It is very complicated to develop an accurate model of someone's voice using a neural network, it requires many data points, and often times ends up sounding very monotone. This is not ideal for someone who wants to quickly create a text-to-speech service with their own voice, whether it is because they won't be able to speak due to surgery or are doing it just for fun.
YouSpeak is a text-to-speech service that allows users to easily create their own text-to-speech model. Users can upload audio recordings of themselves speaking so that audio files for each word are automatically extracted and stored. Once the user wishes to use the text-to-speech function of their speech model, they can simply type in the text they would like to generate audio for. After that, the user will receive audio generated by the model for the text.
Log in or sign up for Devpost to join the conversation.