Mimic is a fast, lightweight Text-to-speech engine developed by Mycroft A.I. and VocaliD, based on Carnegie Mellon University’s FLITE software. Mimic takes in text and reads it out loud to create a high quality voice. Mimic's low-latency, small resource footprint, and good quality voices set it apart from other open source text-to-speech projects.
Mimic is going to be used for the voice of Mycroft as its small footprint makes it a very attractive solution for running not only on the Mycroft embedded device, but on multiple other platforms as well. We are working to make an A.I. that sounds great, and Mimic is a great step forward on that front.
Mimic is a powerful tool that can also help solve other important problems. That is why we’ve partnered with VocaliD to help Dr. Rupal Patel and her team to bring realistic voices to people with speech disorders. VocaliD’s technology allows them to create customized voices that better represent the people who use them. To use these voices VocaliD’s clients need a fast, lightweight, cross-platform engine. That is where Mimic comes in. VocaliD’s clients can use Mimic as the engine that empowers them to speak with their own unique voice.
Mimic works on Linux, Android & Windows and we are working on iOS support. We are also adding more languages to enable many people to access realistic voices for the first time.
Creating realistic voices also requires everyday people to share their voice with VocaliD’s Human Voicebank.