Add Voxtral Realtime Windows WPF application

Author: seyeong-han

.gitignore

@@ -1,5 +1,10 @@
 # System files
 .DS_Store
+*.png
+
+# IDE / editor settings
+.claude/
+.vs/
 
 # Python environment
 .venv/
@@ -37,3 +42,30 @@ local.properties
 node_modules/
 __pycache__/
 .cursor/
+
+# .NET / C# / Visual Studio
+[Bb]in/
+[Oo]bj/
+[Dd]ebug/
+[Rr]elease/
+*.dll
+*.exe
+*.pdb
+*.cache
+*.baml
+*.resources
+*.user
+*.suo
+*.nupkg
+*.snupkg
+*.g.cs
+*.g.resources
+*.AssemblyInfo.cs
+*.editorconfig
+project.assets.json
+project.nuget.cache
+*.nuget.dgspec.json
+*.nuget.g.props
+*.nuget.g.targets
+publish/
+.vs/

WINDOWS_APP_SKILLS.md

@@ -0,0 +1,73 @@
+Windows App Developer
+Purpose
+Provides expertise in building modern Windows desktop applications using WinUI 3, WPF, and Windows App SDK. Specializes in XAML-based UI development, MVVM architecture, native Windows integration, and modern packaging with MSIX.
+
+When to Use
+Building Windows desktop applications with WinUI 3 or WPF
+Implementing MVVM architecture for Windows apps
+Creating XAML layouts and custom controls
+Packaging applications with MSIX
+Integrating with Windows features (notifications, taskbar, system tray)
+Migrating WPF applications to WinUI 3
+Implementing Windows-specific features (jump lists, live tiles)
+Building Microsoft Store-ready applications
+Quick Start
+Invoke this skill when:
+
+Building Windows desktop applications with WinUI 3 or WPF
+Implementing MVVM architecture for Windows apps
+Creating XAML layouts and custom controls
+Packaging applications with MSIX
+Integrating with Windows features (notifications, taskbar)
+Do NOT invoke when:
+
+Building cross-platform apps → use mobile-developer or electron-pro
+Console applications → use appropriate language skill
+PowerShell GUI → use powershell-ui-architect
+Web applications → use appropriate web skill
+Decision Framework
+Windows App Task?
+├── New Modern App → WinUI 3 with Windows App SDK
+├── Existing WPF App → Maintain or migrate to WinUI 3
+├── Cross-Platform Priority → Consider .NET MAUI
+├── Enterprise Internal → WPF with proven patterns
+├── Store Distribution → MSIX packaging required
+└── System Integration → P/Invoke or Windows SDK APIs
+Core Workflows
+1. WinUI 3 Application Setup
+Create project using Windows App SDK template
+Configure Package.appxmanifest for capabilities
+Set up MVVM infrastructure (CommunityToolkit.Mvvm)
+Implement navigation and shell structure
+Create reusable control library
+Configure MSIX packaging
+Set up CI/CD for Store or sideload distribution
+2. MVVM Implementation
+Define ViewModels with observable properties
+Implement commands for user actions
+Create services for data and business logic
+Set up dependency injection container
+Bind Views to ViewModels in XAML
+Implement navigation service
+Add design-time data for XAML preview
+3. MSIX Packaging
+Configure Package.appxmanifest
+Define application identity and capabilities
+Set up visual assets (icons, splash)
+Configure installation behavior
+Sign package with certificate
+Test installation and updates
+Submit to Microsoft Store or deploy internally
+Best Practices
+Use WinUI 3 for new development, WPF for legacy maintenance
+Implement MVVM strictly for testability and separation
+Use x:Bind for compile-time binding validation
+Leverage Community Toolkit for common patterns
+Package with MSIX for modern installation experience
+Follow Fluent Design System for consistent UX
+Anti-Patterns
+Code-behind logic → Move to ViewModels
+Synchronous UI operations → Use async/await for I/O
+Direct service calls from Views → Go through ViewModels
+Ignoring DPI awareness → Test at multiple scale factors
+Missing capabilities → Declare required capabilities in manifest

