June 25th, 2025
Batch SaaS
Real-Time SaaS
Real-time transcription now supports the End of Utterance feature. When enabled, this helps detect the end of turn in a conversation. This can benefit use cases such as Voice Agents, dictation and translation, reducing latency. Refer to the documentation for more details.
New models released, notable accuracy uplifts for the below languages (Standard Operating Point only):
Relative improvements: Bashkir (ba) - 8%, Belarusian (be) - 37%, Bulgarian (bg) - 6%, Catalan (ca) - 18%, Galician (gl) - 41%, Korean (ko) - 7%, Latvian (lv) - 12%, Marathi (mr) - 9%, Mongolian (mn) - 5%, Thai (th) - 6%, Ukrainian (uk) - 18%, Vietnamese (vi) - 14%
💡Updated Orchestrator Version: "2025.06.28651+1eb4127132.HEAD"