@deepseek-ai/dsh-experimental-voice-input-bundle 0.1.7-alpha.1

package/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 DeepSeek
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

package/README.i18n.yaml

@@ -0,0 +1,6 @@
+# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
+# side as of the last confirmed-consistent state. Both languages carry equal authority;
+# after editing either side, bring the other along and re-record with:
+#   pnpm run verify-translation-pairing --write packages/experimental/voice-input-bundle/README.md
+README.md: 48320f7430bd9f1343492e49d3199c180970acad
+README.zh.md: f0a5b49741966b2e139ec5f803c15ddd79d12043

package/README.md

@@ -0,0 +1,77 @@
+---
+description: "Enable experimental speech input from the plugin manager."
+kind: "package-bundle"
+---
+
+# @deepseek-ai/dsh-experimental-voice-input-bundle
+
+English | [中文](README.zh.md)
+
+## Summary
+
+This optional bundle composes a speech Service Definition, local SenseVoice provider, authenticated Remote and browser microphone control. Shipped profiles leave it disabled.
+
+## Table of Contents
+
+- [Use this package](#use-this-package)
+- [Understand the implementation](#understand-the-implementation)
+- [Further Exploration](#further-exploration)
+- [Model Experience](#model-experience)
+- [Known Limitations and Deferred Work](#known-limitations-and-deferred-work)
+- [Dev Note](#dev-note)
+
+-----
+
+<a id="use-this-package"></a>
+## Use this package
+
+Open Plugins in the Web sidebar and enable Voice Input, marked by a blue waveform icon. If models need preparation, a dialog offers Go to setup or Later; Go to setup opens the bundle details. Complete caches need no setup prompt. In the details, choose Download and prepare; the collapsed current-step summary expands to the complete step list. Downloads report actual bytes; verification and loading show elapsed time. Once ready, click the microphone between the model selector and Send, then Stop to insert a transcript. Bundle details store the recognizer and language through the Settings service. Disabling the bundle cancels active work; cached assets remain on disk.
+
+-----
+
+<a id="understand-the-implementation"></a>
+## Understand the implementation
+
+<details>
+<summary>Maintainer details — click to expand</summary>
+
+The static `cordis.patch.yml` adds the four voice rows, selects `sensevoice-local` as the default recognizer and supplies the provider cache directory with `dshHomePath`. Optional-bundle installation makes the package available to management without selecting it in default profiles. The browser contribution owns its generated Remote mount; stable API Remotes do not import experimental code. No runtime invariant companion is published because this configuration-only package has no independently mutable runtime state.
+
+</details>
+
+-----
+
+<a id="further-exploration"></a>
+## Further Exploration
+
+[Voice input subsystem](../../../docs/subsystems/voice-input.md)
+
+-----
+
+<a id="model-experience"></a>
+## Model Experience
+
+None, as recordings and preparation remain outside model requests; ordinary user submission owns any later text.
+
+#### KV Cache effect
+
+No direct effect; ordinary submission owns the message content.
+
+## Known Limitations and Deferred Work
+
+<a id="known-limitations-and-deferred-work"></a>
+
+- The initial bundle supplies one local recognizer. Additional providers register with the same service under distinct ids; cloud recognition requires an explicit new provider and credential configuration. The bundle does not add a model tool or change the agent loop.
+- Installing dsh also installs `sherpa-onnx-node` and its platform-specific native runtime, including ONNX Runtime, even when this bundle is disabled. Runtime installation adds disk and download costs separate from the models downloaded by Download and prepare; the native package size varies by platform and version.
+
+-----
+
+<a id="dev-note"></a>
+### Dev Note
+
+<details>
+<summary>Maintainer details — click to expand</summary>
+
+None.
+
+</details>

package/README.zh.md

@@ -0,0 +1,77 @@
+---
+description: "从插件管理页启用实验性语音输入。"
+kind: "package-bundle"
+---
+
+# @deepseek-ai/dsh-experimental-voice-input-bundle
+
+[English](README.md) | 中文
+
+## 概述
+
+此可选 Bundle 组合语音服务定义、本地 SenseVoice Provider、带认证的 Remote 与浏览器麦克风控件。随包配置默认禁用。
+
+## 目录
+
+- [使用此包](#use-this-package)
+- [理解实现](#understand-the-implementation)
+- [进一步探索](#further-exploration)
+- [模型体验](#model-experience)
+- [已知限制与后续工作](#known-limitations-and-deferred-work)
+- [开发备注](#dev-note)
+
+-----
+
+<a id="use-this-package"></a>
+## 使用此包
+
+打开 Web 侧栏的插件管理页并启用带蓝色声波图标的“语音输入”。模型需要准备时，弹窗提供“前往安装”和“稍后”选项；“前往安装”打开 Bundle 详情。缓存完整时不会提示安装。在详情中选择“下载并准备”；默认折叠的当前步骤摘要可展开为完整步骤列表。下载报告真实字节，校验和加载显示等待时间。就绪后点击模型选择器与发送按钮之间的麦克风，再点击停止以插入转写文字。Bundle 详情通过 Settings 服务保存识别器和语言。禁用 Bundle 会取消当前任务；缓存资源保留在磁盘上。
+
+-----
+
+<a id="understand-the-implementation"></a>
+## 理解实现
+
+<details>
+<summary>维护者信息 — 点击展开</summary>
+
+静态 `cordis.patch.yml` 添加四个语音条目，选择 `sensevoice-local` 作为默认识别器，并通过 `dshHomePath` 提供 Provider 缓存目录。可选 Bundle 安装使插件管理器能够发现此包，但不会在默认配置中选择它。浏览器贡献拥有其生成 Remote 的挂载；稳定 API Remotes 不导入实验性代码。此纯配置包没有独立可变的运行时状态，因此不发布不变量伴随模块。
+
+</details>
+
+-----
+
+<a id="further-exploration"></a>
+## 进一步探索
+
+[语音输入子系统](../../../docs/subsystems/voice-input.zh.md)
+
+-----
+
+<a id="model-experience"></a>
+## 模型体验
+
+无，因为录音与准备不进入模型请求；之后的文字由普通用户提交拥有。
+
+#### KV 缓存影响
+
+没有直接影响；普通提交拥有消息内容。
+
+## 已知限制与后续工作
+
+<a id="known-limitations-and-deferred-work"></a>
+
+- 此 Bundle 提供一个本地识别器。额外 Provider 使用不同 id 注册到同一服务；云端识别需要显式增加 Provider 与凭据配置。Bundle 不增加模型工具或修改智能体循环。
+- 安装 dsh 时会一并安装 `sherpa-onnx-node` 及其平台原生运行时（含 ONNX Runtime），即使此 Bundle 处于禁用状态。运行时的磁盘占用和下载量独立于“下载并准备”所下载的模型；原生包体积随平台和版本变化。
+
+-----
+
+<a id="dev-note"></a>
+### 开发备注
+
+<details>
+<summary>维护者信息 — 点击展开</summary>
+
+无。
+
+</details>

