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

> On 22 September 2026 Google made its next‑gen text‑to‑speech models generally available via the Gemini API.

Oossa · 2026-09-30 · https://oossa.com/en/google-adds-gemini-3-8-flash-tts-and-flash-lite-tts-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 targets high‑quality, studio‑like voices with regional accents and long‑form stability. The Flash‑Lite version is faster and cheaper, designed for real‑time audio agents. Developers can start using them via the new /v1beta/voices endpoint.

## The facts

- 22 Sep 2026 – GA release of gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts
- Two new TTS models: high‑fidelity (Flash) and low‑latency, low‑cost (Flash‑Lite)

## Why it matters

The models let apps add more natural, multilingual speech at lower cost, expanding voice‑based experiences.

## Sources & references

1. [ai.google.dev: 6 Mayıs 2026](https://ai.google.dev/gemini-api/docs/changelog#05-06-2026) – Google Gemini API, 2026-09-30

Last updated: 2026-09-30