# ggml-org/whisper.cpp

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

- GitHub: https://github.com/ggml-org/whisper.cpp
- Category: Generative Media (https://ideas.asveas.com/c/genmedia)
- Tags: inference, openai, speech-recognition, stt, transformer, whisper, cpp
- Language: C++ · License: MIT
- Stars: 55,098 · Forks: 6,296 · Open issues: 363
- Last push: 2026-11-10 (yesterday)
- Vibe score: 89/100

## 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.

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

## Quick start
```bash
git clone https://github.com/ggml-org/whisper.cpp.git
```

## Alternatives in Generative Media
- [yt-dlp/yt-dlp](https://github.com/yt-dlp/yt-dlp) — A feature-rich command-line audio/video downloader (★207k, Python, vibe 99/100) · details: https://ideas.asveas.com/r/yt-dlp/yt-dlp
- [Comfy-Org/ComfyUI](https://github.com/Comfy-Org/ComfyUI) — The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world. (★146k, Python, vibe 98/100) · details: https://ideas.asveas.com/r/Comfy-Org/ComfyUI
- [remotion-dev/remotion](https://github.com/remotion-dev/remotion) — 🎥      Make videos programmatically with React (★72.5k, TypeScript, vibe 94/100) · details: https://ideas.asveas.com/r/remotion-dev/remotion
- [lemomo-ai/lemo-opuscar](https://github.com/lemomo-ai/lemo-opuscar) — A 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 (★14.8k, JavaScript, vibe 87/100) · details: https://ideas.asveas.com/r/lemomo-ai/lemo-opuscar
- [openai/whisper](https://github.com/openai/whisper) — Robust Speech Recognition via Large-Scale Weak Supervision (★112k, Python, vibe 78/100) · details: https://ideas.asveas.com/r/openai/whisper
- [AUTOMATIC1111/stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) — Stable Diffusion web UI (★165k, Python, vibe 76/100) · details: https://ideas.asveas.com/r/AUTOMATIC1111/stable-diffusion-webui

---
Source: https://ideas.asveas.com/r/ggml-org/whisper.cpp · Catalog: https://ideas.asveas.com/llms.txt