feat(engine): 优化 Vosk 字幕引擎支持

- 实现文件夹选择功能，用于选择 Vosk 模型路径 - 在 EngineControl 组件中添加模型路径选择按钮和相关提示 - 在 EngineStatus 组件中增加对空模型路径的检查和错误提示
feat(engine): 添加 Vosk 本地离线引擎支持
2026-02-23 10:14:42 +08:00 · 2025-07-10 11:22:39 +08:00 · 2025-07-09 19:53:30 +08:00 · 2025-07-09 02:34:15 +08:00 · 2025-07-09 01:33:21 +08:00 · 2025-07-08 22:46:51 +08:00
41 changed files with 753 additions and 103 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -7,5 +7,6 @@ out
 __pycache__
 subenv
 caption-engine/build
+caption-engine/models
 output.wav
-.venv
+.venv
--- a/README.md
+++ b/README.md
@@ -2,6 +2,13 @@
    <img src="./build/icon.png" width="100px" height="100px"/>
    <h1 align="center">auto-caption</h1>
    <p>Auto Caption 是一个跨平台的实时字幕显示软件。</p>
+    <p>
+      <img src="https://img.shields.io/badge/version-0.3.0-blue">
+      <img src="https://img.shields.io/github/issues/HiMeditator/auto-caption?color=orange">
+      <img src="https://img.shields.io/github/languages/top/HiMeditator/auto-caption?color=royalblue">
+      <img src="https://img.shields.io/github/repo-size/HiMeditator/auto-caption?color=green">
+      <img src="https://visitor-badge.laobi.icu/badge?page_id=himeditator.auto-caption">
+    </p>
    <p>
        | <b>简体中文</b>
        | <a href="./README_en.md">English</a>
--- a/README_en.md
+++ b/README_en.md
@@ -2,6 +2,13 @@
    <img src="./build/icon.png" width="100px" height="100px"/>
    <h1 align="center">auto-caption</h1>
    <p>Auto Caption is a cross-platform real-time caption display software.</p>
+    <p>
+      <img src="https://img.shields.io/badge/version-0.3.0-blue">
+      <img src="https://img.shields.io/github/issues/HiMeditator/auto-caption?color=orange">
+      <img src="https://img.shields.io/github/languages/top/HiMeditator/auto-caption?color=royalblue">
+      <img src="https://img.shields.io/github/repo-size/HiMeditator/auto-caption?color=green">
+      <img src="https://visitor-badge.laobi.icu/badge?page_id=himeditator.auto-caption">
+    </p>
    <p>
        | <a href="./README.md">简体中文</a>
        | <b>English</b>
--- a/README_ja.md
+++ b/README_ja.md
@@ -2,6 +2,13 @@
    <img src="./build/icon.png" width="100px" height="100px"/>
    <h1 align="center">auto-caption</h1>
    <p>Auto Caption はクロスプラットフォームのリアルタイム字幕表示ソフトウェアです。</p>
+    <p>
+      <img src="https://img.shields.io/badge/version-0.3.0-blue">
+      <img src="https://img.shields.io/github/issues/HiMeditator/auto-caption?color=orange">
+      <img src="https://img.shields.io/github/languages/top/HiMeditator/auto-caption?color=royalblue">
+      <img src="https://img.shields.io/github/repo-size/HiMeditator/auto-caption?color=green">
+      <img src="https://visitor-badge.laobi.icu/badge?page_id=himeditator.auto-caption">
+    </p>
    <p>
        | <a href="./README.md">简体中文</a>
        | <a href="./README_en.md">English</a>
--- a/assets/media/main_en.png
+++ b/assets/media/main_en.png
--- a/assets/media/main_ja.png
+++ b/assets/media/main_ja.png
--- a/assets/media/main_zh.png
+++ b/assets/media/main_zh.png
--- a/caption-engine/audioprcs/init.py
+++ b/caption-engine/audioprcs/init.py
@@ -1 +1 @@
-from .process import mergeChunkChannels, resampleRawChunk
+from .process import mergeChunkChannels, resampleRawChunk, resampleMonoChunk
--- a/caption-engine/audioprcs/process.py
+++ b/caption-engine/audioprcs/process.py
@@ -47,3 +47,22 @@ def resampleRawChunk(chunk, channels, orig_sr, target_sr, mode="sinc_best"):
    chunk_mono_r =  samplerate.resample(chunk_mono, ratio, converter_type=mode)
    chunk_mono_r = np.round(chunk_mono_r).astype(np.int16)
    return chunk_mono_r.tobytes()
+
+def resampleMonoChunk(chunk, orig_sr, target_sr, mode="sinc_best"):
+    """
+    将当前单通道音频块进行重采样
+
+    Args:
+        chunk: (bytes)单通道音频数据块
+        orig_sr: 原始采样率
+        target_sr: 目标采样率
+        mode: 重采样模式，可选：'sinc_best' | 'sinc_medium' | 'sinc_fastest' | 'zero_order_hold' | 'linear'
+
+    Return:
+        (bytes)单通道音频数据块
+    """
+    chunk_np = np.frombuffer(chunk, dtype=np.int16)
+    ratio = target_sr / orig_sr
+    chunk_r =  samplerate.resample(chunk_np, ratio, converter_type=mode)
+    chunk_r = np.round(chunk_r).astype(np.int16)
+    return chunk_r.tobytes()
--- a/caption-engine/main-vosk.py
+++ b/caption-engine/main-vosk.py
@@ -0,0 +1,83 @@
+import sys
+import json
+import argparse
+from datetime import datetime
+import numpy.core.multiarray
+
+if sys.platform == 'win32':
+    from sysaudio.win import AudioStream
+elif sys.platform == 'darwin':
+    from sysaudio.darwin import AudioStream
+elif sys.platform == 'linux':
+    from sysaudio.linux import AudioStream
+else:
+    raise NotImplementedError(f"Unsupported platform: {sys.platform}")
+
+from vosk import Model, KaldiRecognizer, SetLogLevel
+from audioprcs import resampleRawChunk
+
+SetLogLevel(-1)
+
+def convert_audio_to_text(audio_type, chunk_rate, model_path):
+    sys.stdout.reconfigure(line_buffering=True) # type: ignore
+
+    if model_path.startswith('"'):
+        model_path = model_path[1:]
+    if model_path.endswith('"'):
+        model_path = model_path[:-1]
+
+    model = Model(model_path)
+    recognizer = KaldiRecognizer(model, 16000)
+
+    stream = AudioStream(audio_type, chunk_rate)
+    stream.openStream()
+
+    time_str = ''
+    cur_id = 0
+    prev_content = ''
+
+    while True:
+        chunk = stream.read_chunk()
+        chunk_mono = resampleRawChunk(chunk, stream.CHANNELS, stream.RATE, 16000)
+
+        caption = {}
+        if recognizer.AcceptWaveform(chunk_mono):
+            content = json.loads(recognizer.Result()).get('text', '')
+            caption['index'] = cur_id
+            caption['text'] = content
+            caption['time_s'] = time_str
+            caption['time_t'] = datetime.now().strftime('%H:%M:%S.%f')[:-3]
+            caption['translation'] = ''
+            prev_content = ''
+            cur_id += 1
+        else:
+            content = json.loads(recognizer.PartialResult()).get('partial', '')
+            if content == '' or content == prev_content:
+                continue
+            if prev_content == '':
+                time_str = datetime.now().strftime('%H:%M:%S.%f')[:-3]
+            caption['index'] = cur_id
+            caption['text'] = content
+            caption['time_s'] = time_str
+            caption['time_t'] = datetime.now().strftime('%H:%M:%S.%f')[:-3]
+            caption['translation'] = ''
+            prev_content = content
+        try:
+            json_str = json.dumps(caption) + '\n'
+            sys.stdout.write(json_str)
+            sys.stdout.flush()
+        except Exception as e:
+            print(e)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description='Convert system audio stream to text')
+    parser.add_argument('-a', '--audio_type', default=0, help='Audio stream source: 0 for output audio stream, 1 for input audio stream')
+    parser.add_argument('-c', '--chunk_rate', default=20, help='The number of audio stream chunks collected per second.')
+    parser.add_argument('-m', '--model_path', default='', help='The path to the vosk model.')
+    args = parser.parse_args()
+    convert_audio_to_text(
+        int(args.audio_type),
+        int(args.chunk_rate),
+        args.model_path
+    )
--- a/caption-engine/main-vosk.spec
+++ b/caption-engine/main-vosk.spec
@@ -0,0 +1,42 @@
+# -*- mode: python ; coding: utf-8 -*-
+
+from pathlib import Path
+
+vosk_path = str(Path('./subenv/Lib/site-packages/vosk').resolve())
+
+a = Analysis(
+    ['main-vosk.py'],
+    pathex=[],
+    binaries=[],
+    datas=[(vosk_path, 'vosk')],
+    hiddenimports=[],
+    hookspath=[],
+    hooksconfig={},
+    runtime_hooks=[],
+    excludes=[],
+    noarchive=False,
+    optimize=0,
+)
+
+pyz = PYZ(a.pure)
+
+exe = EXE(
+    pyz,
+    a.scripts,
+    a.binaries,
+    a.datas,
+    [],
+    name='main-vosk',
+    debug=False,
+    bootloader_ignore_signals=False,
+    strip=False,
+    upx=True,
+    upx_exclude=[],
+    runtime_tmpdir=None,
+    console=True,
+    disable_windowed_traceback=False,
+    argv_emulation=False,
+    target_arch=None,
+    codesign_identity=None,
+    entitlements_file=None,
+)
--- a/caption-engine/requirements.txt
+++ b/caption-engine/requirements.txt
@@ -3,4 +3,5 @@ numpy
 samplerate
 PyAudio
 PyAudioWPatch # Windows only
+vosk
 pyinstaller
--- a/caption-engine/sysaudio/win.py
+++ b/caption-engine/sysaudio/win.py
@@ -57,7 +57,7 @@ class AudioStream:
        self.stream = None
        self.SAMP_WIDTH = pyaudio.get_sample_size(pyaudio.paInt16)
        self.FORMAT = pyaudio.paInt16
-        self.CHANNELS = self.device["maxInputChannels"]
+        self.CHANNELS = int(self.device["maxInputChannels"])
        self.RATE = int(self.device["defaultSampleRate"])
        self.CHUNK = self.RATE // chunk_rate
        self.INDEX = self.device["index"]
--- a/docs/CHANGELOG.md
+++ b/docs/CHANGELOG.md
@@ -29,6 +29,7 @@

