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

> Google makes its new Gemini 3.8 Flash TTS and Flash‑Lite TTS APIs generally available, offering higher‑quality and faster voice generation.

Oossa · 2026-09-30 · https://oossa.com/en/google-launches-gemini-3-8-flash-text-to-speech-models-65295

Google announced that Gemini 3.8 Flash TTS and Gemini 3.8 Flash‑Lite TTS are now generally available (GA) as part of the Gemini API. The Flash model is designed for studio‑quality voice, regional accents and long‑form content, while the Lite version is cheaper and faster for high‑throughput, real‑time audio. Both models are accessed via the new /v1beta/voices endpoint.

## The facts

- Release date: 22 September 2026
- Model names: gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts

## Why it matters

Developers can now add more natural, customizable speech to apps without the latency or cost of earlier models.

## Sources & references

1. [ai.google.dev: 5 Mayıs 2026](https://ai.google.dev/gemini-api/docs/changelog#05-05-2026) – Google Gemini API, 2026-09-30

Last updated: 2026-09-30