# Google adds Gemini 3.8 text‑to‑speech models to API

> On 22 Sep 2026 Google made its new Gemini 3.8 Flash TTS and Flash‑Lite TTS models generally available via the Gemini API.

Oossa · 2026-09-29 · https://oossa.com/en/google-adds-gemini-3-8-text-to-speech-models-to-api

Google announced that the Gemini 3.8 Flash TTS and Gemini 3.8 Flash‑Lite TTS models are now generally available (GA) through the Gemini API. The Flash TTS model focuses on studio‑quality voice fidelity, nuanced accents and long‑form stability. The Flash‑Lite TTS version is faster and cheaper, aimed at high‑throughput, real‑time voice agents.

## The facts

- 22 Sep 2026 – GA launch of gemini‑3.8‑flash‑tts and gemini‑3.8‑flash‑lite‑tts
- Flash‑Lite TTS is positioned as a cost‑effective alternative for large‑scale production

## Why it matters

Developers can now add higher‑quality or cheaper real‑time speech synthesis to their apps using Google’s latest Gemini models.

## Sources & references

1. [ai.google.dev: 19 Aralık 2025](https://ai.google.dev/gemini-api/docs/changelog#12-19-2025) – Google Gemini API, 2026-09-29

Last updated: 2026-09-29