whisper.cpp
Dependency-free C/C++ port of Whisper for local speech-to-text
What it is
A plain C/C++ implementation of OpenAI's Whisper speech recognition model with no external dependencies. It runs on CPUs and many GPU and NPU backends, is optimised for Apple Silicon, and includes voice activity detection and a C-style API. For developers who need offline transcription on desktop, mobile or embedded targets.
Good for
- Transcribe audio files fully offline
- Embed speech recognition in a native app
- Run Whisper on a machine with no GPU
Install or run
git clone https://github.com/ggml-org/whisper.cpp.gitCommand as given in the project README. Read the repository before you run anything on your machine.
What you need
A C/C++ toolchain to build; a downloaded Whisper model file
Sources
- https://github.com/ggml-org/whisper.cpp (project README, read 10 Nov 2026)
- https://api.github.com/repos/ggml-org/whisper.cpp (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.