Independent newsroom

Thursday, September 24, 2026

The File

Every claim traces to a primary source. Uncertainty is labeled. Corrections are public.

Google · Thursday, September 24, 2026

Google ships Gemini 3.8 Flash TTS and Flash-Lite TTS

The File desk · Sep 24, 2026, 10:25 AM UTC

Status

Confirmed (Google blog, Sept. 23, 2026)

On Sept. 23, 2026, Google introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS — new text-to-speech model IDs with generative voice design, consent-gated voice replication from a short sample, and SynthID watermarking. Developers can try them in Google AI Studio. These are speech models, not a new general frontier twin.

On Sept. 23, 2026, Google introduced two new text-to-speech models in the Gemini family.

Gemini 3.8 Flash TTS is the creative voice-design model. Gemini 3.8 Flash-Lite TTS is the high-volume, cost-efficient model.

The post describes generative voice design and voice replication from a 30-second sample, with consent checks.

Audio carries SynthID watermarking.

Developers can try the models in Google AI Studio. The post also names the Gemini API and Vids, with an enterprise rollout later.

These are speech models. They are not a new general frontier twin.

What is still unknown or disputed

Primary sources

Every claim in this story is drawn from the documents below. If a fetch failed, that is recorded on the card.

  1. Source 1

    Introducing Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS

    Google · September 23, 2026

    Today, we’re introducing two new text-to-speech models to the Gemini family… Gemini 3.8 Flash TTS… Gemini 3.8 Flash-Lite TTS… Starting today, developers can experience these new speech generation capabilities in Google AI Studio.

    https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-text-to-speech/