Lyra is a lossy audio codec developed by Google that is designed for compressing speech at very low bitrates.

The Lyra codec is designed to transmit speech in real-time when bandwidth is severely restricted, such as over slow or unreliable network connections.

[2][3] Instead, compression is achieved via a machine learning algorithm that encodes the input with feature extraction, and then reconstructs an approximation of the original using a generative model.

[1][4][5] Ian Buckley at MakeUseOf said, "It succeeds in creating almost eerie levels of audio reproduction with bitrates as low as 3 kbps."

[5] In December 2017, Google researchers published a preprint paper on replacing the Codec 2 decoder with a WaveNet neural network.