Skip to main content

Digital Human Videos

Create talking-head videos from a static portrait — make any person speak with lip-sync.

How It Works​

  1. Upload a portrait image — A clear, front-facing photo works best
  2. Provide the script — Type the narration text or upload reference audio
  3. Generate — The AI creates a video of the person speaking your script

Input Requirements​

  • Portrait Image — Clear, front-facing, with the subject looking at the camera
  • Script or Audio — Either type the narration text (TTS will generate the voice) or upload your own audio file

Example Prompts​

  • "Make this person say: Welcome to our store, we have the best deals in town"
  • "Generate a digital human video using this portrait and script"
  • "Create a talking-head video from this image with the following narration..."

Tips​

  • Use high-quality, well-lit portrait photos
  • Front-facing poses with a neutral expression work best
  • Keep narration clear and at a natural speaking pace
  • Audio files should be clean recordings without background noise