Google has introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, describing them as its most expressive audio-generation models yet. In a post on X, @GoogleAIStudio says the models are intended to help creators, developers and enterprises build richer, more expressive audio experiences.

What Google announced

The announcement names two models:

  • Gemini 3.8 Flash TTS

  • Gemini 3.8 Flash-Lite TTS

TTS, or text to speech, refers to technology that generates spoken audio from written text. Google presents both models as audio-generation tools, but the post does not explain how the standard Flash TTS model differs from the Flash-Lite version.

The announcement also does not include supported languages, voice options, expressive controls, audio formats, latency figures, context limits, pricing, quotas or benchmark results. It provides no generated-audio examples for comparison.

Where developers can try the models

Google says the models can be tried through the Gemini API and in Google AI Studio's speech-generation interface. The linked AI Studio page is configured for Gemini 3.8 Flash TTS.

The supplied announcement does not establish the models' broader rollout scope, eligibility requirements or implementation details. Developers evaluating them for production use will need more information about availability, limits, pricing and supported functionality than this post provides.

Sources