# Google AI launches Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS

Google AI is launching two speech models that can create custom voices in more than 100 languages or use more than 2,000 ready-made voices, with conversation direction and line-by-line delivery control.

Language: en
Time zone: America/Los_Angeles
Current time (UTC, cached as of): 2026-11-10T07:01:00.000Z
Query date (America/Los_Angeles): 2026-11-09

HTML: https://didcodexreset.com/news/2a588785df0d44a785e3e565.html

Content language: en
Localization state: sameLanguage

Source: Google AI · Published 9/23/2026, 08:33:34

Google AI is launching Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, which it calls its most expressive audio models yet. The models can create custom voices across more than 100 languages or use more than 2,000 ready-made voices. They can direct back-and-forth conversations, guide delivery line by line, and add cues such as laughs or an active-listening “mhm.” Google AI says they can generate hours of consistent, glitch-free audio.

Gemini 3.8 Flash TTS is for designing vocal personas from scratch with line-by-line control, aimed at high-fidelity production such as games, audiobooks, and podcasts. Gemini 3.8 Flash-Lite TTS is built to adjust tone and pacing automatically for near real-time voice agents, as well as cost-efficient, high-volume dubbing and bulk audio.

Tags: Google AI, Gemini, Text-to-speech, Voice

[View original post](https://x.com/GoogleAI/status/2102781694730285427)