A self-hosted speech-to-text transcription service using OpenAI's Whisper AI and Docker. This service monitors a directory for audio files, transcribes them automatically, and saves the results in both text and JSON formats.
Sign in to like and favorite skills
A self-hosted speech-to-text transcription service using OpenAI's Whisper AI and Docker. This service monitors a directory for audio files, transcribes them automatically, and saves the results in both text and JSON formats.
/docker-transcriptions ├── docker-compose.yml # Main Docker configuration ├── app/ # Application code │ └── transcribe.py # Python script for transcription ├── data/ # Persistent storage for uploaded files and transcriptions │ ├── uploads/ # Audio files to be transcribed │ │ └── processed/ # Audio files that have been processed │ └── transcriptions/ # Generated transcription files └── docs/ # Project documentation └── PROJECT_MAP.md # This file
docker-compose.ymlapp/transcribe.pydata/uploads/data/transcriptions/docs/PROJECT_MAP.md