HeyGen · video

HeyGen Avatar IV

HeyGen's photo avatar: lifelike lip sync, head motion and expressions from a single photo.

Talking photo
Resolution
360p, 480p, 540p, 720p, 1080p
Aspect ratio
16:9, 9:16, 1:1, 4:5, 5:4
References
Up to 2 image or audio files

About HeyGen Avatar IV

HeyGen Avatar IV animates a photo into a talking avatar with HeyGen's Avatar IV, lip-syncing it to the audio you upload. Your audio replaces HeyGen's own voice, so the avatar speaks exactly your track. Priced at $0.25 per second of audio.

It offers more framing control than most talking-photo models here: 360p, 480p, 540p, 720p and 1080p, a choice of shapes and a talking style. A typical generation takes about 3 min.

Good for

  • Presenter-style talking videos in the shape you need, from 16:9, 9:16, 1:1, 4:5 and 5:4
  • Choosing how much the head moves, with a stable or an expressive style

Getting good results

  1. Use a photo with a clear face, as the provider asks.
  2. Pick Stable for minimal movement and Expressive for more animation; the price is the same.
  3. With the shape on automatic, the provider keeps the photo's own aspect ratio when it can read it.

HeyGen Avatar IV questions

Does resolution change the price?

No. Every resolution from 360p to 1080p costs $0.25 per second, $15.00 for a minute.

Other video models

AI video generator