graph TD A[Start] --> B[Input MP4 Video URL] B --> C[FFmpeg Transcoder] C --> D[Speech-to-Text Engine] D --> E[Process Raw Transcription] E --> F[Add Timestamps] F --> G[Format Output] G --> H[Generate video_transcription_with_timestamps.txt] H --> I[End] subgraph TranscriptionGenerator C D E F G H end style TranscriptionGenerator fill:#f9f,stroke:#333,stroke-width:2px