VibePaper Guide

Create a talking avatar video with HeyGen

Connect a portrait and a voice track on one canvas, then turn them into a synchronized avatar video.

The digital-human card brings the essential HeyGen workflow into VibePaper. Your portrait defines who appears, your audio defines what they say, and an optional motion prompt guides performance.

Portrait
Voice
Motion

Three inputs, one finished video

01

Prepare a clear portrait

Use a front-facing image with one visible subject, even lighting, and an unobstructed face. Connect it to the image reference slot.

02

Add the voice track

Connect an audio card or uploaded recording. Clean speech with limited background noise produces the most stable lip sync.

03

Direct the performance

Optionally describe restrained gestures, facial expression, or camera behavior, then generate and review the result beside its source assets.

Before you generate

  • Use one person per portrait and keep the mouth clearly visible.
  • Trim silence at the start and end of the audio.
  • Keep motion direction short and physically plausible.