After you have loaded your facial image, the accompanying mask, and have completed the alignment, you are ready for the next step in furnishing your facial model with a voice.
Keep in mind that whenever you record a voice (speech clip) or are loading external voice clips into TalkingShow™, all file attributes for the Wave formatted files are acceptable, but because of internal processing requirements, TalkingShow™ will convert and format these files with the following attributes:
16 kHz
16 Bit
Mono
Caution: Files that contain music or any kind of singing may be loaded, but is not advised because of unsuitable and improper viseme recognition.