← Back to the wire

Intelligent transcription with Gemini 3.5 Transcribe

AnnouncementModelAug 26, 2026

Google announced Gemini 3.5 Transcribe, a speech-to-text model that achieved a 4.0% average Word Error Rate for streaming and 2.6% for non-streaming use, as measured by Artificial Analysis. Available in public preview via the Gemini API and Gemini Enterprise Agent Platform, it offers real-time streaming through gemini-3.5-transcribe-live and pre-recorded processing with speaker attribution. It supports over 85 languages, custom vocabulary, and function calling.

Receipt № 15811 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

GoogleCompanyGemini 3.5 TranscribeModelgemini-3.5-transcribe-liveModel
Canonical: https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5-transcribe/