graph TD
A[Start TalkingHeadAssembler] --> B[Receive Inputs]
B --> C[Get MP3 File]
B --> D[Get Avatar Image]
C --> E[Task 1: Generate Timed Transcription]
E --> F[Use Skill #198]
F --> G[Output: Transcription with Timestamps]
D --> H[Task 2: Create Lip-Synced Video]
G --> H
C --> H
H --> I[Use Skill #168]
I --> J[Output: Talking Head MP4]
J --> K[Return Final Video]
K --> L[End TalkingHeadAssembler]
style A fill:#f9f,stroke:#333,stroke-width:2px
style L fill:#f9f,stroke:#333,stroke-width:2px
style F fill:#bbf,stroke:#333,stroke-width:2px
style I fill:#bbf,stroke:#333,stroke-width:2px