This post continues where we left of after the previous part: Optimizing wLipSync. While it seemed there wouldn’t be much performance left to squeeze out after the initial improvements, that turned out to be false.

As is often the case in software development, letting a problem rest for a while leads to fresh ideas and new insights.

When porting uLipSync for the web, the choice for WASM was quickly made. Performance is paramount for audio processing. Especially since the lip sync should run in realtime on mobile devices. However, just using WASM does not automatically mean performance. After porting the C# code to C++, it was time to look for possible optimizations.