Gemini 3.8 text-to-speech says hello

First reported 23 Sep, 15:15 UTCSource: Google BlogLast editorial activity 23 Sep, 15:15 UTC

Close-up of a GeForce RTX graphics card on a desk, showcasing its design and technology. — Illustrative photo.Photo by Trần Chính on PexelsGoogle logo shown for identification only; no affiliation with or endorsement of WORLDTECH is implied.

What happened

Google just launched new AI tools that let you create and customize realistic voices from scratch. Plus, they added safety features to make sure these voices are used responsibly.

Use these models for high-quality audiobooks, podcasts, or real-time voice agents at scale. These models enable creators, developers, and enterprises to create richer, more expressive audio experiences, while enabling improved user experiences in products like Gemini Notebook and Google Vids .

Gemini 3.8 Flash TTS: Built for deep creative direction and character design. Gemini 3.8 Flash-Lite TTS: Built for high-volume, cost-efficient scale.

Sources & evidence

Google Blog Primary / official
Gemini 3.8 text-to-speech says hello ↗
https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-text-to-speech/

What happened

Sources & evidence

Your privacy choice