Google releases Lyra V2 ultra-low bitrate voice codec for voice chat at 56kbps
- Seagate 12TB HDD: 7.46% failure rate and 1.5 year lifespan
- An American company made 0.7nm chips: EUV lithography machines can’t do it
- 14000 cores + 450W: RTX 4080 graphics card perfectly replaces the RTX 3080
- Big upgrade: The difference between Bluetooth 5.0 and 5.2
- Geeks Disappointed that RTX 4080/4090 doesn’t come with PCIe 5.0
- What are advantages and disadvantages of different load balancing?
Google releases Lyra V2 ultra-low bitrate voice codec for voice chat at 56kbps.
Last year, Google announced the Lyra voice codec for low bit rates, combined with the open AV1 codec, can achieve voice chat at a network speed of 56kbps.
Lyra utilizes machine learning and other techniques for very low bitrate speech compression, even working at 3kbps.
Google opened up the code for Lyra last year, and they announced that Lyra V2 is available on Oct. 01.
Google summarizes Lyra V2 as “a better, faster, more versatile speech codec…a new architecture that enjoys broader platform support, offers scalable bitrate capabilities, has better performance, and produce higher quality audio.”
Lyra V2 utilizes the SoundStream end-to-end neural audio codec, which has better performance than the Opus audio codec, improved audio quality, etc.
The open source code for Lyra V2 is available today.
More details about Lyra V2 can be found through Google’s open source blog, and the code can be found on GitHub .
The GitHub release notes mention that Lyra V2 can perform up to 5 times faster on Android devices, reduce codec latency from 100ms to 20ms, and now supports Mac and Windows to complement Linux and Android support.
- DIY a PBX (Phone System) on Raspberry Pi
- How to host multiple websites on Raspberry Pi 3/4?
- A Free Intercom/Paging system with Raspberry pi and old Android phones
- DIY project: How to use Raspberry Pi to build DNS server?
- Raspberry Pi project : How to use Raspberry Pi to build git server?