Google's new Gemini 3.5 Transcribe recognizes over 85 languages, strips filler words, and corrects slips of the tongue in real time. It hits a 4.0 percent word error rate in streaming mode, with 70 percent lower latency than its predecessor, Chirp 3. Through function calling, the model can hand off tasks to other Gemini models.
The article .
Vollständiger Original-Bericht
Ausführliche Details, Code-Beispiele & Hersteller-Stellungnahme auf the-decoder.com.
