tools
whisper.cpp
whisper.cpp is a C/C++ implementation for running Whisper speech recognition locally on many platforms.
whisper.cpp transcribes and translates audio using OpenAI's Whisper model. It provides a command-line tool, C-style API, voice activity detection, real-time microphone examples, model quantization, and CPU or GPU acceleration.
It is used by developers building offline transcription, dictation, subtitle, voice-assistant, and embedded applications. It is an open-source library and local tool, not a hosted transcription service; model files and optional tools such as ffmpeg are obtained separately.
Features
- C/C++ implementation with a C-style API
- CPU-only inference and GPU acceleration
- Apple Silicon support through Metal, Core ML, and Accelerate
- Integer quantization for smaller model files and lower memory use
- Voice activity detection through the --vad option
- Command-line transcription with whisper-cli
- Real-time microphone transcription example
- MIT-licensed open-source project
Use cases
- Transcribe audio files locally without sending recordings to a server
- Build offline dictation or voice-assistant applications
- Add speech recognition to iOS, Android, desktop, or embedded software
- Generate transcripts or subtitles from recorded audio
- Run speech recognition on CPU, GPU, or Apple Neural Engine hardware