Skip to content
Google

Gemini 3.1 Flash Live

audio

Google•Released on 2026-03-26

Google's highest-quality audio and voice model for real-time dialogue. Released March 26, 2026. Delivers natural rhythm and low latency for voice-first AI applications. Supports 70+ languages with SynthID audio watermarking.

77
Overall Score

Core Specs

0K
Context Window
0K
Max Output
✗
Reasoning
✗
Open Source
Multimodal Support
audiovoicetext

Scenario Scores

Coding
—
Writing
#53 / 5360
Translation
#36 / 5380
Data Analysis
—
Conversation
#5 / 5390
Image Gen
—

User Feedback Highlights

Based on community feedback. Hover to see original reviews.

− Limited to Google ecosystem for full features− Specialized for audio/voice (not text)− Preview only — API pricing TBA+ SynthID audio watermarking+ Natural rhythm and intonation+ Available in 200+ countries via Gemini Live+ Real-time voice dialogue+ Low latency audio processing
Sentiment:👍 70%😐 25%👎 5%

Pros & Cons

Pros

  • +Real-time voice dialogue
  • +Natural rhythm and intonation
  • +Low latency audio processing
  • +SynthID audio watermarking
  • +Available in 200+ countries via Gemini Live

Cons

  • −Preview only — API pricing TBA
  • −Specialized for audio/voice (not text)
  • −Limited to Google ecosystem for full features

Reliability

Incidents (30d)0
View Status Page →

Pricing

Input (per 1M tokens)$0.00
Output (per 1M tokens)$0.00
Free trial available
Updated on 2026-04-21

Get Started

1Visit the provider's website
2Create an account
3Start using the model

Compare with Others

Gemini 3.1 Flash Live vs Claude Opus 4.7 →Gemini 3.1 Flash Live vs Claude Opus 4.6 →Gemini 3.1 Flash Live vs Claude Opus 4.5 →

Benchmarks

complexFuncBenchAudio90.8%
audioMultiChallenge36.1%
noteComplexFuncBench-Audio: multi-step function calling with constraints. AudioMultiChallenge: Scale AI benchmark with thinking enabled.%