whisper.net and whisper.unity
These are ecosystem siblings—both are independent .NET/Unity language bindings that wrap the same underlying Whisper inference engine (whisper.cpp) for different runtime environments, allowing developers to integrate speech-to-text into C# applications or game engines respectively.
About whisper.net
sandrohanea/whisper.net
Whisper.net. Speech to text made simple using Whisper Models
Provides .NET bindings to whisper.cpp with pluggable hardware acceleration across CPU, NVIDIA CUDA (13/12), Apple CoreML, Intel OpenVINO, and Vulkan runtimes. Automatically selects the optimal runtime based on platform and installed drivers, with priority fallback logic (e.g., CUDA 12 devices transparently downgrade from CUDA 13). Supports diverse platforms from Windows/Linux/macOS to mobile (iOS/Android) and WebAssembly, with custom native binary injection for advanced use cases.
About whisper.unity
Macoron/whisper.unity
Running speech to text model (whisper.cpp) in Unity3d on your local machine.
Provides C++ bindings to whisper.cpp with support for 60+ languages, cross-language translation, and optional GPU acceleration via Vulkan (Windows/Linux) or Metal (Apple platforms). Includes swappable model weights ranging from tiny (fastest) to large (highest accuracy), all running inference locally without internet. Distributes as a Unity Package with prebuild libraries for Windows, macOS, Linux, iOS, Android, and visionOS.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work