Re-syncs the lips of a person in a video (100 MB, up to 600 s) to new speech (50 MB, up to 600 s), same inputs as Lipsync Speed. Sync mode loops the video, pads with silence or cuts off the longer one. Options: dynamic duration, remove background music, speech enhancement. Returns the video and an SRT caption file as a text asset. Best for: dialogue replacement, dubbing a presenter, new script on existing talking footage. Not for: videos without a visible face; generating a talking video from a photo. Instead: photo to talking video, HeyGen Avatar 6; full translation with voice, HeyGen Video Translate Precision; other tier, HeyGen Lipsync Speed.