# Gemini 3.1 Flash TTS

> Audio AI Model by Google — available on Layer

Google's most controllable TTS model with 200+ audio tags for vocal style and delivery.

Gemini 3.1 Flash TTS from Google is a next-generation text-to-speech model offering best-in-class controllability and expressiveness. It introduces 200+ audio tags that let you steer vocal style, pace, and delivery using natural language commands embedded directly in the text input. Supporting 70+ languages with native multi-speaker dialogue, it achieved an Elo score of 1,211 on the Artificial Analysis TTS leaderboard. All generated audio is watermarked with SynthID for responsible AI identification.

## Specifications

| Property | Value |
|----------|-------|
| Provider | Google |
| Category | Audio |
| Price | 0.03 / character count per character_count |

## Capabilities

- Text to Speech
- Auto Duration

---

[Try Gemini 3.1 Flash TTS](https://next.app.layer.ai/me/session/new?baseModelId=GEMINI_3_1_FLASH_TTS) | [All Audio Models](https://layer.ai/models/audio) | [All Models](https://layer.ai/models)