Transcribe local audio files to SRT subtitles and TXT transcripts with timestamps using faster-whisper. Use when Claude needs to convert local audio files (MP3, M4A, WAV, etc.) into text transcripts with or without timestamps, generate subtitle files from audio, or perform speech-to-text transcription. Supports multiple Whisper model sizes for accuracy/speed tradeoffs, language specification, VAD filtering, and custom output directories.