Voice transfer has been a hot topic. Recent research introduces a deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices. This webinar introduces how a complex deep learning process for cloning voices unseen during training can easily be converted to a Streamlit app using pre-trained models. Repo: https://github.com/datarootsio/rootslab-streamlit-demo

Check out the video