When will Azure Pronunciation Assessment for en-GB leave preview status?

Frauke Leiss 0 Reputation points
2026-08-04T13:12:31.9166667+00:00

Hi, we're trying to build an English pronunciation practice app for German secondary schools using Azure Speech Pronunciation Assessment. We currently use en-US because en-GB is still in preview and returns empty Phonemes[].Phoneme labels (confirmed via both REST and the Node.js SDK), plus noticeably less sensitive word-level accuracy scoring.

Is there a rough timeline for en-GB Pronunciation Assessment leaving preview with full phoneme-level support? We'd like to switch back once it's production-ready, since our students are taught British English. Thanks!

Azure Speech in Foundry Tools

1 answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. Sridevi Machavarapu 33,820 Reputation points Microsoft External Staff Moderator
    2026-08-06T06:19:32.25+00:00

    Hi Frauke Leiss,

    Thank you for your question.

    According to the Microsoft Learn documentation, en-GB is a supported locale for Pronunciation Assessment and is recommended when evaluating British English pronunciation:

    https://learn.microsoft.com/azure/ai-services/speech-service/language-support?tabs=pronunciation-assessment

    The Supported features per locale section of the Pronunciation Assessment documentation shows that some phoneme-related features are available only for specific locales:

    Feature IPA SAPI
    Phoneme name en-US en-US, zh-CN
    Syllable group en-US en-US
    Spoken phoneme en-US en-US

    The documentation also states:

    For locales that support phoneme name, the phoneme name is provided together with the score. For other locales, you can only get the phoneme score.

    References:

    At this time, there is no publicly available information or timeline regarding additional phoneme name support for other locales.

    Was this answer helpful?

    0 comments

Your answer

Answers can be marked as 'Accepted' by the question author and 'Recommended' by moderators, which helps users know the answer solved the author's problem.