 ### 新增功能

+- 添加长字幕内容隐藏功能 (#1)
 - 添加多界面语言支持（中文、英语、日语）
 - 添加暗色主题

@@ -40,7 +41,7 @@

 ### 修复bug

- 添加字幕引擎长时间空置后报错的问题
+- 添加字幕引擎长时间空置后报错的问题 (#2)

 ### 新增文档

@@ -48,63 +49,26 @@
 - 新增英语、日语字幕引擎说明文档和用户手册
 - 新增 electron ipc api 文档

+## v0.3.0

+2025-07-09

+对字幕引擎代码进行了重构，软件适配了 macOS 平台，添加了新功能。

-Here are the translations of the selected macOS audio output configuration section:
+### 新增功能

-### English Translation:
-```markdown
-### Capturing System Audio Output on macOS
+- 添加软件内设置 API KEY 的功能
+- 添加字幕字体粗细和文本阴影的设置
+- 添加复制字幕记录到剪贴板的功能 (#3)

-The subtitle engine cannot directly capture system audio output on macOS platform and requires additional driver installation. The current subtitle engine uses [BlackHole](https://github.com/ExistentialAudio/BlackHole). First open Terminal and execute one of the following commands (recommended to choose the first one):
+### 优化体验

-```bash
-brew install blackhole-2ch
-brew install blackhole-16ch
-brew install blackhole-64ch
-```
+- 字幕时间记录精确到毫秒
+- 更详细的说明文档（添加字幕引擎规格说明、用户文档和字幕引擎文档更新） (#4)
+- 适配 macOS 平台
+- 字幕窗口有了更大的顶置优先级
+- 预览窗口可以实时显示最新的字幕内容

-After installation completes, open `Audio MIDI Setup` (searchable via `cmd + space`). Check if BlackHole appears in the device list - if not, restart your computer.
+### 修复bug

-Once BlackHole is confirmed installed, in the `Audio MIDI Setup` page, click the plus (+) button at bottom left and select "Create Multi-Output Device". Include both BlackHole and your desired audio output destination in the outputs. Finally, set this multi-output device as your default audio output device.
-
-Now the subtitle engine can capture system audio output and generate subtitles.
-```
-
-### Japanese Translation:
-```markdown
-### macOSでのシステムオーディオ出力の取得方法
-
-字幕エンジンはmacOSプラットフォームで直接システムオーディオ出力を取得できず、追加のドライバーインストールが必要です。現在の字幕エンジンでは[BlackHole](https://github.com/ExistentialAudio/BlackHole)を使用しています。まずターミナルを開き、以下のいずれかのコマンドを実行してください（最初のオプションを推奨します）：
-
-```bash
-brew install blackhole-2ch
-brew install blackhole-16ch
-brew install blackhole-64ch
-```
-
-インストール完了後、`オーディオMIDI設定`（`cmd + space`で検索可能）を開きます。デバイスリストにBlackHoleが表示されているか確認してください - 表示されていない場合はコンピュータを再起動してください。
-
-BlackHoleのインストールが確認できたら、`オーディオMIDI設定`ページで左下のプラス(+)ボタンをクリックし、「マルチ出力デバイスを作成」を選択します。出力にBlackHoleと希望するオーディオ出力先の両方を含めてください。最後に、このマルチ出力デバイスをデフォルトのオーディオ出力デバイスに設定します。
-
-これで字幕エンジンがシステムオーディオ出力をキャプチャし、字幕を生成できるようになります。
-```
-
-Key translation notes:
-1. Technical terms:
-   - "Audio MIDI Setup" → "オーディオMIDI設定" (Japanese)
-   - "Multi-Output Device" → "マルチ出力デバイス" (Japanese)
-   - Maintained "BlackHole" and "brew" commands as-is
-
-2. Structure:
-   - Kept the same section hierarchy with ### headers
-   - Preserved all code blocks and formatting
-   - Maintained the step-by-step instruction flow
-
-3. Localization:
-   - Used appropriate Japanese technical terms
-   - Adjusted phrasing for natural reading in each language
-   - Kept all terminal commands and interface elements unchanged
-
-Both translations accurately convey the technical procedures while adapting naturally to their target languages.
+- 修复使用系统主题时暗色系统载入为亮色的问题
--- a/docs/TODO.md
+++ b/docs/TODO.md
@@ -8,12 +8,14 @@
 - [x] 添加对自带字幕引擎的详细规格说明 *2025/07/07*
 - [x] 添加复制字幕到剪贴板功能 *2025/07/08*
 - [x] 适配 macOS 平台 *2025/07/08*
+- [x] 添加字幕文字描边 *2025/07/09*
+- [x] 添加基于 Vosk 的字幕引擎 *2025/07/09*

 ## 待完成

- [ ] 添加字幕文字描边
+- [ ] 添加 Ollama 模型用于本地字幕引擎的翻译
+- [ ] 更新 README 和用户手册（字幕引擎构建、Vosk 模型获取和使用）
 - [ ] 添加本地字幕引擎
-  - [ ] 添加基于 Vosk 的字幕引擎
  - [ ] 验证 / 添加基于 FunASR 的字幕引擎
 - [ ] 减小软件不必要的体积

--- a/docs/api-docs/electron-ipc.md
+++ b/docs/api-docs/electron-ipc.md
@@ -44,6 +44,19 @@
 - 发送：无数据
 - 接收：`string`

+### `control.folder.select`
+
+**介绍：** 打开文件夹选择器，并将用户选择的文件夹路径返回给前端
+
+**发起方：** 前端控制窗口
+
+**接收方：** 后端控制窗口实例
+
+**数据类型：**
+
+- 发送：无数据
+- 接收：`string`
+
 ## 前端 ==> 后端

 ### `control.uiLanguage.change`
--- a/docs/img/03.png
+++ b/docs/img/03.png
--- a/docs/img/04.png
+++ b/docs/img/04.png
--- a/docs/img/05.png
+++ b/docs/img/05.png
--- a/docs/user-manual/en.md
+++ b/docs/user-manual/en.md
@@ -35,6 +35,8 @@ Alibaba Cloud provides detailed tutorials for this:

 ### Capturing System Audio Output on macOS

+> Based on the [Setup Multi-Output Device](https://github.com/ExistentialAudio/BlackHole/wiki/Multi-Output-Device) tutorial
+
 The caption engine cannot directly capture system audio output on macOS platform and requires additional driver installation. The current caption engine uses [BlackHole](https://github.com/ExistentialAudio/BlackHole). First open Terminal and execute one of the following commands (recommended to choose the first one):

 ```bash
@@ -43,10 +45,16 @@ brew install blackhole-16ch
 brew install blackhole-64ch
 ```

+![](../img/03.png)
+
 After installation completes, open `Audio MIDI Setup` (searchable via `cmd + space`). Check if BlackHole appears in the device list - if not, restart your computer.

