whisper.cpp and whisper.unity
The Unity3D integration builds upon the C/C++ implementation, making them complements—whisper.unity provides a game engine wrapper around whisper.cpp's core inference engine for local speech-to-text processing.
About whisper.cpp
ggml-org/whisper.cpp
Port of OpenAI's Whisper model in C/C++
Optimized for resource-constrained environments through integer quantization, mixed-precision inference (F16/F32), and zero runtime memory allocations, enabling on-device ASR on mobile and embedded platforms. Leverages the GGML inference library with multi-platform GPU acceleration via Metal, Vulkan, CUDA, and Core ML, alongside CPU-optimized SIMD paths for ARM NEON, AVX, and POWER VSX architectures. Provides a minimal C API and supports deployment across iOS, Android, WebAssembly, Raspberry Pi, and standard desktop/server platforms.
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