graph TD A[VoiceOverMaker] -->|Voice-over MP3 URL| B[Extract MP3 Audio From MP4 File] A -->|Voice-over MP3 URL| C[Get Transcription Of MP3 With Timings] B -->|MP4 URL| D[Generate Talking Head Video From MP3] C -->|Transcription with timings| D E[TalkingHeadVideoMaker] -->|Selected talking head image URL| D D -->|URL of MP4 video| F[Talking Head Video Output]