video-processor

Process videos by extracting audio, converting formats (MP4, WebM), and transcribing with Whisper.

• Extract audio from video files
• Convert videos to MP4 or WebM formats
• Transcribe audio/video to text using Whisper
• Uses FFmpeg and OpenAI Whisper for processing

• Supports audio extraction from video
• Converts to MP4 or WebM with configurable codecs
• Transcribes to txt, srt, vtt, or json
• Automatically extracts audio for transcription
• Handles temporary file cleanup on error
• Validates tool installations and inputs
• Supports multiple Whisper model sizes
• Optimizes audio format (16kHz, WAV/MP3)

1. 1.Run video_processor.py with appropriate command (extract-audio, to-mp4, to-webm, transcribe)
2. 2.Specify input and output file paths
3. 3.Use --format, --model, or --language options as needed
4. 4.Ensure FFmpeg and Whisper are installed and accessible