> For the complete documentation index, see [llms.txt](https://docs.facephi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.facephi.com/docs.facephi-en/sdks/backend-sdk/voice/release_notes/2.9.0_release_notes.md).

# 2.9.0

This Version includes new improvements to the voice engine, especially in noisy environments. The verification algorithm has been updated to offer greater accuracy, and a new algorithm has been implemented for SNR estimation.

### Added

* The Docker image Version is updated to Ubuntu 24.04.
* The number of threads (threads) in the service configuration is 1 by default.
* A new verification algorithm with greater accuracy is added.
* The accuracy of the verification algorithms and liveness detection in noisy scenarios is improved. The verification score may differ slightly compared to the previous Version, but the voice templates remain compatible.
* The recommended threshold for the relative speech length quality check, in the use cases of verification and liveness detection, is now 0 (any relative speech length is allowed).
* The SNR estimation algorithm is updated. The estimated values may differ from those of the previous Version of the product, but the overall accuracy of the algorithm remains the same.
