HeyGen Promotes Voice STS to Carry Recorded Delivery Into Avatar Speech

HeyGen is promoting Voice STS, a speech-to-speech feature that carries a speaker’s recorded performance into an avatar’s voice, preserving details such as pauses and emphasis. The workflow addresses a common limitation of text-to-speech: written scripts alone may not capture the delivery a creator wants. HeyGen’s existing documentation describes a similar capability called Voice Mirroring, in which users record or upload audio and apply its tone, rhythm and pacing to a selected avatar and voice (Voice Mirroring guide).