2.2 Experimental 9 (2.2.2-experimental9) 🧪

[agniuks]

Windows App SDK 2.2 Experimental 9 (2.2.2-experimental9) 🧪

Windows App SDK 2.2 Experimental 9 is the latest experimental release. It ships alongside Windows App SDK 2.2.0 stable and generally brings over the changes from that release; the highlights below describe the experimental-only additions.

What's new in WinAppSDK 2.2 Experimental 9:

• Language Model APIs on GPU [Experimental]. The Language Model APIs now run on non-Copilot+ PCs equipped with a supported GPU, bringing local language model capabilities to a broader range of Windows 11 devices. Supported hardware includes NVIDIA GeForce RTX 30 series and newer with 6+ GB vRAM. GPU inference requires Developer Mode to be enabled and a Windows Insider Experimental Channel build. The GPU model is not pre-installed; it is downloaded on demand via EnsureReadyAsync through Windows Update. Apps should check GetReadyState and display a consent dialog before triggering the download. Users can manage the model at Settings > System > AI Components. For responsible AI guidance, see the new Transparency Note: Language Model APIs on Non-Copilot+ PCs.
• Speech Recognition APIs [Experimental]. New on-device speech recognition APIs in Microsoft.Windows.AI.Speech enable both batch and streaming speech-to-text. BatchRecognition recognizes a complete audio source in a single call, and StreamingRecognition raises Recognizing and Recognized events. Audio can be sourced from a device (AudioConfiguration.FromAudioDevice), file (FromFile), input stream (FromStream), or pushed by the caller via SpeechAudioProvider (16 kHz, 16-bit, single-channel PCM). The on-device model is managed via SpeechRecognitionModel.EnsureReadyAsync / TryCreateAsync, with download and load progress reported through SpeechRecognitionModelProgress.
• New NpuType API. A new Microsoft.Windows.Workloads.NpuType enum surfaces the NPU class on the current device (for example, Qnn, Lnl, Stx, Win365, Unknown, None), so apps and Workloads infrastructure can route AI workloads to the appropriate execution path.

This release also rolls forward all changes from the 2.2.0 stable release: the new Microsoft.Windows.AI.Video.VideoScaler Video Super Resolution API, the new Microsoft.Windows.Storage.ApplicationData.GetForUnpackaged() entry point for unpackaged apps, the new XamlBindingHelper boxing-free setter overloads, and the WinUI / Windows ML reliability fixes shipped in 2.2.0.

New or updated APIs (since 2.1 Experimental 8):

Microsoft.UI.Xaml

    Setter
        ValueProperty

Microsoft.UI.Xaml.Markup

    XamlBindingHelper
        SetPropertyFromColor
        SetPropertyFromCornerRadius
        SetPropertyFromThickness

Microsoft.Windows.AI.Speech

    AudioConfiguration
    BatchRecognition
    SpeechAudioProvider
    SpeechContract
    SpeechRecognitionModel
    SpeechRecognitionModelProgress
    SpeechRecognitionModelProgressStatus
    SpeechRecognitionModelResult
    StreamingRecognition
    StreamingRecognizedEventArgs
    StreamingRecognizingEventArgs

Microsoft.Windows.AI.Text.Experimental

    LanguageModelExperimental
        CompressPromptAsync
        GenerateResponseAsync
        GenerateResponseFromEmbeddingsAsync

    LanguageModelOptionsExperimental
        PreferredRetentionRatio

Microsoft.Windows.Workloads

    NpuType

Try it out

• Download the 2.2.2-experimental9 NuGet package to use WinAppSDK 2.2 Experimental 9 in your app.

Getting started

To get started using Windows App SDK to develop Windows apps, check out the following documentation:

• Install developer tools.
• Create a WinUI 3 app.
• Continue your development journey.

---

This discussion was created from the release 2.2 Experimental 9 (2.2.2-experimental9) 🧪.