whisper.cpp
High-performance C++ port of OpenAI Whisper for local transcription
whisper.cpp is a high-performance C++ implementation of OpenAI's Whisper automatic speech recognition model, offering 2-10x faster performance than the original Python implementation.
Key features include:
- Cross-Platform: Runs on Windows, macOS, Linux, iOS, Android, and even Raspberry Pi.
- Hardware Acceleration: Supports NVIDIA CUDA, Apple Metal, Vulkan, OpenVINO, and Core ML.
- Voice Activity Detection: Built-in VAD to skip silence and speed up transcription.
- Multiple Languages: Supports 99 languages with automatic language detection.
- Real-time Processing: Can process audio in real-time on modern hardware.
Created by Georgi Gerganov (also behind llama.cpp), whisper.cpp has become the go-to solution for local speech recognition.
Frequently Asked Questions
What is whisper.cpp?
High-performance C++ port of OpenAI Whisper for local transcription whisper.cpp is a high-performance C++ implementation of OpenAI's Whisper automatic speech recognition model, offering 2-10x faster performance than the original Python implementation. Key features in...
Is whisper.cpp free?
Yes, whisper.cpp is completely free to use. It's also open source.
Does whisper.cpp work offline?
Yes, whisper.cpp works 100% offline once installed.
What platforms does whisper.cpp support?
whisper.cpp is available for Windows, macOS, Linux.
Related Tools
View all →
Ollama
Run large language models locally with a simple CLI interface
LM Studio
Discover, download, and run local LLMs with an easy-to-use desktop app
Jan
Open-source ChatGPT alternative that runs 100% offline on your computer
GPT4All
Free-to-use, locally running, privacy-aware chatbot by Nomic AI
Text Generation WebUI
The AUTOMATIC1111 of text generation - maximum control for LLMs
KoboldCpp
Easy-to-use AI text generation software for GGML/GGUF models