whisper.cpp

OpenAI Whisper is a high-performance inference version of the automated speech recognition model developed with pure C/C++. Its non-addictive structure offers zero memory allocation and integer quantization (quantization) support at runtime. Apple Silicon includes hardware optimizations for NVIDIA, AMD GPU, NPU and x86 architectures.

WH

ggml-org · AI / LLM / RAG

STARS54.8K
FORKS6.3K
COMMITS4.2K
CONTRIBUTORS860
VERSIONv1.9.1
UPDATEDyesterday
C++STTCpu HızlıEdgeMIT

Common commercial products in this category: ChatGPT, Claude, Gemini

What can it do?
  • You integrate the speech recognition model without requiring additional dependency on C/C++ based applications
  • Convert audio files locally to text on Apple Silicon, x86 or supported hardware accelerators
  • Develop offline voice assistant applications for different platforms such as Mac, iOS, Android, Linux, Windows and WebAssembly
User reviews
  • • NeutralHacker News

    Whisper.cpp example running fully in the browser

    “I recently laid off and currently trying to build some apps that could create some revenue that can afford my costs for some weeks. I built a transcription and dictation app for Mac [0] using whisper.cpp, small model works really well on 2019 mpb and m1 for streaming…”

  • • NeutralHacker News

    Whisper.cpp example running fully in the browser

    “Three clicks to find out what it is: 1: “Minimal whisper.cpp example running fully in the browser” 2: “Port of OpenAI's Whisper model in C/C++” 3: “Whisper is a general-purpose speech recognition model.””

GitHub

Verified against README · Oct 26, 2026 · source

My note

Alternative pages

More in: AI / LLM / RAG