Avatar Video Generation

Generate lip-synced avatar videos from text using the OmniHuman v1.5 pipeline.

Prerequisites

• Python 3.10+
• OpenAI API key (for TTS)
• fal.ai API key (for OmniHuman)
• Avatar image (portrait, clear face)

Pipeline Overview

Text → TTS → Audio → CDN Upload → OmniHuman → Video → Post-Processing → Final Video

Step-by-Step Commands