Official Source· Google Gemini News· AI· Published Sep 29, 2026

Google introduces Gemini 3.8 Flash TTS and Flash-Lite TTS

Announced September 23, the two text-to-speech models target different needs: custom voice direction and detailed performance guidance, or high-volume audio generation. Both are rolling out through the Gemini API and Google AI Studio, with Flash TTS also coming to Gemini Notebook and Flash-Lite TTS to Google Vids.

Google introduces Gemini 3.8 Flash TTS and Flash-Lite TTS

Full Report

Google announced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS on September 23, 2026, positioning the two text-to-speech models for different use cases. Flash TTS focuses on custom voice direction and detailed performance guidance, while Flash-Lite TTS is aimed at high-volume audio generation.

Both models are beginning to roll out through the Gemini API and Google AI Studio. Google is also bringing them to different products: Flash TTS to Gemini Notebook and Flash-Lite TTS to Google Vids.

The announcement gives developers two distinct model options while extending text-to-speech capabilities into Google’s notebook and video products. The separate product rollouts underline the release’s two tracks: access through developer tools and integration into specific Google products.

Why This Matters

The models have distinct stated emphases: one offers more control over voice and performance, while the other targets high-volume generation. That distinction gives developers a clearer basis for choosing between them, and both models share the Gemini API and Google AI Studio as rollout channels.

Evidence

Start with the primary evidence, then review supporting sources and context.

1 items

Primary Evidence

1
  • OfficialGoogle Gemini NewsDocumentOriginal

    Gemini 3.8 text-to-speech says hello

    Leland Rechis

    “a text card image reading "Introducing Gemini 3.8 Flash TTS and 3.8 Flash-Lite TTS"”

Recommended signals

Recommended by brand, topic, and recent related coverage

No more recommended signals right now

Official statement

Open original source