Does Gemini 3.1 Flash TTS (text-to-speech) preview support streaming output?

Yes. Gemini 3.1 Flash TTS (text-to-speech) preview is declared as supporting streamed responses.

Can Gemini 3.1 Flash TTS (text-to-speech) preview clone a voice, and how much sample audio does it need?

Gemini 3.1 Flash TTS (text-to-speech) preview supports voice customization. Check the API documentation for available voice options.

What is the maximum audio length per request on Gemini 3.1 Flash TTS (text-to-speech) preview?

Gemini 3.1 Flash TTS (text-to-speech) preview accepts up to 8,192 tokens of input text. Check the API documentation for maximum audio duration.

How do you start calling Gemini 3.1 Flash TTS (text-to-speech) preview?

Set the model parameter to “gemini-3.1-flash-tts-preview” and use your MixRoute API key. Compatible with OpenAI SDK.

What is the rate limit for Gemini 3.1 Flash TTS (text-to-speech) preview?

Rate limits for Gemini 3.1 Flash TTS (text-to-speech) preview depend on your MixRoute plan tier. Check your console quota.

What should you evaluate before moving production traffic to Gemini 3.1 Flash TTS (text-to-speech) preview?

Before switching production traffic to Gemini 3.1 Flash TTS (text-to-speech) preview, run a pilot on a representative slice of your traffic and check output quality, latency at peak concurrency, and cost per request. Verify the error and retry behaviour, and confirm the request limits you depend on match your plan.

When was Gemini 3.1 Flash TTS (text-to-speech) preview released, and is it still maintained?

Gemini 3.1 Flash TTS (text-to-speech) preview is listed with catalog status stable. The recorded release date is 2026-04-15. Check the model page for deprecation notices before you build a long-lived integration on it.

Model detail

Gemini 3.1 Flash TTS (text-to-speech) preview

Provided by Google

Pay-as-you-go

A low-latency Gemini speech model with expressive audio tags and prompt controls for natural, multilingual narration.

Model specs

Model ID: gemini-3.1-flash-tts-preview

Context length: 8.192K
Max output: 8.192K
I/O modalities
Released: 2026-04

API endpoints

One MixRoute gateway, OpenAI-compatible

Gemini /v1beta/models/{model}:generateContent POST
OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$1.0000 /1M Tokens

Completion

$20.0000 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Text-To-Speech synthesis for low-latency speech generation with steerable prompts and expressive audio tags for precise narration

Gemini 3.1 Flash TTS — Powerful, low-latency speech generation with natural outputs, steerable prompts, and expressive audio tags.

What should you check before using it?

8,192 context, 8,192 output

Text-To-Speech. Knowledge cutoff: 2025-01. Released 2026-04.

Why use it through MixRoute?

Available through MixRoute's OpenAI-compatible endpoint

Use the Google Gen AI SDK or call through MixRoute. Set the model parameter to "gemini-3.1-flash-tts-preview".

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Streaming

Gemini 3.1 Flash TTS (text-to-speech) preview supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens Max per request 8.192K

Output tokens Max per request 8.192K

Requests / month

Cache hit rate –

This model has no cache-read price; caching is not counted

FAQ

Gemini 3.1 Flash TTS (text-to-speech) preview: A low-latency Gemini speech model with expressive audio tags and prompt controls for natural, multilingual narration.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

gemini-3.1-flash-tts-preview

Create an API key

New users get $5 in free credits

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs