#text-to-speech

All articles tagged with "text-to-speech"

Gemini 3.1 Flash TTS: the next generation of expressive AI speech

Google Expands AI Voice Tools With Gemini 3.1 Flash TTS Preview

Google has begun rolling out Gemini 3.1 Flash TTS, a new text-to-speech model aimed at giving developers and enterprise users finer control over synthetic voices while extending support to more than 70 languages.

Key Takeaways

Google is previewing Gemini 3.1 Flash TTS across its developer, enterprise and Workspace products.
The model adds natural-language audio tags for more precise control over delivery and style.

DT Editorial Team·Apr 18, 2026·via blog.google

Google expands Gemini speech tools with a more expressive TTS model

Google says its new Gemini 3.1 Flash TTS model adds finer control over speech style and supports more than 70 languages, positioning it as a stronger developer option in a crowded voice market.

Key Takeaways

Google says Gemini 3.1 Flash TTS is its most natural and expressive speech model yet.
The system adds audio tags for style, pace, tone, and accent control across 70+ languages.

DT Editorial Team·Apr 16, 2026·via the-decoder.com

Washington State's Spanish Hotline Spoke English in a Spanish Accent Due to AI Misconfiguration

When Washington residents pressed 2 for Spanish on the state's DMV phone line, they heard English words pronounced with a Spanish accent instead of actual Spanish. The embarrassing error was traced to Amazon's Polly text-to-speech system being fed English text with a Spanish-language voice.

Key Takeaways

DMV phone system used Amazon Polly's Spanish voice to read English text
TikTok video exposing the error went viral with millions of views

DT Editorial Team·Mar 1, 2026·4 min read·via gizmodo.com