whisper.cpp and RuntimeSpeechRecognizer
One project is a port of Whisper in C/C++, and the other is an Unreal Engine plugin that leverages the first project for cross-platform, real-time, offline speech recognition, making them ecosystem siblings where the latter depends on the former.
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 RuntimeSpeechRecognizer
gtreshchev/RuntimeSpeechRecognizer
Cross-platform, real-time, offline speech recognition plugin for Unreal Engine. Based on Whisper OpenAI technology, whisper.cpp.
Leverages whisper.cpp for local inference without external API calls, enabling private audio processing entirely on-device. Provides both C++ and Blueprint APIs for Unreal Engine integration, with support for multiple audio input sources and real-time streaming transcription. Includes automatic model downloading and caching, allowing developers to embed various Whisper model sizes optimized for accuracy versus performance trade-offs.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work