Run This Ai
EN DE

whisper.cpp

High-performance C++ port of OpenAI Whisper for fast local speech recognition

★ 51,133 GitHub MIT speech-recognitionwhisperstttranscriptioncpplocal-aiaudiovoice Bild & Video

Überblick

whisper.cpp is a high-performance C++ port of OpenAI Whisper automatic speech recognition model. With 51k+ GitHub stars, it enables fast, local speech-to-text on CPU, GPU (CUDA/Vulkan), and Apple Silicon. Supports multiple Whisper model sizes from tiny to large, running efficiently on edge devices, servers, and desktops. Perfect for transcription services, voice assistants, accessibility tools, and any app needing offline STT.

Anforderungen

Min vCPU
1
Min RAM
512 MB
Min Disk
10 GB
Rec vCPU
2
Rec RAM
2048 MB
Rec Disk
20 GB

Empfohlener VPS

Hostinger · KVM 2

2 vCPU · 8192 MB · 100 GB

$6.99
Zum Anbieter

Hostinger · KVM 2

2 vCPU · 8192 MB · 100 GB

$6.99
Zum Anbieter

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
Zum Anbieter

Affiliate-Hinweis

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  whisper-cpp:
    image: ghcr.io/ggml-org/whisper.cpp:main
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/whisper-cpp:/data

Bester VPS für whisper.cpp →

Verwandte Tools

Anleitungen & Artikel