OpenAI’s Whisper Audio to text transcription right into your web browser!

Visit the Github Repo for more information

Features

  • Record and transcribe audio right from your browser.
  • Upload any media file (video, audio) in any format and transcribe it.
  • Download .srt subtitle file generated from audio.
  • Lightweight and beautiful UI.
  • Self-hosted. No 3rd parties.
  • Docker compose for easy self-hosting
  • Select input audio language
  • Privacy respecting:
  • All happens locally. No third parties involved.
  • Audio files are deleted immediately after processing.
  • Backend written in Go
  • Frontend written with Svelte and Tailwind CSS.
  • Uses C++ whisper version from whisper.cpp.
  • You don’t need a GPU, uses CPU.
  • No need for complex installations.

docker-compose.yml

version: "3.9"

services:
  backend:
    image: schklom/web-whisper-backend:base
    environment:
      - CUT_MEDIA_SECONDS=0
      #- WHISPER_MODEL-small # I imagine this env is not used when using hosted images
    container_name: web-whisper-backend
    networks:
      - default
  whisper:
    image: schklom/web-whisper-frontend:latest
    environment:
      - DOMAIN_NAME=whisper.apps.domain.com
      - ALLOW_FILE_UPLOADS=true
    container_name: web-whisper
  # uncomment the ports below if not using reverse proxy #
   # ports:
    #  - "3000:80"
    networks:
      - npm         # reverse proxy network goes here, either edit to match your reverse proxy network or simply remove it if not using reverse proxy
      - default
   
networks:
  default:
  npm:
    external: true