DSH Marketplace
中文

dsh-ears

WizisCool/dsh-ears

Voice input for DSH. Transcribes with browser Web Speech, local Whisper, Groq, Aliyun Bailian or any OpenAI-compatible endpoint, optionally polishes the text with a model already configured in the harness, and leaves an editable draft you send by hand.

40TypeScriptMITSource[DSH插件] dsh-ears — 自带大模型润色的DSH语音输入插件，给 DSH 加一对耳朵

Install

Add dsh-ears to DeepSeek Harness

via npm

Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.

via GitHub · npm package

Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.

Due diligence

Before you install dsh-ears

  • Source of record: WizisCool/dsh-ears — added by hand from a community post; not in the curated registry.
  • Licensed under MIT.
  • A listing here is not a security review. Plugins run with your agent's permissions.

What dsh-ears does

Sound waves flow through transcription and polishing channels into an editable draft.

dsh-ears is a DeepSeek Harness plugin that adds voice input to the web interface and turns speech into an editable draft. After installation and a Web UI refresh, a microphone icon appears beside the input box. The default shortcut is Ctrl+Shift+Space. Recording is transcribed by browser Web Speech, the local whisper CLI, Groq, Aliyun Bailian, or a specified OpenAI-compatible /audio/transcriptions endpoint. The draft is inserted into the composer for review and must be sent manually.

The host handles provider requests and local Whisper execution. In the plugin settings, dsh-ears stores the selected transcription provider and its model or endpoint details, while the optional polishing step uses a model already configured under dsh → 设置 → 模型. It stores the polishing prompt and reuses the existing LLM key rather than adding a separate key. Leaving the prompt empty uses the built-in default; failed or cancelled polishing keeps the original transcription.

This is for DSH users who want to dictate text without giving the agent automatic permission to speak or submit messages. It is a poor fit where audio must remain entirely local but local openai-whisper is unavailable, or where a Chromium-based browser is not available for Web Speech. Remote backends send recordings to their providers, and local Whisper transcribes only after recording stops. The plugin requires DeepSeek Harness 0.1.0-rc.6 or rc.7 and Node.js ^22.19.0 || >=24.0.0.

dsh-ears documentation

How it behaves

After the Web UI is refreshed, the plugin adds a microphone icon beside the input box. Use Ctrl+Shift+Space by default to start voice input. The flow is:

microphone → transcription → optional polishing → editable draft → manual send

The draft is not sent automatically. Polishing can remove speech fillers, correct ASR errors, and handle spoken corrections such as “not A, but B” and numbered points. If polishing fails or is cancelled, the original transcription remains.

Transcription backends

Backend Operation Required setup
Web Speech Browser performs real-time recognition Chromium-based browser; audio may be processed by the browser vendor
本地 Whisper Host runs the local whisper CLI after recording stops Pre-installed openai-whisper; download a model in the plugin settings
Groq Host sends the recording to the Groq Whisper API Groq API key
阿里云百炼 Host uses DashScope synchronous transcription HTTPS origin, API key, model name; 300-second per-request limit
自定义 OpenAI 兼容 Sends a POST request to the configured endpoint Endpoint URL, API key and model name; endpoint must provide /audio/transcriptions

Whisper model weights are not bundled with the plugin. Provider quotas and free allowances are subject to the providers’ current documentation.

Polishing configuration

The polishing model is selected from models already connected in dsh → 设置 → 模型. The plugin stores the provider, model name and prompt, and reuses the LLM key from the existing DSH configuration. An empty prompt selects the built-in default prompt, which can be viewed in the settings page.

Requirements and commands

The documented runtime requirements are DeepSeek Harness 0.1.0-rc.6 or rc.7, and Node.js ^22.19.0 || >=24.0.0. Remove the installed plugin with dsh plugin --profile web remove dsh-ears; refresh the Web UI afterwards. For local development, the repository documents pnpm install, pnpm check, pnpm test, pnpm build, pnpm dev:config, pnpm dev:web, and pnpm dev:watch.

Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub

Same category

Alternatives to dsh-ears

modlens

liustack

2.8k

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

Installed cleanly when we ran it

npm packageTypeScriptyesterday

AI review

modlens

What it is — ModLens adds image pasting vision capabilities to text-only models in DeepSeek Harness. Pasting an image returns structured JSON evidence including OCR, layout, and semantics.

Who it is for — When you use a text-only model in DeepSeek Harness for chat tasks that require analyzing pasted images, this plugin is suitable. If you use a model that supports native image processing or your work does not involve any image input, you do not need to install it because it does not affect the independent operation of pure text models.