+![](../img/04.png)
+
 Once BlackHole is confirmed installed, in the `Audio MIDI Setup` page, click the plus (+) button at bottom left and select "Create Multi-Output Device". Include both BlackHole and your desired audio output destination in the outputs. Finally, set this multi-output device as your default audio output device.

+![](../img/05.png)
+
 Now the caption engine can capture system audio output and generate captions.

 ### Modifying Settings
--- a/docs/user-manual/ja.md
+++ b/docs/user-manual/ja.md
@@ -37,6 +37,9 @@ macOS プラットフォームでオーディオ出力を取得するには追

 ### macOS でのシステムオーディオ出力の取得方法

+> [マルチ出力デバイスの設定](https://github.com/ExistentialAudio/BlackHole/wiki/Multi-Output-Device) チュートリアルに基づいて作成
+
+
 字幕エンジンは macOS プラットフォームで直接システムオーディオ出力を取得できず、追加のドライバーインストールが必要です。現在の字幕エンジンでは [BlackHole](https://github.com/ExistentialAudio/BlackHole) を使用しています。まずターミナルを開き、以下のいずれかのコマンドを実行してください（最初のオプションを推奨します）：

 ```bash
@@ -45,10 +48,16 @@ brew install blackhole-16ch
 brew install blackhole-64ch
 ```

+![](../img/03.png)
+
 インストール完了後、`オーディオMIDI設定`（`cmd + space`で検索可能）を開きます。デバイスリストにBlackHoleが表示されているか確認してください - 表示されていない場合はコンピュータを再起動してください。

+![](../img/04.png)
+
 BlackHoleのインストールが確認できたら、`オーディオ MIDI 設定`ページで左下のプラス(+)ボタンをクリックし、「マルチ出力デバイスを作成」を選択します。出力に BlackHole と希望するオーディオ出力先の両方を含めてください。最後に、このマルチ出力デバイスをデフォルトのオーディオ出力デバイスに設定します。

+![](../img/05.png)
+
 これで字幕エンジンがシステムオーディオ出力をキャプチャし、字幕を生成できるようになります。

 ### 設定の変更
--- a/docs/user-manual/zh.md
+++ b/docs/user-manual/zh.md
@@ -38,6 +38,8 @@ Auto Caption 是一个跨平台的字幕显示软件，能够实时获取系统

 ### macOS 获取系统音频输出

+> 基于 [Setup Multi-Output Device](https://github.com/ExistentialAudio/BlackHole/wiki/Multi-Output-Device) 教程编写
+
 字幕引擎无法在 macOS 平台直接获取系统的音频输出，需要安装额外的驱动。目前字幕引擎采用的是 [BlackHole](https://github.com/ExistentialAudio/BlackHole)。首先打开终端，执行以下命令中的其中一个（建议选择第一个）：

 ```bash
@@ -46,10 +48,16 @@ brew install blackhole-16ch
 brew install blackhole-64ch
 ```

+![](../img/03.png)
+
 安装完成后打开 `音频 MIDI 设置`（`cmd + space` 打开搜索，可以搜索到）。观察设备列表中是否有 BlackHole 设备，如果没有需要重启电脑。

+![](../img/04.png)
+
 在确定安装好 BlackHole 设备后，在 `音频 MIDI 设置` 页面，点击左下角的加号，选择“创建多输出设备”。在输出中包含 BlackHole 和你想要的音频输出目标。最后将该多输出设备设置为默认音频输出设备。

+![](../img/05.png)
+
 现在字幕引擎就能捕获系统的音频输出并生成字幕了。

 ### 修改设置
--- a/electron-builder.yml
+++ b/electron-builder.yml
@@ -10,8 +10,15 @@ files:
  - '!{.env,.env.*,.npmrc,pnpm-lock.yaml}'
  - '!{tsconfig.json,tsconfig.node.json,tsconfig.web.json}'
 extraResources:
-  from: ./caption-engine/dist/main-gummy
-  to: ./caption-engine/main-gummy
+  - from: ./caption-engine/dist/main-gummy.exe
+    to: ./caption-engine/main-gummy.exe
+  - from: ./caption-engine/dist/main-vosk.exe
+    to: ./caption-engine/main-vosk.exe
+  # For macOS and Linux
+  # - from: ./caption-engine/dist/main-gummy
+  #   to: ./caption-engine/main-gummy
+  # - from: ./caption-engine/dist/main-vosk
+  #   to: ./caption-engine/main-vosk
 asarUnpack:
  - resources/**
 win:
--- a/engine-test/vosk.ipynb
+++ b/engine-test/vosk.ipynb
@@ -0,0 +1,124 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "6fb12704",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "d:\\Projects\\auto-caption\\caption-engine\\subenv\\Lib\\site-packages\\vosk\\__init__.py\n"
+     ]
+    }
+   ],
+   "source": [
+    "import vosk\n",
+    "print(vosk.__file__)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "63a06f5c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "        采样设备：\n",
+      "            - 设备类型：音频输入\n",
+      "            - 序号：1\n",
+      "            - 名称：麦克风阵列 (Realtek(R) Audio)\n",
+      "            - 最大输入通道数：2\n",
+      "            - 默认低输入延迟：0.09s\n",
+      "            - 默认高输入延迟：0.18s\n",
+      "            - 默认采样率：44100.0Hz\n",
+      "            - 是否回环设备：False\n",
+      "\n",
+      "        音频样本块大小：2205\n",
+      "        样本位宽：2\n",
+      "        采样格式：8\n",
+      "        音频通道数：2\n",
+      "        音频采样率：44100\n",
+      "        \n"
+     ]
+    }
+   ],
+   "source": [
+    "import sys\n",
+    "import os\n",
+    "import json\n",
+    "from vosk import Model, KaldiRecognizer\n",
+    "\n",
+    "current_dir = os.getcwd() \n",
+    "sys.path.append(os.path.join(current_dir, '../caption-engine'))\n",
+    "\n",
+    "from sysaudio.win import AudioStream\n",
+    "from audioprcs import resampleRawChunk, mergeChunkChannels\n",
+    "\n",
+    "stream = AudioStream(1)\n",
+    "stream.printInfo()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "5d5a0afa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = Model(os.path.join(\n",
+    "    current_dir,\n",
+    "    '../caption-engine/models/vosk-model-small-cn-0.22'\n",
+    "))\n",
+    "recognizer = KaldiRecognizer(model, 16000)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7e9d1530",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stream.openStream()\n",
+    "\n",
+    "for i in range(200):\n",
+    "    chunk = stream.read_chunk()\n",
+    "    chunk_mono = resampleRawChunk(chunk, stream.CHANNELS, stream.RATE, 16000)\n",
+    "    if recognizer.AcceptWaveform(chunk_mono):\n",
+    "        result = json.loads(recognizer.Result())\n",
+    "        print(\"acc:\", result.get(\"text\", \"\"))\n",
+    "    else:\n",
+    "        partial = json.loads(recognizer.PartialResult())\n",
+    "        print(\"else:\", partial.get(\"partial\", \"\"))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "subenv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
--- a/src/main/ControlWindow.ts
+++ b/src/main/ControlWindow.ts
@@ -1,4 +1,4 @@
-import { shell, BrowserWindow, ipcMain, nativeTheme } from 'electron'
+import { shell, BrowserWindow, ipcMain, nativeTheme, dialog } from 'electron'
 import path from 'path'
 import { is } from '@electron-toolkit/utils'
 import icon from '../../build/icon.png?asset'
@@ -65,8 +65,20 @@ class ControlWindow {
    })

