Google’s new Gemini TTS models can clone a voice from 30 seconds of audio

TNW•Wed, Sep 23, 2026, 03:58 PM•2 min read

“Today, we’re introducing two new text-to-speech models to the Gemini family, transforming voice generation from static presets into a dynamic creative studio,” Google wrote in its announcement. Google released Gemini 3. 8 Flash TTS and Gemini 3.

Source: [TNW](https://thenextweb.com/news/gemini-tts-3-8-flash-voice-design-cloning)

📰 Read Full Story

This is an aggregated headline summary. For the complete report, visit the original publisher.

Continue Reading at TNW ↗

#tech #gemini #google #tts #models #voice #today #studio #flash

More Headlines

TechnologyHacker News• 5m ago

KDE and AI, and You, and Me

1 points, 0 comments on Hacker News

TechnologyHacker News• 5m ago

Security auditing in the age of (good enough) AI

1 points, 0 comments on Hacker News

TechnologyDev.to• 8m ago

Flash Loan Attack Vector Analysis: Bitstamp

Flash Loan Attack Vector Analysis: Bitstamp Target Protocol : Bitstamp (TVL: $4526. 5M) Flash‑Loan Attack Vector Analysis – Bitstamp Prepared by: Senior DeFi Security Researcher Date: 23 September 2026 1. Executive Summary Bitstamp, one of the longest‑running crypto custodial platforms, has rece...

TechnologyHacker News• 9m ago

Buzz: Share spare compute and run open models together over P2P networks

1 points, 0 comments on Hacker News

TechnologyHacker News• 10m ago

Prepping for an engineering interview? Created this skill you can use

1 points, 0 comments on Hacker News

TechnologyDev.to• 11m ago

Gemini App Integrations May Expand: What Businesses Should Watch Next

Google Gemini may be preparing to add more app integrations. The available teaser says that more users' favorite apps are coming to Gemini, but it does not identify partners, provide a launch schedule, explain functionality, or disclose any pricing changes. For businesses, the practical takeawa...