Open Source C++ Codec Software for Windows

lyra is a neural audio codec designed to deliver intelligible, natural-sounding speech at extremely low bitrates, making real-time communication viable on constrained networks. It replaces hand-engineered codecs with learned models that capture speech characteristics more efficiently and reconstruct waveforms with a neural vocoder. The system targets mobile-class hardware, balancing latency and quality so it can run in real-time on phones. Its architecture is resilient to packet loss and jitter through framing strategies and error concealment, helping conversations remain understandable under adverse conditions. The codebase includes encoder and decoder components, along with tools for data preparation and evaluation. By pushing bitrates down to just a few kilobits per second while retaining quality, lyra expands access to voice calls where bandwidth is scarce.

This project aims to development a universal media codecs for video/audio/image processing. It use same interfaces for all codecs. And it target system is embedded system. The codecs will be include: MPEG2, MPEG4, H264, AAC, VC-1, AVS.