Google Posts Initial Code For Lyra Speech Codec

Back in February we covered Google's work on the Lyra voice/audio codec designed for fitting with very low bit-rate audio for speech compression in use-cases like WebRTC and video chatting even on the most limited Internet connections. Thanks to leveraging machine learning, Lyra can function at just 3kbps. The code to Lyra is now public.

Lyra when originally announced by Google back in February sounded quite promising with their effort to allow for video chats over 56kbps Internet connections when Lyra is paired with the AV1 video codec. Getting decent voice quality at 3kbps was quite an engineering feat but made possible via their machine learning work.

It was unfortunate they hadn't published the code back then but now this week it's available in beta form.

The Lyra high-quality, low-bitrate speech codec is open-source with an initial v0.0.1 beta commit made today. Building Lyra requires the Bazel build system as well as a particular revision of LLVM/Clang for ABI compatibility.

The Lyra code can be found on GitHub. I'll be working on adding Lyra as an interesting Phoronix Test Suite benchmark shortly for looking at its performance characteristics.