LLM ReferenceLLM Reference

Gemini 3.1 Flash TTS Preview

Proprietary

About

Google's cost-efficient expressive text-to-speech model, released April 15, 2026. Supports 70+ languages, native multi-speaker dialogue, and 200+ audio style tags for precise delivery control. SynthID watermarking included. Achieves Elo 1,211 on the Artificial Analysis TTS leaderboard. Priced at $1.00/M input tokens and $20.00/M audio output tokens. API ID: gemini-3.1-flash-tts-preview.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

Rankings

Specifications

Released2026-04-15
Context16K
ArchitectureDecoder Only
Specializationaudio
LicenseProprietary
Trainingpretrained

Created by

Pioneering artificial intelligence research.

London, United Kingdom
Founded 2014
Website