    ipcMain.handle('control.nativeTheme.get', () => {
-      if(nativeTheme.shouldUseDarkColors) return 'dark'
-      return 'light'
+      if(allConfig.uiTheme === 'system'){
+        if(nativeTheme.shouldUseDarkColors) return 'dark'
+        return 'light'
+      }
+      return allConfig.uiTheme
+    })
+
+    ipcMain.handle('control.folder.select', async () => {
+      const result = await dialog.showOpenDialog({
+        properties: ['openDirectory']
+      });
+
+      if (result.canceled) return "";
+      return result.filePaths[0];
    })

    ipcMain.on('control.uiLanguage.change', (_, args) => {
--- a/src/main/types/index.ts
+++ b/src/main/types/index.ts
@@ -6,10 +6,11 @@ export interface Controls {
  engineEnabled: boolean,
  sourceLang: string,
  targetLang: string,
-  engine: 'gummy',
+  engine: string,
  audio: 0 | 1,
  translation: boolean,
  API_KEY: string,
+  modelPath: string,
  customized: boolean,
  customizedApp: string,
  customizedCommand: string
@@ -20,13 +21,20 @@ export interface Styles {
  fontFamily: string,
  fontSize: number,
  fontColor: string,
+  fontWeight: number,
  background: string,
  opacity: number,
  showPreview: boolean,
  transDisplay: boolean,
  transFontFamily: string,
  transFontSize: number,
-  transFontColor: string
+  transFontColor: string,
+  transFontWeight: number,
+  textShadow: boolean,
+  offsetX: number,
+  offsetY: number,
+  blur: number,
+  textShadowColor: string
 }

 export interface CaptionItem {
--- a/src/main/utils/AllConfig.ts
+++ b/src/main/utils/AllConfig.ts
@@ -11,13 +11,20 @@ const defaultStyles: Styles = {
  fontFamily: 'sans-serif',
  fontSize: 24,
  fontColor: '#000000',
+  fontWeight: 4,
  background: '#dbe2ef',
  opacity: 80,
  showPreview: true,
  transDisplay: true,
  transFontFamily: 'sans-serif',
  transFontSize: 24,
-  transFontColor: '#000000'
+  transFontColor: '#000000',
+  transFontWeight: 4,
+  textShadow: false,
+  offsetX: 2,
+  offsetY: 2,
+  blur: 0,
+  textShadowColor: '#ffffff'
 };

 const defaultControls: Controls = {
@@ -27,6 +34,7 @@ const defaultControls: Controls = {
  audio: 0,
  engineEnabled: false,
  API_KEY: '',
+  modelPath: '',
  translation: true,
  customized: false,
  customizedApp: '',
--- a/src/main/utils/CaptionEngine.ts
+++ b/src/main/utils/CaptionEngine.ts
@@ -13,26 +13,20 @@ export class CaptionEngine {
  processStatus: 'running' | 'stopping' | 'stopped' = 'stopped'

  private getApp(): boolean {
+    allConfig.controls.customized = false
    if (allConfig.controls.customized && allConfig.controls.customizedApp) {
      this.appPath = allConfig.controls.customizedApp
      this.command = [allConfig.controls.customizedCommand]
+      allConfig.controls.customized = true
    }
    else if (allConfig.controls.engine === 'gummy') {
-      allConfig.controls.customized = false
      if(!allConfig.controls.API_KEY && !process.env.DASHSCOPE_API_KEY) {
        controlWindow.sendErrorMessage(i18n('gummy.key.missing'))
        return false
      }
-      let gummyName = ''
+      let gummyName = 'main-gummy'
      if (process.platform === 'win32') {
-        gummyName = 'main-gummy.exe'
-      }
-      else if (process.platform === 'darwin' || process.platform === 'linux') {
-        gummyName = 'main-gummy'
-      }
-      else {
-        controlWindow.sendErrorMessage(i18n('platform.unsupported') + process.platform)
-        throw new Error(i18n('platform.unsupported'))
+        gummyName += '.exe'
      }
      if (is.dev) {
        this.appPath = path.join(
@@ -55,10 +49,29 @@ export class CaptionEngine {
      if(allConfig.controls.API_KEY) {
        this.command.push('-k', allConfig.controls.API_KEY)
      }
-
-      console.log('[INFO] Engine Path:', this.appPath)
-      console.log('[INFO] Engine Command:', this.command)
    }
+    else if(allConfig.controls.engine === 'vosk'){
+      let voskName = 'main-vosk'
+      if (process.platform === 'win32') {
+        voskName += '.exe'
+      }
+      if (is.dev) {
+        this.appPath = path.join(
+          app.getAppPath(),
+          'caption-engine', 'dist', voskName
+        )
+      }
+      else {
+        this.appPath = path.join(
+          process.resourcesPath, 'caption-engine', voskName
+        )
+      }
+      this.command = []
+      this.command.push('-a', allConfig.controls.audio ? '1' : '0')
+      this.command.push('-m', `"${allConfig.controls.modelPath}"`)
+    }
+    console.log('[INFO] Engine Path:', this.appPath)
+    console.log('[INFO] Engine Command:', this.command)
    return true
  }

--- a/src/renderer/src/assets/input.css
+++ b/src/renderer/src/assets/input.css
@@ -11,6 +11,8 @@

 .switch-label {
  display: inline-block;
+  min-width: 80px;
+  text-align: right;
  margin-right: 10px;
 }

--- a/src/renderer/src/components/CaptionStyle.vue
+++ b/src/renderer/src/components/CaptionStyle.vue
@@ -22,6 +22,7 @@
        v-model:value="currentFontFamily"
      />
    </div>
+
    <div class="input-item">
      <span class="input-label">{{ $t('style.fontColor') }}</span>
      <a-input
@@ -41,6 +42,16 @@
      />
      <div class="input-item-value">{{ currentFontSize }}px</div>
    </div>
+    <div class="input-item">
+      <span class="input-label">{{ $t('style.fontWeight') }}</span>
+      <a-input
+        class="input-area"
+        type="range"
+        min="1" max="9"
+        v-model:value="currentFontWeight"
+      />
+      <div class="input-item-value">{{ currentFontWeight*100 }}</div>
+    </div>
    <div class="input-item">
      <span class="input-label">{{ $t('style.background') }}</span>
      <a-input
@@ -70,6 +81,11 @@
        <span class="switch-label">{{ $t('style.translation') }}</span>
        <a-switch v-model:checked="currentTransDisplay" />
      </div>
+      <span style="display:inline-block;width:20px;"></span>
+      <div style="display: inline-block;">
+        <span class="switch-label">{{ $t('style.textShadow') }}</span>
+        <a-switch v-model:checked="currentTextShadow" />
+      </div>
    </div>

