The Hallway Track
Product Launches

How to build with Gemini 3.5 Transcribe

Google Developers (Google I/O) · Aug 26, 2026 · Product Launches

Google launches Gemini 3.5 Transcribe, its first LLM-based transcription model with live streaming support.

“this model is both available for unary on the interactions API but also for life transcription on the life API”

Google has launched Gemini 3.5 Transcribe, an LLM-based transcription model available via both batch and live streaming APIs. Unlike traditional ASR models, it leverages language model capabilities to correctly handle alphanumeric content like email addresses and phone numbers, and supports custom vocabulary injection. The LLM foundation gives it an edge on structured data transcription, though this developer demo session lacks broader strategic context.

Google Gemini speech-to-text transcription multimodal API

Watch / read the original source →