Google is rolling out Gemini 3.8 Flash TTS and Flash-Lite TTS, new text-to-speech models designed to produce more natural and expressive AI-generated voices.
Gemini 3.8 Flash TTS can create custom voices from descriptions, replicate an authorized voice from a 30-second sample and control accents, pacing, emotion, pauses and conversational sounds. It can also generate consistent two-speaker dialogue in more than 100 languages and dialects.
The models are coming to Gemini Notebook and Google Vids, while developers can access both through Google AI Studio and the Gemini API. Google is also adding safeguards such as consent verification, SynthID watermarking and C2PA credentials for voice replication.
Source: Android Authority
