PulseAugur
LIVE 14:32:31
research · [1 source] ·
0
research

Google AI ships Gemini 3.1 Flash TTS and Robotics-ER 1.6 models

Google AI has released Gemini 3.1 Flash TTS, a new text-to-speech model. This model offers native multi-speaker dialogue capabilities and enhanced control over voice expression. It supports over 70 languages and aims to produce more natural and expressive audio. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

RANK_REASON Release of a new model by a major AI lab, but not described as a frontier model or paradigm-shifting.

Read on X — Google AI →

COVERAGE [1]

  1. X — Google AI TIER_1 · GoogleAI ·

    What a week! Here’s everything we shipped:

    What a week! Here’s everything we shipped: — Gemini 3.1 Flash TTS, our latest text-to-speech model, featuring native multi-speaker dialogue and improved controllability and audio tags for more natural, expressive voices in 70+ languages — Gemini Robotics-ER 1.6 by