Google

Gemini 3.1 Flash Live Preview

Google's preview audio-to-audio model for low-latency dialogue with multimodal awareness, thinking, search grounding, and function calling.

Open provider docs See key facts

Plain-English overview

What Gemini 3.1 Flash Live Preview actually is

Gemini 3.1 Flash Live accepts live audio alongside text, images, and video, then returns text and audio. It is aimed at conversations that benefit from acoustic nuance and visual context rather than simple text-to-speech playback.

Google publishes both token rates and per-minute audio equivalents. This makes early budgeting easier, but search grounding and multimodal inputs can still add separate usage.

Good fit for

Multimodal voice assistants
Google search-grounded live experiences
Low-cost audio experimentation

Category comparison

The facts that matter for voice models

These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.

Price basisToken-, character-, or minute-based price for the listed access route.: Audio $0.005/min in · $0.018/min out
Interaction modeSpeech-to-speech, audio-to-audio, or streamed text-to-speech behavior.: Realtime audio-to-audio, multimodal input
Published latencyProvider-published measurement with its stated exclusions; not a Cody test.: Not published
LanguagesProvider-documented language coverage or a clear unpublished marker.: Multilingual; verify current Live API support
Tools & controlNative function calling, reasoning, or speech-control features.: Function calling and search grounding
Context or input limitDocumented token or character limit where it is meaningful.: 131,072 input · 65,536 output

Pricing source: Google ↗Speed basis: Google ↗

API and provider access

Where to get Gemini 3.1 Flash Live Preview

GoogleGemini 3.1 Flash Live docsDirect Gemini Live API access.

Availability

Regions and access stage

Preview access through the Gemini Live API and Google AI Studio in supported regions.

Use Google's live Gemini API region list and confirm preview eligibility.

Check live availability

Data and training

The route matters.

Google says paid Gemini API content is not used to improve its products; unpaid service data generally can be. Confirm billing status and current terms before sending sensitive conversations.

This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.

Read the provider policy

Frequently asked questions

Gemini 3.1 Flash Live Preview FAQ

What is Gemini 3.1 Flash Live Preview?

Google's preview audio-to-audio model for low-latency dialogue with multimodal awareness, thinking, search grounding, and function calling. Gemini 3.1 Flash Live accepts live audio alongside text, images, and video, then returns text and audio. It is aimed at conversations that benefit from acoustic nuance and visual context rather than simple text-to-speech playback.

When was Gemini 3.1 Flash Live Preview released?

Gemini 3.1 Flash Live Preview was released on March 1, 2026 according to the cited provider materials.

Where can I access Gemini 3.1 Flash Live Preview?

Preview access through the Gemini Live API and Google AI Studio in supported regions. The access routes listed in this guide are Google.

How much does Gemini 3.1 Flash Live Preview cost?

$0.005/min audio input · $0.018/min audio output. Google's paid-tier equivalents; text input/output are $0.75/$4.50 per million tokens and image/video input is $0.002 per minute equivalent.

Where is Gemini 3.1 Flash Live Preview available?

Preview access through the Gemini Live API and Google AI Studio in supported regions. Use Google's live Gemini API region list and confirm preview eligibility.

Is my Gemini 3.1 Flash Live Preview API data used for training?

Google says paid Gemini API content is not used to improve its products; unpaid service data generally can be. Confirm billing status and current terms before sending sensitive conversations. The policy belongs to the provider route and account terms, so verify it again before production use.

Research trail

Sources for this guide

Checked September 3, 2026

Keep comparing

More voice & realtime models

View category

OpenAI · Stable

GPT-Realtime-2.1

OpenAI's realtime speech-to-speech reasoning model for tool-using voice agents that also need text and image context.

Read guide

ElevenLabs · Stable

Eleven v3 Conversational

ElevenLabs' expressive realtime text-to-speech model for natural dialogue, emotional delivery, audio tags, and more than 70 languages.

Read guide

Inworld AI · Stable

Inworld Realtime TTS-2

Inworld's newest expressive realtime text-to-speech model, designed to remember conversational delivery and speak in more than 100 languages.

Read guide