Hi {{first_name}}, thanks for watching, I hope you're finding these videos informative. Our Text to voice uses Google’s groundbreaking DeepMind AI technology, to generate speech with humanlike intonation, and delivers voices that are near human quality. Add personalisation merge tags into the audio text input, to create dynamic speech in your videos. Choose from a set of 220+ voices across 40+ languages and variants. Pick the voice that works best for you and the {{business_name}} use-case. If you have multiple audio layers in your video, you can copy settings to all. As audio can be variable length due to accent, length of spoken names and speech speed, we only need to set the start time for the audio in the video. Thanks for watching {{first_name}}! Please select another video feature to learn more about how it can benefit {{business_name}}.