Google DeepMind logoGoogle DeepMindAudio

Gemini 3.8 Flash TTS

Expressive text-to-speech with voice design, character direction and multilingual dialogue.

Playground

Audio Generator

Model

Gemini 3.8 Flash TTS

No audio generated yet

Enter text and click Generate to create audio.

About this model

Capabilities & specifications

Input
Text
Output
Audio

Gemini 3.8 Flash TTS supports single- and multi-speaker generation, natural-language voice design and fine-grained performance direction. Its transcript and styling inputs are distinct from the unstructured audio conversation supported by a Live API.

  • Voice synthesis
Speech generation

Examples

Gemini expressive speech demonstration excerpt

Model output documented by the source.

blog.google

Questions and answers

Where do Gemini 3.8 Flash TTS specifications come from?

The references below identify the sources for this model’s capabilities. Confirm current access, request limits and pricing with your service provider before integration.

Where do Gemini 3.8 Flash TTS specifications come from?

Things to consider

Review generated results before use. Available modes and request limits depend on the service you choose; check the linked documentation before integration.

Model information sources

  • Gemini 3.8 Flash TTS reference