    <div v-show="currentTransDisplay">
@@ -103,6 +119,60 @@
          />
          <div class="input-item-value">{{ currentTransFontSize }}px</div>
        </div>
+        <div class="input-item">
+          <span class="input-label">{{ $t('style.fontWeight') }}</span>
+          <a-input
+            class="input-area"
+            type="range"
+            min="1" max="9"
+            v-model:value="currentTransFontWeight"
+          />
+          <div class="input-item-value">{{ currentTransFontWeight*100 }}</div>
+        </div>
+      </a-card>
+    </div>
+
+    <div v-show="currentTextShadow" style="margin-top:10px;">
+      <a-card size="small" :title="$t('style.shadow.title')">
+        <div class="input-item">
+          <span class="input-label">{{ $t('style.shadow.offsetX') }}</span>
+          <a-input
+            class="input-area"
+            type="range"
+            min="-10" max="10"
+            v-model:value="currentOffsetX"
+          />
+          <div class="input-item-value">{{ currentOffsetX }}px</div>
+        </div>
+        <div class="input-item">
+          <span class="input-label">{{ $t('style.shadow.offsetY') }}</span>
+          <a-input
+            class="input-area"
+            type="range"
+            min="-10" max="10"
+            v-model:value="currentOffsetY"
+          />
+          <div class="input-item-value">{{ currentOffsetY }}px</div>
+        </div>
+        <div class="input-item">
+          <span class="input-label">{{ $t('style.shadow.blur') }}</span>
+          <a-input
+            class="input-area"
+            type="range"
+            min="0" max="10"
+            v-model:value="currentBlur"
+          />
+          <div class="input-item-value">{{ currentBlur }}px</div>
+        </div>
+        <div class="input-item">
+          <span class="input-label">{{ $t('style.shadow.color') }}</span>
+          <a-input
+            class="input-area"
+            type="color"
+            v-model:value="currentTextShadowColor"
+          />
+          <div class="input-item-value">{{ currentTextShadowColor }}</div>
+        </div>
      </a-card>
    </div>
  </a-card>
@@ -112,14 +182,16 @@
      v-if="currentPreview"
      class="preview-container"
      :style="{
-        backgroundColor: addOpicityToColor(currentBackground, currentOpacity)
+        backgroundColor: addOpicityToColor(currentBackground, currentOpacity),
+        textShadow: currentTextShadow ? `${currentOffsetX}px ${currentOffsetY}px ${currentBlur}px ${currentTextShadowColor}` : 'none'
      }"
    >
      <p :class="[currentLineBreak?'':'left-ellipsis']"
        :style="{
          fontFamily: currentFontFamily,
          fontSize: currentFontSize + 'px',
-          color: currentFontColor
+          color: currentFontColor,
+          fontWeight: currentFontWeight * 100
      }">
        <span v-if="captionData.length">{{ captionData[captionData.length-1].text }}</span>
        <span v-else>{{ $t('example.original') }}</span>
@@ -129,7 +201,8 @@
        :style="{
          fontFamily: currentTransFontFamily,
          fontSize: currentTransFontSize + 'px',
-          color: currentTransFontColor
+          color: currentTransFontColor,
+          fontWeight: currentTransFontWeight * 100
        }"
      >
        <span v-if="captionData.length">{{ captionData[captionData.length-1].translation }}</span>
@@ -147,7 +220,6 @@ import { storeToRefs } from 'pinia'
 import { notification } from 'ant-design-vue'
 import { useI18n } from 'vue-i18n'
 import { useCaptionLogStore } from '@renderer/stores/captionLog';
-
 const captionLog = useCaptionLogStore();
 const { captionData } = storeToRefs(captionLog);

@@ -160,6 +232,7 @@ const currentLineBreak = ref<number>(0)
 const currentFontFamily = ref<string>('sans-serif')
 const currentFontSize = ref<number>(24)
 const currentFontColor = ref<string>('#000000')
+const currentFontWeight = ref<number>(4)
 const currentBackground = ref<string>('#dbe2ef')
 const currentOpacity = ref<number>(50)
 const currentPreview = ref<boolean>(true)
@@ -167,6 +240,12 @@ const currentTransDisplay = ref<boolean>(true)
 const currentTransFontFamily = ref<string>('sans-serif')
 const currentTransFontSize = ref<number>(24)
 const currentTransFontColor = ref<string>('#000000')
+const currentTransFontWeight = ref<number>(4)
+const currentTextShadow = ref<boolean>(false)
+const currentOffsetX = ref<number>(2)
+const currentOffsetY = ref<number>(2)
+const currentBlur = ref<number>(0)
+const currentTextShadowColor = ref<string>('#ffffff')

 function addOpicityToColor(color: string, opicity: number) {
  const opicityValue = Math.round(opicity * 255 / 100);
@@ -185,6 +264,7 @@ function applyStyle(){
  captionStyle.fontFamily = currentFontFamily.value;
  captionStyle.fontSize = currentFontSize.value;
  captionStyle.fontColor = currentFontColor.value;
+  captionStyle.fontWeight = currentFontWeight.value;
  captionStyle.background = currentBackground.value;
  captionStyle.opacity = currentOpacity.value;
  captionStyle.showPreview = currentPreview.value;
@@ -192,6 +272,12 @@ function applyStyle(){
  captionStyle.transFontFamily = currentTransFontFamily.value;
  captionStyle.transFontSize = currentTransFontSize.value;
  captionStyle.transFontColor = currentTransFontColor.value;
+  captionStyle.transFontWeight = currentTransFontWeight.value;
+  captionStyle.textShadow = currentTextShadow.value;
+  captionStyle.offsetX = currentOffsetX.value;
+  captionStyle.offsetY = currentOffsetY.value;
+  captionStyle.blur = currentBlur.value;
+  captionStyle.textShadowColor = currentTextShadowColor.value;

  captionStyle.sendStylesChange();

@@ -206,6 +292,7 @@ function backStyle(){
  currentFontFamily.value = captionStyle.fontFamily;
  currentFontSize.value = captionStyle.fontSize;
  currentFontColor.value = captionStyle.fontColor;
+  currentFontWeight.value = captionStyle.fontWeight;
  currentBackground.value = captionStyle.background;
  currentOpacity.value = captionStyle.opacity;
  currentPreview.value = captionStyle.showPreview;
@@ -213,6 +300,12 @@ function backStyle(){
  currentTransFontFamily.value = captionStyle.transFontFamily;
  currentTransFontSize.value = captionStyle.transFontSize;
  currentTransFontColor.value = captionStyle.transFontColor;
+  currentTransFontWeight.value = captionStyle.transFontWeight;
+  currentTextShadow.value = captionStyle.textShadow;
+  currentOffsetX.value = captionStyle.offsetX;
+  currentOffsetY.value = captionStyle.offsetY;
+  currentBlur.value = captionStyle.blur;
+  currentTextShadowColor.value = captionStyle.textShadowColor;
 }

 function resetStyle() {
@@ -229,6 +322,16 @@ watch(changeSignal, (val) => {

 <style scoped>
@import url(../assets/input.css);
+.general-note {
+  padding: 10px 10px 0;
+  max-width: min(36vw, 400px);
+}
+
+.hover-label {
+  color: #1668dc;
+  cursor: pointer;
+  font-weight: bold;
+}

 .preview-container {
  line-height: 2em;
--- a/src/renderer/src/components/EngineControl.vue
+++ b/src/renderer/src/components/EngineControl.vue
@@ -16,6 +16,7 @@
    <div class="input-item">
      <span class="input-label">{{ $t('engine.transLang') }}</span>
      <a-select
+        :disabled="currentEngine === 'vosk'"
        class="input-area"
        v-model:value="currentTargetLang"
        :options="langList.filter((item) => item.value !== 'auto')"
@@ -47,15 +48,38 @@
        <a-switch v-model:checked="showMore" />
      </div>
    </div>
-    <a-card size="small" :title="$t('engine.custom.title')" v-show="showMore">
+
+    <a-card size="small" :title="$t('engine.showMore')" v-show="showMore">
      <div class="input-item">
-        <span class="input-label">{{ $t('engine.apikey') }}</span>
+        <a-popover>
+          <template #content>
+            <p class="label-hover-info">{{ $t('engine.apikeyInfo') }}</p>
+          </template>
+          <span class="input-label info-label">{{ $t('engine.apikey') }}</span>
+        </a-popover>
        <a-input
          class="input-area"
          type="password"
          v-model:value="currentAPI_KEY"
        />
      </div>
+      <div class="input-item">
+        <a-popover>
+          <template #content>
+            <p class="label-hover-info">{{ $t('engine.modelPathInfo') }}</p>
+          </template>
+          <span class="input-label info-label">{{ $t('engine.modelPath') }}</span>
+        </a-popover>
+        <span
+          class="input-folder"
+          @click="selectFolderPath"
+        ><span><FolderOpenOutlined /></span></span>
+        <a-input
+          class="input-area"
+          style="width:calc(100% - 140px);"
+          v-model:value="currentModelPath"
+        />
+      </div>
      <div class="input-item">
        <span style="margin-right:5px;">{{ $t('engine.customEngine') }}</span>
        <a-switch v-model:checked="currentCustomized" />
@@ -85,9 +109,8 @@
            ></a-input>
          </div>
        </a-card>
-      </div>      
+      </div>
    </a-card>
-
  </a-card>
  <div style="height: 20px;"></div>
 </template>
@@ -95,9 +118,10 @@
 <script setup lang="ts">
 import { ref, computed, watch } from 'vue'
 import { storeToRefs } from 'pinia'
+import { useGeneralSettingStore } from '@renderer/stores/generalSetting'
 import { useEngineControlStore } from '@renderer/stores/engineControl'
 import { notification } from 'ant-design-vue'
-import { InfoCircleOutlined } from '@ant-design/icons-vue';
+import { FolderOpenOutlined ,InfoCircleOutlined } from '@ant-design/icons-vue';
 import { useI18n } from 'vue-i18n'

