transcribe-audio

Transcribes audio files to text using whisper-cpp locally and offline. No API keys or network required.

Basic Transcription

transcribe-audio input.mp3                    # Transcribe with default settings
transcribe-audio input.wav --language en      # Specify language
transcribe-audio input.flac --model medium    # Use a larger model for better accuracy

Options

• --language <code> — specify source language (auto-detect by default)
• --model <size> — choose model size: tiny, base, small, medium, large
• --output <format> — output format: txt, srt, vtt (default: txt)
• --timestamp — include timestamps in output