voxtral_realtime/windows/README.md

@@ -0,0 +1,119 @@
+# Voxtral Realtime - Windows CUDA
+
+Real-time speech transcription desktop app powered by ExecuTorch with CUDA acceleration.
+
+This is the Windows equivalent of the [macOS Voxtral Realtime app](../macos/).
+
+## Quick Start (Pre-built Release)
+
+Download `VoxtralRealtime.exe` from the [Releases](https://github.com/meta-pytorch/executorch-examples/releases) page and run it directly. No installation required.
+
+You also need:
+- The `voxtral_realtime_runner.exe` (built from ExecuTorch with CUDA support)
+- Model files from HuggingFace (see [Model Files](#model-files) below)
+
+## Prerequisites
+
+- Windows 10/11 with NVIDIA GPU (CUDA-capable)
+- CUDA Toolkit installed (auto-detected from `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\`)
+- [.NET 8.0 SDK](https://dotnet.microsoft.com/download/dotnet/8.0) (only for building from source)
+
+## Model Files
+
+Download from HuggingFace:
+
+```powershell
+pip install huggingface_hub
+huggingface-cli download younghan-meta/Voxtral-Mini-4B-Realtime-2602-ExecuTorch-CUDA --local-dir voxtral_rt_exports
+```
+
+This downloads: `model.pte`, `preprocessor.pte`, `aoti_cuda_blob.ptd`
+
+You also need the tokenizer from the base model:
+
+```powershell
+huggingface-cli download mistralai/Voxtral-Mini-4B-Realtime-2602 tekken.json --local-dir voxtral_tokenizer
+```
+
+## Building the Runner
+
+Build the `voxtral_realtime_runner.exe` from the ExecuTorch repo:
+
+```bash
+cd executorch
+cmake --preset voxtral-realtime-cuda
+cmake --build --preset voxtral-realtime-cuda
+```
+
+The runner will be at `cmake-out/examples/models/voxtral_realtime/Release/voxtral_realtime_runner.exe`.
+
+## Build from Source
+
+```powershell
+# Install .NET SDK if not already installed
+winget install Microsoft.DotNet.SDK.8
+
+# Build
+cd VoxtralRealtime
+dotnet restore
+dotnet build --configuration Release
+
+# Run
+dotnet run --project VoxtralRealtime --configuration Release
+```
+
+## Publish Standalone Executable
+
+Create a single self-contained exe (no .NET runtime required on target machine):
+
+```powershell
+cd VoxtralRealtime
+dotnet publish VoxtralRealtime --configuration Release --runtime win-x64 --self-contained true /p:PublishSingleFile=true /p:IncludeNativeLibrariesForSelfExtract=true /p:DebugType=none -o publish
+```
+
+The output `publish\VoxtralRealtime.exe` can be distributed and run on any Windows x64 machine.
+
+## Configuration
+
+On first launch, the app auto-loads the model from default paths. All paths are configurable in Settings:
+
+| File | Default Path |
+|------|-------------|
+| Runner | `cmake-out\examples\models\voxtral_realtime\Release\voxtral_realtime_runner.exe` |
+| Model | `voxtral_rt_exports_wsl\model.pte` |
+| Preprocessor | `voxtral_rt_exports_wsl\preprocessor.pte` |
+| CUDA blob | `voxtral_rt_exports_wsl\aoti_cuda_blob.ptd` |
+| Tokenizer | `tekken.json` |
+
+## Features
+
+- **Live Transcription** - Start/Pause/Resume with streaming text output
+- **Session Management** - Save, rename, pin, delete, and export sessions (TXT/JSON/SRT)
+- **Text Replacements** - Auto-correct transcription (e.g., "executorch" -> "ExecuTorch")
+- **Text Snippets** - Voice-triggered templates for common text blocks
+- **Dictation Mode** - Ctrl+Space global hotkey, floating overlay, auto-paste to any app, auto-stop on 2s silence
+- **Audio Level Visualization** - Real-time waveform display
+
+## Keyboard Shortcuts
+
+| Shortcut | Action |
+|----------|--------|
+| Ctrl+Shift+R | Start / Resume transcription |
+| Ctrl+. | Pause transcription |
+| Ctrl+Enter | End session |
+| Ctrl+Space | Toggle dictation mode |
+
+## Architecture
+
+The app wraps the `voxtral_realtime_runner.exe` C++ binary via stdin/stdout pipes:
+
+```
+Microphone (WASAPI 48kHz) -> Resample to 16kHz mono f32le -> stdin pipe -> runner.exe -> stdout tokens -> WPF UI
+```
+
+Platform-specific adaptations from the macOS app:
+- **Audio**: WASAPI (shared mode) replaces AVAudioEngine, with software resampling from native rate to 16kHz
+- **Hotkey**: Win32 `RegisterHotKey` replaces Carbon `RegisterEventHotKey`
+- **UI**: WPF (.NET 8) with MVVM replaces SwiftUI
+- **Backend**: `--data_path` for CUDA blob (macOS uses Metal backend)
+- **Stdin**: Binary mode (`_setmode`) required on Windows to prevent 0x1A byte (Ctrl+Z) from being interpreted as EOF