package/cordis.patch.yml

@@ -0,0 +1,13 @@
+- insert:
+    - id: speech-to-text
+      name: '@deepseek-ai/dsh-experimental-speech-to-text'
+      config:
+        defaultProvider: sensevoice-local
+    - id: speech-to-text-sensevoice
+      name: '@deepseek-ai/dsh-experimental-speech-to-text-sensevoice'
+      config:
+        dataRoot: !!js dshHomePath('speech-to-text', 'sensevoice')
+    - id: api-speech-to-text
+      name: '@deepseek-ai/dsh-experimental-api-speech-to-text'
+    - id: ui-voice-input
+      name: '@deepseek-ai/dsh-experimental-client-ui-voice-input'

package/icon.svg

@@ -0,0 +1,9 @@
+<svg width="36" height="36" viewBox="0 0 36 36" fill="none" xmlns="http://www.w3.org/2000/svg">
+  <path d="M23.7324 8.77148V27.2295L21.2324 27.2285V8.77051L23.7324 8.77148ZM14.6797 10.7715L14.6787 25.2295L12.1787 25.2285L12.1797 10.7705L14.6797 10.7715ZM19.3926 22.4131H16.8926V13.5859H19.3926V22.4131ZM10.0625 20.708H7.5625V15.291H10.0625V20.708ZM28.4375 20.708H25.9375V15.291H28.4375V20.708Z" fill="url(#paint0_linear_3371_85203)" />
+  <defs>
+    <linearGradient id="paint0_linear_3371_85203" x1="8.24602" y1="16.4083" x2="32.5611" y2="22.9699" gradientUnits="userSpaceOnUse">
+      <stop stop-color="#67C7FE" />
+      <stop offset="1" stop-color="#3F77D8" />
+    </linearGradient>
+  </defs>
+</svg>

package/lib/index.js

@@ -0,0 +1 @@
+export {};

package/lib/types/index.d.ts

@@ -0,0 +1,3 @@
+/** Experimental voice input composition; runtime rows live in cordis.patch.yml. */
+export {};
+//# sourceMappingURL=index.d.ts.map

package/locale/en.json

@@ -0,0 +1,6 @@
+{
+  "meta": {
+    "title": "Voice input",
+    "description": "Transcribe recordings locally with SenseVoice; first use requires installing dependencies"
+  }
+}

package/locale/zh.json

@@ -0,0 +1,6 @@
+{
+  "meta": {
+    "title": "语音输入",
+    "description": "在本机使用 SenseVoice 转写录音；首次使用需安装依赖"
+  }
+}

package/package.json

@@ -0,0 +1,54 @@
+{
+  "name": "@deepseek-ai/dsh-experimental-voice-input-bundle",
+  "description": "Experimental voice input with local SenseVoice; downloads its runtime on first use",
+  "version": "0.1.7-alpha.1",
+  "icon": "./icon.svg",
+  "publishConfig": {
+    "access": "public"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/deepseek-ai/deepseek-harness.git",
+    "directory": "packages/experimental/voice-input-bundle"
+  },
+  "type": "module",
+  "main": "lib/index.js",
+  "types": "lib/types/index.d.ts",
+  "exports": {
+    ".": {
+      "types": "./lib/types/index.d.ts",
+      "default": "./lib/index.js"
+    },
+    "./src/*": "./src/*",
+    "./package.json": "./package.json",
+    "./cordis.patch.yml": "./cordis.patch.yml",
+    "./locale/*.json": "./locale/*.json"
+  },
+  "files": [
+    "icon.svg",
+    "locale/*.json",
+    "lib/index.js",
+    "cordis.patch.yml",
+    "lib/types/**/*.d.ts"
+  ],
+  "license": "MIT",
+  "dependencies": {
+    "@deepseek-ai/dsh-experimental-speech-to-text": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-experimental-speech-to-text-sensevoice": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-experimental-api-speech-to-text": "^0.1.7-alpha.1",
+    "@deepseek-ai/dsh-experimental-client-ui-voice-input": "^0.1.7-alpha.1"
+  },
+  "peerDependencies": {
+    "@deepseek-ai/cordis": "^4.0.3"
+  },
+  "devDependencies": {
+    "js-yaml": "^4.2.0",
+    "@deepseek-ai/cordis": "^4.0.3",
+    "@deepseek-ai/cordis-plugin-include": "^1.0.8"
+  },
+  "dsh": {
+    "bundle": {
+      "patch": "./cordis.patch.yml"
+    }
+  }
+}