Lyrebird: AI & speech synthesis

It will need as little as one minute of audio recording of a speaker to compute a unique key defining her/his voice. This key will then allow to generate anything from its corresponding voice. The API will be robust enough to learn from noisy recordings. The following sample illustrates this feature, the samples are not cherry-picked.

Lyrebird will offer a new generation of speech synthesis technologies for developers. It is the result of several months of research conducted at the MILA lab at University of Montréal.


Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.