Important Note
Please don't forget to check the version history of LMS as it is a system that allows users to store speech recognition models.
Q1 2026 (Jan–Mar 2026)
Enhancements
- Custom Pronunciation Support for WebSocket-Based Recognition
Custom pronunciation definitions, previously supported only over HTTP, can now also be applied to speech recognition requests made over WebSocket.
Improvements
- Updated System Components for Long-Term Support
Replaced end-of-support runtime components (Microsoft Visual C++ Redistributable 2013) with a currently supported version across LMS, improving long-term security and maintainability.