October 2018 | By Google Creative Lab
A fun way to play with speech and music.
This experiment lets you combine speech and music in a fun way. Just type some words, then set them to your own melody. You can change the melody with your mouse or keyboard, and explore different voices, scales, and more.
It was built with Google Cloud Text-to-Speech API, which enables developers to synthesize natural-sounding speech. This API is based on Wavenet, which generates audio using neural networks.
This experiment was made by Yotam Mann, Kyle Phillips, Claire Kearney-Volpe, Luisa Pereira, and Google Creative Lab. Special thanks to friends at Henry Viscardi School at The Viscardi Center, Tech Kids Unlimited, and ADAPT Community Network.