-skills

Image generation and image reading for DSH: an Images page in the sidebar, labelled 图像 in Chinese (one row per model, 10 ratios, 1K–4K sizes, a contact sheet with detail cards, zoom, reuse and delete), three preset providers plus custom endpoints — one needs no key at all — and a vision-review skill. A pasted key is written to ~/.dsh/secrets/media-tools.env (mode 600) and only sent to the provider you picked. The page follows the harness language (Chinese or English). Requires Python 3.9+ (generation runs through scripts/generate.py); the page needs desktop DSH 0.2.1+.

2916 days agoVision, Voice & MultimodalMIT
O

dsh-vision

oil-oil/dsh-vision

Near-native image understanding for DeepSeek Harness

243 months agoVision, Voice & MultimodalMIT
J

dsh-visual-plugin

jyh20030112/dsh-visual-plugin

Gives text-only models vision: forwards user images to an OpenAI-compatible vision model and shows the descriptions in a Web UI right panel.

232 months agoVision, Voice & MultimodalMIT
L

dsh-doubao-painter

liangzz1998/dsh-doubao-painter

Drives the local Doubao desktop client over CDP so the agent can generate images with the doubao_paint tool, covering text-to-image, image-to-image and batch prompts, and downloads the watermark-free originals from Doubao's own CDN instead of the thumbnail with a burned-in logo. Requires the Doubao client installed, signed in and started with a debug port.

2222 days agoVision, Voice & Multimodal
P

dsh-talk

perrylink/dsh-talk

Voice I/O for DeepSeek Harness — speech-to-text and text-to-speech over the microphone and audio output.

2221 hours agoVision, Voice & MultimodalApache-2.0
H

dsh-asr-plugin

huliux/dsh-asr-plugin

Local meeting transcription for DeepSeek Harness on Apple Silicon macOS: dual-track recording, live transcript drafts with speaker labels, and @-referenced summaries into decisions and action items.

2012 days agoVision, Voice & MultimodalApache-2.0