 const { t } = useI18n()
@@ -108,10 +132,11 @@ const { platform, captionEngine, audioType, changeSignal } = storeToRefs(engineC

 const currentSourceLang = ref('auto')
 const currentTargetLang = ref('zh')
-const currentEngine = ref<'gummy'>('gummy')
+const currentEngine = ref<string>('gummy')
 const currentAudio = ref<0 | 1>(0)
 const currentTranslation = ref<boolean>(false)
 const currentAPI_KEY = ref<string>('')
+const currentModelPath = ref<string>('')
 const currentCustomized = ref<boolean>(false)
 const currentCustomizedApp = ref('')
 const currentCustomizedCommand = ref('')
@@ -132,6 +157,7 @@ function applyChange(){
  engineControl.audio = currentAudio.value
  engineControl.translation = currentTranslation.value
  engineControl.API_KEY = currentAPI_KEY.value
+  engineControl.modelPath = currentModelPath.value
  engineControl.customized = currentCustomized.value
  engineControl.customizedApp = currentCustomizedApp.value
  engineControl.customizedCommand = currentCustomizedCommand.value
@@ -151,22 +177,70 @@ function cancelChange(){
  currentAudio.value = engineControl.audio
  currentTranslation.value = engineControl.translation
  currentAPI_KEY.value = engineControl.API_KEY
+  currentModelPath.value = engineControl.modelPath
  currentCustomized.value = engineControl.customized
  currentCustomizedApp.value = engineControl.customizedApp
  currentCustomizedCommand.value = engineControl.customizedCommand
 }

+function selectFolderPath() {
+  window.electron.ipcRenderer.invoke('control.folder.select').then((folderPath) => {
+    if(!folderPath) return
+    currentModelPath.value = folderPath
+  })
+}
+
 watch(changeSignal, (val) => {
  if(val == true) {
    cancelChange();
    engineControl.changeSignal = false;
  }
 })
+
+watch(currentEngine, (val) => {
+  if(val == 'vosk'){
+    currentSourceLang.value = 'auto'
+    currentTargetLang.value = ''
+  }
+  else if(val == 'gummy'){
+    currentSourceLang.value = 'auto'
+    currentTargetLang.value = useGeneralSettingStore().uiLanguage
+  }
+})
 </script>

 <style scoped>
@import url(../assets/input.css);

+.label-hover-info {
+  margin-top: 10px;
+  max-width: min(36vw, 380px);
+}
+
+.info-label {
+  color: #1677ff;
+  cursor: pointer;
+}
+
+.input-folder {
+  display:inline-block;
+  width: 40px;
+  font-size:1.38em;
+  cursor: pointer;
+  transition: all 0.25s;
+}
+
+.input-folder>span {
+  padding: 0 4px;
+  border: 2px solid #1677ff;
+  color: #1677ff;
+  border-radius: 30%;
+}
+
+.input-folder:hover {
+  transform: scale(1.1);
+}
+
 .customize-note {
  padding: 10px 10px 0;
  color: red;
--- a/src/renderer/src/components/EngineStatus.vue
+++ b/src/renderer/src/components/EngineStatus.vue
@@ -47,7 +47,7 @@
      <p class="about-desc">{{ $t('status.about.desc') }}</p>
      <a-divider />
      <div class="about-info">
-        <p><b>{{ $t('status.about.version') }}</b><a-tag color="green">v0.2.0</a-tag></p>
+        <p><b>{{ $t('status.about.version') }}</b><a-tag color="green">v0.3.0</a-tag></p>
        <p>
          <b>{{ $t('status.about.author') }}</b>
          <a
@@ -106,6 +106,11 @@ function openCaptionWindow() {
 }

 function startEngine() {
+  console.log(`@@${engineControl.modelPath}##`)
+  if(engineControl.modelPath.trim() === '') {
+    engineControl.emptyModelPathErr()
+    return
+  }
  window.electron.ipcRenderer.send('control.engine.start')
 }

--- a/src/renderer/src/i18n/config/engine.ts
+++ b/src/renderer/src/i18n/config/engine.ts
@@ -16,6 +16,13 @@ export const engines = {
        { value: 'it', label: '意大利语' },
      ]
    },
+    {
+      value: 'vosk',
+      label: '本地 -  Vosk',
+      languages: [
+        { value: 'auto', label: '需要自行配置模型' },
+      ]
+    }
  ],
  en: [
    {
@@ -34,6 +41,13 @@ export const engines = {
        { value: 'it', label: 'Italian' },
      ]
    },
+    {
+      value: 'vosk',
+      label: 'Local - Vosk',
+      languages: [
+        { value: 'auto', label: 'Model needs to be configured manually' },
+      ]
+    }
  ],
  ja: [
    {
@@ -52,6 +66,13 @@ export const engines = {
        { value: 'it', label: 'イタリア語' },
      ]
    },
+    {
+      value: 'vosk',
+      label: 'ローカル - Vosk',
+      languages: [
+        { value: 'auto', label: 'モデルを手動で設定する必要があります' },
+      ]
+    }
  ]
 }

