graph TD START[Start VideoAssemblerPro] --> INPUT[Receive Inputs] INPUT --> IN1[Avatar PNG URL] INPUT --> IN2[Voice-over MP3 URL] INPUT --> IN3[Transcription Data] IN1 & IN2 & IN3 --> SILO1[Audio Preparation Silo] SILO1 --> S1T1[Get Transcription With Timings] S1T1 --> S1T2[Convert MP3 to WAV] S1T2 --> TIMING[Timing Data Generated] TIMING --> SILO2[Video Generation Silo] SILO2 --> S2T1[Generate Base Video] S2T1 --> S2T2[Apply Lip Sync] S2T2 --> S2T3[Resize to 1920x1080] S2T3 --> OUTPUT[Final MP4 Video] subgraph Audio Processing SILO1 S1T1 S1T2 TIMING end subgraph Video Processing SILO2 S2T1 S2T2 S2T3 end