Google DeepMind announces Gemini 3.5 Transcribe for real-time speech recognition
Gemini 3.5 Transcribe is available through the gemini-3.5-transcribe-live and gemini-3.5-transcribe APIs. Google reports 4.0% streaming WER and 2.6% nonstreaming WER, with support for over 85 languages and identification of up to three speakers.
Visit original source