#98 · Primary category： Speech & Audio
whisper.net
Whisper.net. Speech to text made simple using Whisper Models
Project last updated：08/23/26
GitHub Stars
940
Forks
136
Contributors
19
License
MIT
Why we included this project
For C# developers who want speech recognition without shipping audio to a cloud API, whisper.net is the closest thing to a native Whisper binding for .NET. It wraps whisper.cpp behind a managed interface, so loading a model and transcribing an audio file takes a few lines of code instead of hand-rolled native interop. The runtime selection is the part that stands out: the same package can run on CPU, NVIDIA CUDA, Apple CoreML, Intel OpenVINO, or Vulkan, and it picks whichever accelerator is fastest on the machine in front of it. That keeps it practical for desktop tools and for server-side services that want local transcription, while still working across Windows, Linux, macOS, iOS, Android, and WebAssembly.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production