What is whisper.cpp used for?

whisper.cpp is a dependency-free C/C++ port of OpenAI's Whisper speech recognition model that runs offline on CPUs, GPUs and mobile devices. It is a good fit for offline speech-to-text in apps, private voice assistants and transcribing audio on local hardware.

Is whisper.cpp open source?

Yes. whisper.cpp is open source under the MIT licence. Its source code is on GitHub at ggml-org/whisper.cpp and is written mainly in C++.

Yes. whisper.cpp is open source, so the software itself is free to use.

What is whisper.cpp an alternative to?

whisper.cpp is an open-source alternative to Deepgram and AssemblyAI. Other open-source alternatives to Deepgram include Whisper and LocalAI.

Is whisper.cpp actively maintained?

Yes. The most recent commit to whisper.cpp was on 2 October 2026, and the latest release is v1.9.4, published on 11 September 2026. The project has 54k stars on GitHub.

whisper.cpp: open-source alternative to Deepgram, AssemblyAI

About whisper.cpp

whisper.cpp is a C/C++ implementation of OpenAI's Whisper automatic speech recognition model, built for efficient inference without external dependencies. It is released under the MIT license and part of the ggml project, and the whole high-level model implementation lives in two files, which makes it easy to embed in different platforms and applications.

It is tuned for many kinds of hardware: Apple Silicon through ARM NEON, Accelerate, Metal and Core ML, AVX on x86, VSX on POWER, plus Vulkan, NVIDIA GPUs, AMD ROCm, OpenVINO and several NPUs. Mixed F16 and F32 precision, integer quantization and zero memory allocations at runtime keep resource use low, and a C-style API and voice activity detection are included.

Supported platforms include macOS, iOS, Android, Java, Linux and FreeBSD, WebAssembly, Windows, Raspberry Pi and Docker. The README shows the model running fully offline on an iPhone and suggests building offline voice assistants. It suits developers adding private speech-to-text to apps, and hobbyists transcribing audio on their own hardware.

Key features

Plain C/C++ implementation without dependencies
Optimized for Apple Silicon, AVX and GPUs
Integer quantization and mixed precision
Zero memory allocations at runtime
Voice activity detection
C-style API for embedding
Runs on mobile, desktop, web and Raspberry Pi

Good fit for

→Offline speech-to-text in apps
→Private voice assistants
→Transcribing audio on local hardware

Built with: C++
Tags: speech-recognition; speech-to-text; whisper; cpp; inference; offline; ggml; transcription

whisper.cpp: questions and answers

What is whisper.cpp used for?: whisper.cpp is a dependency-free C/C++ port of OpenAI's Whisper speech recognition model that runs offline on CPUs, GPUs and mobile devices. It is a good fit for offline speech-to-text in apps, private voice assistants and transcribing audio on local hardware.
Is whisper.cpp open source?: Yes. whisper.cpp is open source under the MIT licence. Its source code is on GitHub at ggml-org/whisper.cpp and is written mainly in C++.
Is whisper.cpp free?: Yes. whisper.cpp is open source, so the software itself is free to use.
What is whisper.cpp an alternative to?: whisper.cpp is an open-source alternative to Deepgram and AssemblyAI. Other open-source alternatives to Deepgram include Whisper and LocalAI.
Is whisper.cpp actively maintained?: Yes. The most recent commit to whisper.cpp was on 2 October 2026, and the latest release is v1.9.4, published on 11 September 2026. The project has 54k stars on GitHub.