Watch out — It was successfully installed and registered in a fresh profile during sandbox testing. The static check indicates it executes shell commands for image reading bridging. No other issues were observed.

The verdict — I would install it because it provides an extension for text models to read images and generate structured evidence; it is not worth it if you do not handle visual input tasks.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

agent-vision-toolkit

Anionex

1.0k

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Installed cleanly when we ran it

GitHub sourcePythonyesterday

AI review

agent-vision-toolkit

What it is — agent-vision-toolkit provides a vision toolkit and skill for text-only models to handle image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation.

Who it is for — In DeepSeek Harness using a text-only model for software development, if the model lacks image understanding for screenshots or UI, this can be used for visual tasks. If using native multimodal models, this provides optional seamless integration.

Watch out — Sandbox test passed with successful registration in a new profile. Code has been verified in real Codex and DeepSeek sessions, and the same pipeline has been live-verified end-to-end in Claude Code, Pi, Oh My Pi, and OpenCode.

The verdict — If your agent needs to handle UI screenshots and GUI automation in DeepSeek Harness, I would install it because it can make the text-model agent's visual experience as seamless as using a multimodal one, and ultimately let a tool-equipped text-model agent outperform a native multimodal agent that does not use this toolkit.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

dsh-vision-router

ysr666

648

Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.

Installed cleanly when we ran it

npm packageJavaScriptyesterday

AI review

dsh-vision-router

What it is — dsh-vision-router enables text-only agents to process images using pixel tools and vision chain.

Who it is for — Users conducting image grounding or OCR tasks with text-only models in DeepSeek Harness are suitable to install this plugin. If the agent focuses on pure text reasoning without visual support, it is unnecessary to install this plugin.

Watch out — Sandbox test passed: installed in a fresh profile and registered into the harness profile. It executes shell commands. No obvious pitfalls found.

The verdict — I would install it because it supports Oh-DSH Desktop and fixes DSH runtime readiness issues.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

dsh-vision-toolkit

Anionex

634

Vision tasks for text-only models: intent-aware image Q&A, long-screenshot OCR, UI reproduction, grounding, and pixel diff.

Installed cleanly when we ran it

npm packageTypeScriptyesterday

AI review

dsh-vision-toolkit

What it is — Enables text-only models in DeepSeek Harness with vision capabilities including image Q&A, long screenshot OCR, UI reproduction, grounding, and pixel diff.

Who it is for — When using text-only models in DeepSeek Harness for tasks involving screenshots and UI elements. If your tasks use native vision models rather than text-only ones, you can leverage their native features instead.

Watch out — It executes shell commands. Sandbox test passed in a fresh profile where it is registered by Harness. No other issues found.

The verdict — I would install it because it is the first comprehensive vision-tool plugin in the DeepSeek Harness ecosystem and sandbox testing passed.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Details

dsh-crew

ZSeven-W

50

DeepSeek Harness (DSH) plugin: dispatch work to DSH agents from Claude Code / Codex — native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge that lends the text-only harness vision and image generation.

Installed cleanly when we ran it

npm packageJavaScriptyesterday

AI review

dsh-crew

What it is — dsh-crew is a DeepSeek Harness plugin that dispatches work to DSH agents from Claude Code or Codex with native subagent progress and multimodal bridge.

Who it is for — When using Claude Code or Codex to dispatch tasks to DSH agents it is suitable to install dsh-crew. If your task is limited to a single text model call without subagent dispatch you can skip it.

Watch out — Sandbox test passed in a fresh profile and was registered with harness. No obvious issues found.

The verdict — I would install it because it integrates DSH agents as native subagents in Claude Code while the harness still controls the sandbox and tools.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
1Source

DSH-vison

hisence999

33

DSH-vison is a DeepSeek Harness plugin that adds image understanding for text-only models by converting images into descriptions from a configured vision-capable model.

Installed cleanly when we ran it

GitHub sourceJavaScript3d ago

AI review

DSH-vison

What it is — DSH-vison provides image understanding for text-only models by converting images into descriptions from a configured vision model.

Who it is for — When you use a text-only model to process user messages containing images, you need image understanding capability. If you use a multimodal model, you can skip installing this plugin.

Watch out — Sandbox test passed: it was installed in a fresh profile and registered by harness. No obvious pitfalls found.

The verdict — I would install it because the sandbox test passed and it enables global image handling for text models.

Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.Read the source
LINUX DO1Details