MODEL RELEASEAUDIOreleaseGoogle

Gemini 3.1 Flash TTS Preview

Cost-efficient, expressive, and steerable text to speech model.

Visit site

Google's cost-efficient, expressive, and steerable text-to-speech model for generating audio from text.

Pricing

Official site · Apr 16, 2026, 6:22 AM

Input / 1M

$1.00

Output / 1M

$20.00

Audio tokens correspond to 25 tokens per second of audio. The pricing page lists the model under Gemini-TTS as Gemini 3.1 Flash TTS (Preview).

Google’s official Text-to-Speech pricing page lists Gemini 3.1 Flash TTS (Preview) at $1.00 per 1 million text input tokens and $20.00 per 1 million audio output tokens, with no free usage limit. This is a first-party public price for the named preview model.

View source

Model Intelligence

Context window

8,192 tokens

Benchmarkable

Yes

Model level

release

Recent stories

1 linked story

releasePRIMARY2026-04-15

Gemini 3.1 Flash TTS launches with Audio Tags, 70+ languages and API preview

Google released Gemini 3.1 Flash TTS with inline Audio Tags, multi-speaker control and 70+ languages, and opened preview access through the Gemini API and AI Studio with rollout to Vertex AI and Google Vids. Independent evals ranked it near the top of current speech leaderboards, but it runs slower and costs more than the leading system.