--- a/src/renderer/src/i18n/lang/en.ts
+++ b/src/renderer/src/i18n/lang/en.ts
@@ -17,6 +17,8 @@ export default {
    "custom": "Type: Custom engine, engine path: ",
    "args": ", command arguments: ",
    "pidInfo": ", caption engine process PID: ",
+    "empty": "Model Path is Empty",
+    "emptyInfo": "The Vosk model path is empty. Please set the Vosk model path in the additional settings of the subtitle engine settings.",
    "stopped": "Caption Engine Stopped",
    "stoppedInfo": "The caption engine has stopped. You can click the 'Start Caption Engine' button to restart it.",
    "error": "An error occurred",
@@ -48,6 +50,9 @@ export default {
    "enableTranslation": "Translation",
    "showMore": "More Settings",
    "apikey": "API KEY",
+    "modelPath": "Model Path",
+    "apikeyInfo": "API KEY required for the Gummy subtitle engine, which needs to be obtained from the Alibaba Cloud Bailing platform. For more details, see the project user manual.",
+    "modelPathInfo": "The folder path of the model required by the Vosk subtitle engine. You need to download the required model to your local machine in advance. For more details, see the project user manual.",
    "customEngine": "Custom Engine",
    custom: {
      "title": "Custom Caption Engine",
@@ -66,6 +71,7 @@ export default {
    "fontFamily": "Font Family",
    "fontColor": "Font Color",
    "fontSize": "Font Size",
+    "fontWeight": "Font Weight",
    "background": "Background",
    "opacity": "Opacity",
    "preview": "Preview",
@@ -73,6 +79,14 @@ export default {
    trans: {
      "title": "Translation Style Settings",
      "useSame": "Use Original Style"
+    },
+    "textShadow": "Text Shadow",
+    shadow: {
+      "title": "Text Shadow Settings",
+      "offsetX": "Offset X",
+      "offsetY": "Offset Y",
+      "blur": "Blur",
+      "color": "Color"
    }
  },
  status: {
@@ -96,7 +110,7 @@ export default {
      "projLink": "Project Link",
      "manual": "User Manual",
      "engineDoc": "Caption Engine Manual",
-      "date": "July 5, 2026"
+      "date": "July 9, 2026"
    }
  },
  log: {
--- a/src/renderer/src/i18n/lang/ja.ts
+++ b/src/renderer/src/i18n/lang/ja.ts
@@ -17,6 +17,8 @@ export default {
    "custom": "タイプ：カスタムエンジン、エンジンパス：",
    "args": "、コマンド引数：",
    "pidInfo": "、字幕エンジンプロセス PID：",
+    "empty": "モデルパスが空です",
+    "emptyInfo": "Vosk モデルのパスが空です。字幕エンジン設定の追加設定で Vosk モデルのパスを設定してください。",
    "stopped": "字幕エンジンが停止しました",
    "stoppedInfo": "字幕エンジンが停止しました。再起動するには「字幕エンジンを開始」ボタンをクリックしてください。",
    "error": "エラーが発生しました",
@@ -48,6 +50,9 @@ export default {
    "enableTranslation": "翻訳",
    "showMore": "詳細設定",
    "apikey": "API KEY",
+    "modelPath": "モデルパス",
+    "apikeyInfo": "Gummy 字幕エンジンに必要な API KEY は、アリババクラウド百煉プラットフォームから取得する必要があります。詳細情報はプロジェクトのユーザーマニュアルをご覧ください。",
+    "modelPathInfo": "Vosk 字幕エンジンに必要なモデルのフォルダパスです。必要なモデルを事前にローカルマシンにダウンロードする必要があります。詳細情報はプロジェクトのユーザーマニュアルをご覧ください。",
    "customEngine": "カスタムエンジン",
    custom: {
      "title": "カスタムキャプションエンジン",
@@ -66,6 +71,7 @@ export default {
    "fontFamily": "フォント",
    "fontColor": "カラー",
    "fontSize": "サイズ",
+    "fontWeight": "文字の太さ",
    "background": "背景色",
    "opacity": "不透明度",
    "preview": "プレビュー",
@@ -73,6 +79,14 @@ export default {
    trans: {
      "title": "翻訳スタイル設定",
      "useSame": "原文のスタイルを使用"
+    },
+    "textShadow": "文字影",
+    shadow: {
+      "title": "テキストの影設定",
+      "offsetX": "Offset X",
+      "offsetY": "Offset Y",
+      "blur": "ぼかし半径",
+      "color": "影の色"
    }
  },
  status: {
@@ -96,7 +110,7 @@ export default {
      "projLink": "プロジェクトリンク",
      "manual": "ユーザーマニュアル",
      "engineDoc": "字幕エンジンマニュアル",
-      "date": "2025 年 7 月 5 日"
+      "date": "2025 年 7 月 9 日"
    }
  },
  log: {
--- a/src/renderer/src/i18n/lang/zh.ts
+++ b/src/renderer/src/i18n/lang/zh.ts
@@ -17,6 +17,8 @@ export default {
    "custom": "类型：自定义引擎，引擎路径：",
    "args": "，命令参数：",
    "pidInfo": "，字幕引擎进程 PID：",
+    "empty": "模型路径为空",
+    "emptyInfo": "Vosk 模型模型路径为空，请在字幕引擎设置的更多设置中设置 Vosk 模型的路径。",
    "stopped": "字幕引擎停止",
    "stoppedInfo": "字幕引擎已经停止，可点击“启动字幕引擎”按钮重新启动",
    "error": "发生错误",
@@ -48,6 +50,9 @@ export default {
    "enableTranslation": "启用翻译",
    "showMore": "更多设置",
    "apikey": "API KEY",
+    "modelPath": "模型路径",
+    "apikeyInfo": "Gummy 字幕引擎需要的 API KEY，需要在阿里云百炼平台获取。详细信息见项目用户手册。",
+    "modelPathInfo": "Vosk 字幕引擎需要的模型的文件夹路径，需要提前下载需要的模型到本地。信息详情见项目用户手册。",
    "customEngine": "自定义引擎",
    custom: {
      "title": "自定义字幕引擎",
@@ -66,6 +71,7 @@ export default {
    "fontFamily": "字体族",
    "fontColor": "字体颜色",
    "fontSize": "字体大小",
+    "fontWeight": "字体粗细",
    "background": "背景颜色",
    "opacity": "不透明度",
    "preview": "显示预览",
@@ -73,6 +79,14 @@ export default {
    trans: {
      "title": "翻译样式设置",
      "useSame": "使用原文样式"
+    },
+    "textShadow": "文本阴影",
+    shadow: {
+      "title": "文本阴影设置",
+      "offsetX": "X轴偏移",
+      "offsetY": "Y轴偏移",
+      "blur": "模糊半径",
+      "color": "阴影颜色"
    }
  },
  status: {
@@ -96,7 +110,7 @@ export default {
      "projLink": "项目链接",
      "manual": "用户手册",
      "engineDoc": "字幕引擎手册",
-      "date": "2025 年 7 月 5 日"
+      "date": "2025 年 7 月 9 日"
    }
  },
  log: {
--- a/src/renderer/src/stores/captionStyle.ts
+++ b/src/renderer/src/stores/captionStyle.ts
@@ -8,6 +8,7 @@ export const useCaptionStyleStore = defineStore('captionStyle', () => {
  const fontFamily = ref<string>('sans-serif')
  const fontSize = ref<number>(24)
  const fontColor = ref<string>('#000000')
+  const fontWeight = ref<number>(4)
  const background = ref<string>('#dbe2ef')
  const opacity = ref<number>(80)
  const showPreview = ref<boolean>(true)
@@ -15,6 +16,12 @@ export const useCaptionStyleStore = defineStore('captionStyle', () => {
  const transFontFamily = ref<string>('sans-serif')
  const transFontSize = ref<number>(24)
  const transFontColor = ref<string>('#000000')
+  const transFontWeight = ref<number>(4)
+  const textShadow = ref<boolean>(false)
+  const offsetX = ref<number>(2)
+  const offsetY = ref<number>(2)
+  const blur = ref<number>(0)
+  const textShadowColor = ref<string>('#ffffff')

  const iBreakOptions = ref(breakOptions['zh'])
  const changeSignal = ref<boolean>(false)
@@ -35,13 +42,20 @@ export const useCaptionStyleStore = defineStore('captionStyle', () => {
      fontFamily: fontFamily.value,
      fontSize: fontSize.value,
      fontColor: fontColor.value,
+      fontWeight: fontWeight.value,
      background: background.value,
      opacity: opacity.value,
      showPreview: showPreview.value,
      transDisplay: transDisplay.value,
      transFontFamily: transFontFamily.value,
      transFontSize: transFontSize.value,
-      transFontColor: transFontColor.value
+      transFontColor: transFontColor.value,
+      transFontWeight: transFontWeight.value,
+      textShadow: textShadow.value,
+      offsetX: offsetX.value,
+      offsetY: offsetY.value,
+      blur: blur.value,
+      textShadowColor: textShadowColor.value
    }
    window.electron.ipcRenderer.send('control.styles.change', styles)
  }
@@ -55,13 +69,20 @@ export const useCaptionStyleStore = defineStore('captionStyle', () => {
    fontFamily.value = args.fontFamily
    fontSize.value = args.fontSize
    fontColor.value = args.fontColor
+    fontWeight.value = args.fontWeight
    background.value = args.background
    opacity.value = args.opacity
    showPreview.value = args.showPreview
    transDisplay.value = args.transDisplay
    transFontFamily.value = args.transFontFamily
    transFontSize.value = args.transFontSize
-    transFontColor.value = args.transFontColor
+    transFontColor.value = args.transFontColor,
+    transFontWeight.value = args.transFontWeight
+    textShadow.value = args.textShadow
+    offsetX.value = args.offsetX
+    offsetY.value = args.offsetY
+    blur.value = args.blur
+    textShadowColor.value = args.textShadowColor
    changeSignal.value = true
  }

