graph TD A[Start Transcription Processing] --> B[Extract MP3 from Video] B --> C[Process Audio through STT API] C --> D[Generate Raw Transcript] D --> E[Add Timestamp Markers] E --> F[Format to JSON] F --> G[Validate JSON Structure] G --> H[Add Metadata] H --> I[Output Final JSON Transcript] subgraph Input A end subgraph Processing B C D E F G H end subgraph Output I end style A fill:#f9f,stroke:#333 style I fill:#9ff,stroke:#333