Automates the transcription and embedding of subtitles into video files using FFmpeg and OpenAI Whisper API.
This tool provides a comprehensive solution for video subtitling, leveraging FFmpeg for robust video processing and OpenAI's Whisper API for accurate audio transcription. It efficiently extracts audio from common video formats like MP4 and MOV, transcribes the audio into various languages, generates industry-standard SRT subtitle files, and seamlessly embeds them back into the video. Supporting the Model Context Protocol (MCP), it enables secure local file access during processing. The tool offers flexibility through both a Python library for programmatic control and a convenient command-line interface for quick operations, including subtitle refinement and language support queries.