中文 | English
AudioCaptureDemo is an Avalonia real-time speech recognition GUI. It lets you choose a language model, recognition mode, and either microphone or system-audio input. The interface is available in Chinese and English.
Build or run it from the repository root:
dotnet build demo/demo.sln -c Release
dotnet run --project demo/AudioCaptureDemo/AudioCaptureDemo.csprojGitHub Releases provide self-contained archives for every supported platform. Each archive extracts to one AudioCaptureDemo executable and does not require a .NET installation. Models are downloaded separately.
See AudioCaptureDemo/README.md for platform backends and system-audio requirements.