voxtral_realtime/windows/VoxtralRealtime/VoxtralRealtime.sln

@@ -0,0 +1,19 @@
+
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 17
+VisualStudioVersion = 17.0.31903.59
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "VoxtralRealtime", "VoxtralRealtime\VoxtralRealtime.csproj", "{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|Any CPU = Debug|Any CPU
+		Release|Any CPU = Release|Any CPU
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}.Release|Any CPU.Build.0 = Release|Any CPU
+	EndGlobalSection
+EndGlobal

voxtral_realtime/windows/VoxtralRealtime/VoxtralRealtime/App.xaml

@@ -0,0 +1,17 @@
+<!-- Copyright (c) Meta Platforms, Inc. and affiliates. -->
+<!-- All rights reserved. -->
+<!-- This source code is licensed under the BSD-style license found in the -->
+<!-- LICENSE file in the root directory of this source tree. -->
+
+<Application x:Class="VoxtralRealtime.App"
+             xmlns="http://schemas.microsoft.com/winfx/2006/xaml/presentation"
+             xmlns:x="http://schemas.microsoft.com/winfx/2006/xaml"
+             StartupUri="Views/MainWindow.xaml">
+    <Application.Resources>
+        <ResourceDictionary>
+            <ResourceDictionary.MergedDictionaries>
+                <ResourceDictionary Source="Resources/Styles.xaml"/>
+            </ResourceDictionary.MergedDictionaries>
+        </ResourceDictionary>
+    </Application.Resources>
+</Application>

