# Google launches Gemini 3.8 Flash and Flash‑Lite text‑to‑speech models

> The new models let developers create custom voices with prompts and scale high‑volume dubbing, available via the Gemini API from Sep 22 2026.

Oossa · 2026-09-29 · https://oossa.com/en/google-launches-gemini-3-8-flash-and-flash-lite-text-to-speech-models

Google announced that its Gemini 3.8 Flash TTS and Gemini 3.8 Flash‑Lite TTS models are now generally available. Flash TTS is aimed at creative voice design – you can describe a character’s accent, tone and pace in plain text and get a studio‑quality voice. Flash‑Lite TTS is built for cheap, high‑throughput dubbing and voice‑agent use. Both models are accessible through the Gemini API and Google AI Studio.

## The facts

- Release date: 22 Sep 2026 (GA)
- Model IDs: gemini‑3.8‑flash‑tts and gemini‑3.8‑flash‑lite‑tts

## Why it matters

They give developers a simple way to generate expressive, custom audio at scale, opening new possibilities for audiobooks, games and real‑time voice agents.

## Sources & references

1. [ai.google.dev: 18 Şubat 2026](https://ai.google.dev/gemini-api/docs/changelog#02-18-2026) – Google Gemini API, 2026-09-29

Last updated: 2026-09-29