# Google adds Gemini 3.8 Flash TTS models to its API

> On 22 Sept 2026 Google released two new text‑to‑speech models, Gemini 3.8 Flash TTS and Flash‑Lite TTS, via the Gemini API.

Oossa · 2026-09-30 · https://oossa.com/en/google-adds-gemini-3-8-flash-tts-models-to-its-api-65299

Google announced that its Gemini API now offers two new text‑to‑speech (TTS) models. Gemini‑3.8‑flash‑tts is a high‑quality, studio‑grade voice model with regional dialects and long‑form stability. Gemini‑3.8‑flash‑lite‑tts is a faster, cheaper model meant to replace the older flash‑tts‑preview for real‑time voice agents.

## The facts

- Release date: 22 Sept 2026
- Models added: gemini‑3.8‑flash‑tts and gemini‑3.8‑flash‑lite‑tts

## Why it matters

Developers can now add more natural, cost‑effective voice output to apps, especially for agents that need real‑time conversation.

## Sources & references

1. [ai.google.dev: 4 Mayıs 2026](https://ai.google.dev/gemini-api/docs/changelog#05-04-2026) – Google Gemini API, 2026-09-30

Last updated: 2026-09-30