graph TD A[Start VideoSync Subagent] --> B[Receive Inputs] B --> C1[voiceover-mp3] B --> C2[avatar-image] C1 --> D[SILO 1: Audio Transcription] D --> E[Use Skill #198] E --> F[Generate Transcription] F --> G[transcription-text] C1 --> H[SILO 2: Video Generation] C2 --> H G --> H H --> I[Use Skill #168] I --> J[Generate Lip-Synced Video] J --> K[talking-head-video] K --> L[End VideoSync Subagent] style A fill:#f9f,stroke:#333 style L fill:#f9f,stroke:#333 style C1 fill:#ddf,stroke:#333 style C2 fill:#ddf,stroke:#333 style G fill:#ddf,stroke:#333 style K fill:#ddf,stroke:#333