Shulou(Shulou.com)11/24 Report--

Thanks to CTOnews.com netizens Wu Yanzu in South China for the delivery of clues! CTOnews.com, October 2 (Xinhua)-- Last year, Google announced a Lyra voice codec for low bit rate, which, combined with the open AV1 codec, can achieve voice chat at the speed of 56kbps. Lyra uses machine learning and other technologies to compress speech at very low bit rates, and can even work at the speed of 3kbps. Google opened the Lyra code last year, and yesterday they announced that Lyra V2 was available.

Google summed up Lyra V2 as "a better, faster, more versatile voice codec... a new architecture that enjoys broader platform support, provides scalable bit rate capabilities, has better performance, and produces higher quality audio."

Lyra V2 uses SoundStream end-to-end neural audio codec, has better performance than Opus audio codec, improves audio quality, etc., the open source code of Lyra V2 is available today.

CTOnews.com learned that more details about Lyra V2 can be found on Google's open source blog and the code can be found on GitHub. GitHub's release notes mention that Lyra V2 can perform five times faster on Android devices, reduce codec latency from 100ms to 20ms, and now support Mac and Windows to supplement Linux and Android support.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.