2025.05.22 - SaaS

New

• Reduce the likelihood of incorrectly switching between similar sounding speakers by setting the prefer_current_speaker parameter. Refer to documentation for more details.

• Real-time transcription now supports the speaker_sensitivity parameter to configure the sensitivity of speaker detection. Refer to documentation for more details.

Fixes

• Real-time transcription - Fix for failure to generate Final transcripts for numbers when punctuation is disabled.