@@ -74,6 +95,7 @@ export const useCaptionStyleStore = defineStore('captionStyle', () => {
    fontFamily,         // 字体族
    fontSize,           // 字体大小
    fontColor,          // 字体颜色
+    fontWeight,         // 字体粗细
    background,         // 背景颜色
    opacity,            // 背景透明度
    showPreview,        // 是否显示预览
@@ -81,6 +103,12 @@ export const useCaptionStyleStore = defineStore('captionStyle', () => {
    transFontFamily,    // 翻译字体族
    transFontSize,      // 翻译字体大小
    transFontColor,     // 翻译字体颜色
+    transFontWeight,    // 翻译字体粗细
+    textShadow,         // 是否显示文本阴影
+    offsetX,            // 阴影X轴偏移
+    offsetY,            // 阴影Y轴偏移
+    blur,               // 阴影模糊度半径
+    textShadowColor,    // 阴影颜色
    backgroundRGBA,     // 带透明度的背景颜色
    setStyles,          // 设置样式
    sendStylesChange,   // 发送样式改变
--- a/src/renderer/src/stores/engineControl.ts
+++ b/src/renderer/src/stores/engineControl.ts
@@ -16,13 +16,14 @@ export const useEngineControlStore = defineStore('engineControl', () => {

  const captionEngine = ref(engines[useGeneralSettingStore().uiLanguage])
  const audioType = ref(audioTypes[useGeneralSettingStore().uiLanguage])
-  const API_KEY = ref<string>('')
  const engineEnabled = ref(false)
  const sourceLang = ref<string>('en')
  const targetLang = ref<string>('zh')
-  const engine = ref<'gummy'>('gummy')
+  const engine = ref<string>('gummy')
  const audio = ref<0 | 1>(0)
  const translation = ref<boolean>(true)
+  const API_KEY = ref<string>('')
+  const modelPath = ref<string>('')
  const customized = ref<boolean>(false)
  const customizedApp = ref<string>('')
  const customizedCommand = ref<string>('')
@@ -38,6 +39,7 @@ export const useEngineControlStore = defineStore('engineControl', () => {
      audio: audio.value,
      translation: translation.value,
      API_KEY: API_KEY.value,
+      modelPath: modelPath.value,
      customized: customized.value,
      customizedApp: customizedApp.value,
      customizedCommand: customizedCommand.value
@@ -53,12 +55,20 @@ export const useEngineControlStore = defineStore('engineControl', () => {
    engineEnabled.value = controls.engineEnabled
    translation.value = controls.translation
    API_KEY.value = controls.API_KEY
+    modelPath.value = controls.modelPath
    customized.value = controls.customized
    customizedApp.value = controls.customizedApp
    customizedCommand.value = controls.customizedCommand
    changeSignal.value = true
  }

+  function emptyModelPathErr() {
+    notification.open({
+      message: t('noti.empty'),
+      description: t('noti.emptyInfo')
+    });
+  }
+
  window.electron.ipcRenderer.on('control.controls.set', (_, controls: Controls) => {
    setControls(controls)
  })
@@ -102,7 +112,7 @@ export const useEngineControlStore = defineStore('engineControl', () => {

  return {
    platform,           // 系统平台
-    captionEngine,      // 字幕引擎
+    captionEngine,      // 字幕引擎列表
    audioType,          // 音频类型
    engineEnabled,      // 字幕引擎是否启用
    sourceLang,         // 源语言
@@ -111,11 +121,13 @@ export const useEngineControlStore = defineStore('engineControl', () => {
    audio,              // 选择音频
    translation,        // 是否启用翻译
    API_KEY,            // API KEY
+    modelPath,          // vosk 模型路径
    customized,         // 是否使用自定义字幕引擎
    customizedApp,      // 自定义字幕引擎的应用程序
    customizedCommand,  // 自定义字幕引擎的命令
    setControls,        // 设置引擎配置
    sendControlsChange, // 发送最新控制消息到后端
+    emptyModelPathErr,  // 模型路径为空时显示警告
    changeSignal,       // 配置改变信号
  }
 })
--- a/src/renderer/src/stores/generalSetting.ts
+++ b/src/renderer/src/stores/generalSetting.ts
@@ -14,6 +14,11 @@ export const useGeneralSettingStore = defineStore('generalSetting', () => {

  const antdTheme = ref<Object>(antDesignTheme['light'])

+  window.electron.ipcRenderer.invoke('control.nativeTheme.get').then((theme) => {
+    if(theme === 'light') setLightTheme()
+    else if(theme === 'dark') setDarkTheme()
+  })
+
  watch(uiLanguage, (newValue) => {
    i18n.global.locale.value = newValue
    useEngineControlStore().captionEngine = engines[newValue]
--- a/src/renderer/src/types/index.ts
+++ b/src/renderer/src/types/index.ts
@@ -6,10 +6,11 @@ export interface Controls {
  engineEnabled: boolean,
  sourceLang: string,
  targetLang: string,
-  engine: 'gummy',
+  engine: string,
  audio: 0 | 1,
  translation: boolean,
  API_KEY: string,
+  modelPath: string,
  customized: boolean,
  customizedApp: string,
  customizedCommand: string
@@ -20,13 +21,20 @@ export interface Styles {
  fontFamily: string,
  fontSize: number,
  fontColor: string,
+  fontWeight: number,
  background: string,
  opacity: number,
  showPreview: boolean,
  transDisplay: boolean,
  transFontFamily: string,
  transFontSize: number,
-  transFontColor: string
+  transFontColor: string,
+  transFontWeight: number,
+  textShadow: boolean,
+  offsetX: number,
+  offsetY: number,
+  blur: number,
+  textShadowColor: string
 }

 export interface CaptionItem {
--- a/src/renderer/src/views/CaptionPage.vue
+++ b/src/renderer/src/views/CaptionPage.vue
@@ -19,11 +19,17 @@
        <CloseOutlined />
      </div>
    </div>
-    <div class="caption-container">
+    <div
+      class="caption-container"
+      :style="{
+        textShadow: captionStyle.textShadow ? `${captionStyle.offsetX}px ${captionStyle.offsetY}px ${captionStyle.blur}px ${captionStyle.textShadowColor}` : 'none'
+      }"
+    >
      <p :class="[captionStyle.lineBreak?'':'left-ellipsis']" :style="{
        fontFamily: captionStyle.fontFamily,
        fontSize: captionStyle.fontSize + 'px',
-        color: captionStyle.fontColor
+        color: captionStyle.fontColor,
+        fontWeight: captionStyle.fontWeight * 100
      }">
        <span v-if="captionData.length">{{ captionData[captionData.length-1].text }}</span>
        <span v-else>{{ $t('example.original') }}</span>
@@ -33,7 +39,8 @@
        :style="{
        fontFamily: captionStyle.transFontFamily,
        fontSize: captionStyle.transFontSize + 'px',
-        color: captionStyle.transFontColor
+        color: captionStyle.transFontColor,
+        fontWeight: captionStyle.transFontWeight * 100
      }">
        <span v-if="captionData.length">{{ captionData[captionData.length-1].translation }}</span>
        <span v-else>{{ $t('example.translation') }}</span>
Author	SHA1	Message	Date
himeditator	d354a6fefa	feat(engine): 优化 Vosk 字幕引擎支持 - 实现文件夹选择功能，用于选择 Vosk 模型路径 - 在 EngineControl 组件中添加模型路径选择按钮和相关提示 - 在 EngineStatus 组件中增加对空模型路径的检查和错误提示	2025-07-10 11:22:39 +08:00
himeditator	1c29fd5adc	feat(engine): 添加 Vosk 本地离线引擎支持 - 新增 Vosk 引擎配置和识别逻辑 - 更新用户界面，增加 Vosk 引擎选项和模型路径设置 - 更新依赖，添加 vosk 库	2025-07-09 19:53:30 +08:00
himeditator	f97b885411	release v0.3.0 - 在 README中更新访问者徽章的 page_id 为正确的项目路径 - 修改 electron-builder.yml 中的 extraResources 配置	2025-07-09 02:34:15 +08:00
himeditator	606f9b480b	release v0.3.0 - 新增字幕字体粗细、文本阴影等设置选项 - 更新相关文档，增加新功能说明 - 修复系统主题载入颜色bug	2025-07-09 01:33:21 +08:00
Chen Janai	546beb3112	Merge pull request #6 from HiMeditator/mac-adaption Mac Adaption	2025-07-08 22:46:51 +08:00