How to build with Gemini 3.5 Transcribe

Why watch

Google DeepMind's Thor Schaeff demonstrates building real-time transcription applications using Gemini 3.5 Transcribe on the Interactions API and Live API. The tutorial covers transcribing email addresses, phone numbers, and multilingual speech, plus how to use custom vocabulary and language hints to achieve high accuracy across 85+ supported languages. Developers looking to integrate speech-to-text capabilities into their applications will find this practical implementation guide useful.