# Google adds Gemini 3.8 Flash and Flash‑Lite TTS models to API

> Two new voice generation models—gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts—became generally available on 22 Sept 2026.

Oossa · 2026-09-29 · https://oossa.com/en/google-adds-gemini-3-8-flash-and-flash-lite-tts-models-to-api

Google announced that the Gemini API now includes two text‑to‑speech (TTS) models. The flagship gemini‑3.8‑flash‑tts is tuned for studio‑quality voices, regional accents and long multi‑turn conversations. The faster, cheaper gemini‑3.8‑flash‑lite‑tts is meant for high‑volume real‑time use and replaces the preview model gemini‑3.1‑flash‑tts‑preview.

## The facts

- 22 Sep 2026 – Gemini 3.8 Flash and Flash‑Lite TTS models GA
- Endpoints: /v1beta/voices

## Why it matters

Developers can now add higher‑quality or lower‑cost voice output to apps using the same Gemini API.

## Sources & references

1. [ai.google.dev: 1° giugno 2026](https://ai.google.dev/gemini-api/docs/changelog#06-01-2026) – Google Gemini API, 2026-09-29

Last updated: 2026-09-29