Checked fact 18828 Sep 2026Models and releases

The models create custom voices from natural-language prompts and can replicate a voice from a 30-second audio sample, across more than 100 languages.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

create bespoke voices from scratch by customizing role, accent and voice characteristics across more than 100 languages and dialects using natural language prompting ... Recreate consistent vocal profiles from just a 30-second audio sample

What the source said when we opened it, on 28 Sep 2026.

The source

Gemini 3.8 text-to-speech says hello
Google · 2026-09-23

Open the source archived copy

Checked

Checked by the notis newsroom on 28 Sep 2026, against the source above.

In the story

Google says Gemini 3.8 Flash TTS and Flash-Lite TTS are rolling out from September 23, 2026 in the Gemini API. 28 Sep 2026

Cite this fact

Short permanent address

In a sentence

“The models create custom voices from natural-language prompts and can replicate a voice from a 30-second audio sample, across more than 100 languages.” ai notis, checked 28 Sep 2026. Source: Gemini 3.8 text-to-speech says hello (Google). https://ainotis.com/c/188

As a reference (APA style)

ai notis. (2026, September 28). The models create custom voices from natural-language prompts and can replicate a voice from a 30-second audio sample, across more than 100 languages [Checked claim 188]. ai notis. https://ainotis.com/c/188

Anyone may quote this address. It does not change; if we correct the story, this page says so.