graph TD
A[Voiceover audio WAV] --> B{Split voiceover audio into 5-10 second clips}
B --> C[Voiceover audio clips]
D[3D character model file] --> E{Import 3D character model into animation software}
E --> F[3D character loaded in software]
G[Phoneme/viseme dataset for character] --> H{Import phoneme/viseme dataset}
H --> I[Phoneme/viseme data loaded]
C --> J{Analyze audio clips to generate phoneme data}
J --> K[Phoneme sequence data for each clip]
F --> L{Animate character lip sync and facial expressions}
I --> L
K --> L
L --> M[Character animation for each clip]
M --> N{Render character animations as video clips}
N --> O[Rendered video clips of character animation]
O --> P{Export character animation video clips}
P --> Q[Character animation video clips MP4]