i ideas / repo launcher
ggml-org avatar

ggml-org/whisper.cpp

★ 55,098C++MIT89

Port of OpenAI's Whisper model in C/C++

What it is

High-performance inference of OpenAI's Whisper automatic speech recognition (ASR) model: Plain C/C++ implementation without dependencies Apple Silicon first-class citizen - optimized via ARM NEON, Accelerate framework, Metal and Core ML AVX intrinsics support for x86 architectures VSX intrinsics support for POWER architectures Mixed F16 / F32 precision Integer quantization support Zero memory allocations at runtime Vulkan support Support for CPU-only inference Efficient GPU support for NVIDIA AMD ROCm GPU support AMD Ryzen AI NPU Support OpenVINO Support Huawei Ascend NPU Support Moore Threads GPU Support C-style API Voice Activity Detection (VAD)

When to use it

Reach for whisper.cpp when your project generates or processes images, video, speech or audio — it's written in C++ and fits stacks tagged inference, openai, speech-recognition, stt.

Category
Generative Media
Also in
—
Stars
55,098
Forks
6,296
Last push
yesterday
Created
2022-09-25
Open issues
363
Website
—
#inference#openai#speech-recognition#stt#transformer#whisper#cpp

Quick start

$ git clone https://github.com/ggml-org/whisper.cpp.git

Hand it to your AI

Read https://ideas.asveas.com/r/ggml-org/whisper.cpp.md and help me add ggml-org/whisper.cpp to my project. Explain the setup steps for my stack and show the minimal code to get it working.
Generative MediaMarkdown .mdOpen on GitHub ↵

Alternatives to whisper.cpp

All Generative Media →
yt-dlp avataryt-dlpA feature-rich command-line audio/video downloader★ 207kComfy-Org avatarComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.★ 146kremotion-dev avatarremotion🎥 Make videos programmatically with React★ 72.5klemomo-ai avatarlemo-opuscarA toolbox of film styles made in code for Claude Code: 66 ready to use, and your own. Each style is a style prompt plus a demo film made entirely in code by Claude Opus 5.5, with no video model. By Lemomo. · 一套用代码做片的风格工具箱：66 种现成风格，也能做出你自己的★ 14.8kopenai avatarwhisperRobust Speech Recognition via Large-Scale Weak Supervision★ 112kAUTOMATIC1111 avatarstable-diffusion-webuiStable Diffusion web UI★ 165k

Pairs well with

unslothai avatarunslothLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.★ 79.3k

FAQ

What is whisper.cpp?

ggml-org/whisper.cpp is a media tool on GitHub: Port of OpenAI's Whisper model in C/C++ High-performance inference of OpenAI's Whisper automatic speech recognition (ASR) model: Plain C/C++ implementation without dependencies Apple Silicon first-class citizen - optimized via ARM NEON, Accelerate framework, Metal and Core ML AVX intrinsics support for x86 architectures VSX intrinsics support for POWER architectures Mixed F16 / F32 precision Integer quantization support Zero memory allocations at runtime Vulkan support Support for CPU-only inference Efficient GPU support for NVIDIA AMD ROCm GPU support AMD Ryzen AI NPU Support OpenVINO Support Huawei Ascend NPU Support Moore Threads GPU Support C-style API Voice Activity Detection (VAD)

When should I use whisper.cpp?

Reach for whisper.cpp when your project generates or processes images, video, speech or audio — it's written in C++ and fits stacks tagged inference, openai, speech-recognition, stt.

What are the best alternatives to whisper.cpp?

Popular alternatives in Generative Media: yt-dlp/yt-dlp (207k★), Comfy-Org/ComfyUI (146k★), remotion-dev/remotion (72.5k★), lemomo-ai/lemo-opuscar (14.8k★), openai/whisper (112k★).

Is whisper.cpp actively maintained?

ggml-org/whisper.cpp looks very actively maintained: the last push was yesterday (2026-11-10), with 55,098 stars and 363 open issues.

What license does whisper.cpp use?

ggml-org/whisper.cpp is published under the MIT license. Check the repository's LICENSE file before commercial use.