Directory › Audio & voice › whisper.cpp
> GEM AUDIO & VOICE · DEVELOPMENT · LOCAL AI
whisper.cpp
by ggml-org
Whisper in dependency-free C/C++: fast, lightweight and portable.
View on GitHub →What it does
- No Python setup: one binary and one model file
- Very efficient on Apple Silicon Macs, even runs on phones or a Raspberry Pi
- Ships a command-line tool and a small HTTP server
Install it
Requirements: Git, CMake and a C++ compiler.
Clone the repository
git clone https://github.com/ggml-org/whisper.cpp.git
Download a model
cd whisper.cpp && sh ./models/download-ggml-model.sh base.en
Build
cmake -B build && cmake --build build -j --config Release
Transcribe
./build/bin/whisper-cli -f samples/jfk.wav
The prompt for your agent
Paste it into your coding agent: it checks the requirements and installs it for you.
Claude CodeCodexCursorGemini CLIopencode
Prompt
Install whisper.cpp (https://github.com/ggml-org/whisper.cpp) on my machine.
1. Check the requirements: Git, CMake and a C++ compiler. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Clone the repository: git clone https://github.com/ggml-org/whisper.cpp.git
- Download a model: cd whisper.cpp && sh ./models/download-ggml-model.sh base.en
- Build: cmake -B build && cmake --build build -j --config Release
- Transcribe: ./build/bin/whisper-cli -f samples/jfk.wav
3. Check that it works, then explain how to launch it and where to start.
Always review what your agent is about to run, especially install commands.