voxtral_realtime/windows/VoxtralRealtime/VoxtralRealtime/App.xaml.cs

@@ -0,0 +1,49 @@
+// Copyright (c) Meta Platforms, Inc. and affiliates.
+// All rights reserved.
+// This source code is licensed under the BSD-style license found in the
+// LICENSE file in the root directory of this source tree.
+
+using System.Runtime.InteropServices;
+using System.Windows;
+using VoxtralRealtime.Services;
+using VoxtralRealtime.ViewModels;
+
+namespace VoxtralRealtime;
+
+public partial class App : Application
+{
+    [DllImport("kernel32.dll")]
+    private static extern bool AttachConsole(int dwProcessId);
+    private const int ATTACH_PARENT_PROCESS = -1;
+    public static SettingsViewModel Settings { get; private set; } = null!;
+    public static ReplacementStoreViewModel ReplacementStore { get; private set; } = null!;
+    public static SnippetStoreViewModel SnippetStore { get; private set; } = null!;
+    public static TextPipeline TextPipeline { get; private set; } = null!;
+    public static TranscriptStoreViewModel Store { get; private set; } = null!;
+    public static DictationViewModel Dictation { get; private set; } = null!;
+    public static GlobalHotkeyService HotkeyService { get; private set; } = null!;
+
+    protected override void OnStartup(StartupEventArgs e)
+    {
+        base.OnStartup(e);
+
+        // Attach to parent console so Console.WriteLine shows in the terminal
+        AttachConsole(ATTACH_PARENT_PROCESS);
+        AppLogger.Log("App", "Voxtral Realtime starting up");
+
+        Settings = new SettingsViewModel();
+        ReplacementStore = new ReplacementStoreViewModel();
+        SnippetStore = new SnippetStoreViewModel();
+        TextPipeline = new TextPipeline(ReplacementStore, SnippetStore);
+        Store = new TranscriptStoreViewModel(Settings, TextPipeline);
+        HotkeyService = new GlobalHotkeyService();
+        Dictation = new DictationViewModel(Store, Settings, HotkeyService);
+    }
+
+    protected override void OnExit(ExitEventArgs e)
+    {
+        Dictation.Cleanup();
+        Store.Shutdown();
+        base.OnExit(e);
+    }
+}

voxtral_realtime/windows/VoxtralRealtime/VoxtralRealtime/Converters/BoolToVisibilityConverter.cs

@@ -0,0 +1,70 @@
+// Copyright (c) Meta Platforms, Inc. and affiliates.
+// All rights reserved.
+// This source code is licensed under the BSD-style license found in the
+// LICENSE file in the root directory of this source tree.
+
+using System.Globalization;
+using System.Windows;
+using System.Windows.Data;
+
+namespace VoxtralRealtime.Converters;
+
+public class BoolToVisibilityConverter : IValueConverter
+{
+    public object Convert(object value, Type targetType, object parameter, CultureInfo culture)
+    {
+        bool invert = parameter?.ToString() == "Invert";
+        bool visible = value is bool b && b;
+        if (invert) visible = !visible;
+        return visible ? Visibility.Visible : Visibility.Collapsed;
+    }
+
+    public object ConvertBack(object value, Type targetType, object parameter, CultureInfo culture)
+    {
+        return value is Visibility v && v == Visibility.Visible;
+    }
+}
+
+public class InverseBoolConverter : IValueConverter
+{
+    public object Convert(object value, Type targetType, object parameter, CultureInfo culture)
+    {
+        return value is bool b && !b;
+    }
+
+    public object ConvertBack(object value, Type targetType, object parameter, CultureInfo culture)
+    {
+        return value is bool b && !b;
+    }
+}
+
+public class NullToVisibilityConverter : IValueConverter
+{
+    public object Convert(object value, Type targetType, object parameter, CultureInfo culture)
+    {
+        bool invert = parameter?.ToString() == "Invert";
+        bool isNull = value == null;
+        if (value is string s) isNull = string.IsNullOrEmpty(s);
+        bool visible = invert ? isNull : !isNull;
+        return visible ? Visibility.Visible : Visibility.Collapsed;
+    }
+
+    public object ConvertBack(object value, Type targetType, object parameter, CultureInfo culture)
+    {
+        throw new NotImplementedException();
+    }
+}
+
+public class EnumToVisibilityConverter : IValueConverter
+{
+    public object Convert(object value, Type targetType, object parameter, CultureInfo culture)
+    {
+        if (value == null || parameter == null) return Visibility.Collapsed;
+        return value.ToString() == parameter.ToString() ? Visibility.Visible : Visibility.Collapsed;
+    }
+
+    public object ConvertBack(object value, Type targetType, object parameter, CultureInfo culture)
+    {
+        throw new NotImplementedException();
+    }
+}