Google Unveils Gemini 3.8 TTS Models for Multilingual Audio Generation

WHO:

MarkTechPost - Google is the organization releasing the new models.

WHAT:

Small Business Trends - Google Gemini is described as transforming voice technology with the launch of two innovative AI models designed for smarter, more intuitive voice interactions.

MarkTechPost - Google has released two new text-to-speech models: Gemini 3.8 Flash TTS and Flash-Lite TTS.

MarkTechPost - Flash TTS ranks #1 on Hume AI's Voice Design Benchmark with a score of 71.4.

Techmeme - The models support more than 100 languages.

Techmeme - Gemini 3.8 Flash TTS and Flash-Lite TTS are described as Google's "most expressive audio generation models yet."

WHERE:

MarkTechPost - The models are available through the Gemini API and Google AI Studio.

HOW:

MarkTechPost - Flash TTS designs new voices from natural language prompts.

MarkTechPost - Flash-Lite TTS targets high-volume dubbing and voice agents at a lower cost.

(UPDATED September 23, 2026 22:00 UTC)

Google Gemini is making waves in the tech world with the launch of two innovative AI models that promise to transform voice technology. These advancements are designed to create smarter and more intuitive voice interactions, enhancing how users engage with devices. This exciting development is set to reshape the landscape of voice technology in the coming months.

--

(UPDATED September 23, 2026 21:02 UTC)

Google has just released two new text-to-speech models called Gemini 3.8 Flash TTS and Flash-Lite TTS, which are now available through the Gemini API and Google AI Studio. Flash TTS has achieved the top rank on Hume AI's Voice Design Benchmark with an impressive score of 71.4, and both models support over 100 languages, making them Google's most expressive audio generation models yet. While Flash TTS creates new voices from natural language prompts, Flash-Lite TTS is designed for high-volume dubbing and voice agents at a lower cost.