Google Launches Gemini 3.5 Transcribe Speech Model

Google has introduced Gemini 3.5 Transcribe, its most accurate speech-to-text model, available to developers via the Gemini API, Google AI Studio, and Gemini Enterprise Agent Platform. The model offers real-time streaming with sub-second latency and pre-recorded audio processing with speaker attribution, achieving word error rates of 4.0% and 2.6% respectively. The model handles over 85 languages, removes filler words, recognizes custom vocabulary, and supports multi-speaker identification. It is already integrated into Gboard's Rambler feature, the Gemini macOS app, and Google Antigravity, with Chrome support coming soon.