Google reported its new Lyra audio codec in February, which it would begin using within Google Duo. The codec allows for higher quality audio at lower bandwidths, which means it’s ideal for slower network speeds. On Friday, Google declared that it’s growing this new codec to third-party developers, opening Lyra to a world of possibilities.
As part of our efforts to make the best codecs universally accessible, we are open sourcing Lyra, permitting different designers to control their communications applications and take Lyra in incredible new ways.
As a refresher, Lyra includes an encoder to capture audio, which it compresses and afterward decodes utilizing a generative model, a type of machine learning model. The model permits the audio to be reproduced at especially low bitrates, as low as 3kbps while holding similarly high-quality output. You can get a more detailed clarification on Google’s AI blog, yet Lyra is basically ideal for use on the best modest Android phones or moderate networks. Google features the significance of technology like Lyra, especially in developing markets that don’t have fast internet speeds in when telecommuting has become a norm.
Making Lyra open source implies that the codec can be utilized in more communication applications, however Google trusts designers will concoct better approaches to utilize the codec. That could incorporate utilizations for non-speech applications or even music, which would be ideal for platforms like Spotify that are consistently growing to more global markets, however the prospects are endless.
Google says that Lyra is written in C++ “for speed, efficiency, and interoperability” and that the present beta release and demo on GitHub empowers designers to give feedback rapidly.