whisper-transcribe-docker - Local Speech-to-Text Transcription with Docker
Transcribes audio files to text locally using faster-whisper in Docker containers
Tags
Updated: 2026-02-13Capabilities
Typical Inputs
Typical Outputs
What this skill does
- transcribe audio files
- generate timestamped transcripts
- output text or JSON formats
Inputs
- audio files
- Docker container
- faster-whisper models
Outputs
- text transcript files
- JSON transcript files
Requirements
- Docker environment
- local execution
- model cache volume