Gemini 3.1 Flash Live: Making audio AI more natural and reliable
Quick Answer
Google DeepMind's Gemini 3.1 Flash Live enhances audio AI with improved precision and lower latency, achieving a 90.8% score on the ComplexFuncBench Audio benchmark.
Quick Take
Google DeepMind's Gemini 3.1 Flash Live enhances audio AI with improved precision and lower latency, achieving a 90.8% score on the ComplexFuncBench Audio benchmark. This model is now available via the Gemini Live API and supports real-time dialogue across over 200 countries, making voice interactions more natural and reliable for developers and enterprises alike.
Key Points
- Gemini 3.1 Flash Live offers faster, more natural audio interactions.
- Developers can build reliable voice agents for complex tasks.
- The model scores 90.8% on ComplexFuncBench Audio benchmark.
- Supports real-time conversations in over 200 countries.
- All audio is watermarked to prevent misinformation.
📖 Reader Mode
~6 min readMar 26, 2026
Our latest voice model has improved precision and lower latency to make voice interactions more fluid, natural and precise.
Valeria Wu
Product Manager
Yifan Ding
Software Engineer on behalf of the Gemini team
General summary
Gemini 3.1 Flash Live is Google's highest-quality audio model, designed for natural and reliable real-time dialogue. Developers can access it through the Gemini Live API in Google AI Studio, while enterprises can use it for customer experience. Everyone can experience it via Search Live and Gemini Live, which now supports over 200 countries.
Summaries were generated by Google AI. Generative AI is experimental.
Bullet points
- "Gemini 3.1 Flash Live" is here, making AI audio sound more natural and reliable.
- This new audio model is faster and better at understanding tone for natural conversations.
- Developers can use it to build voice agents that handle complex tasks more reliably.
- Gemini Live and Search Live now offer more helpful responses in many languages.
- All audio from 3.1 Flash Live is watermarked to help prevent the spread of misinformation.
Summaries were generated by Google AI. Generative AI is experimental.
Your browser does not support the audio element.
Listen to article
This content is generated by Google AI. Generative AI is experimental
[[duration]] minutes
Today, we’re advancing Gemini’s real-time dialogue capabilities with Gemini 3.1 Flash Live, our highest-quality audio and voice model yet. It delivers the speed and natural rhythm needed for the next generation of voice-first AI, offering a more intuitive experience for developers, enterprises and everyday users.
3.1 Flash Live is available across Google products:
- For developers in preview via the Gemini Live API in Google AI Studio
- For enterprises in Gemini Enterprise for Customer Experience
- For everyone via Search Live and Gemini Live
For developers: Robust reasoning and task execution
We’ve improved 3.1 Flash Live’s overall quality, making it more reliable for developers and enterprises to build voice-first agents that can complete complex tasks at scale. On ComplexFuncBench Audio, a benchmark that captures multi-step function calling with various constraints, it leads with a score of 90.8% compared to our previous model.
On Scale AI’s Audio MultiChallenge, Gemini 3.1 Flash Live leads with a score of 36.1% with “thinking” on. The benchmark specifically tests complex instruction following and long-horizon reasoning amidst the interruptions and hesitations typical of real-world audio.
3.1 Flash Live also has improved tonal understanding to deliver more natural dialogue. In Gemini Enterprise for Customer Experience, it’s even more effective at recognizing acoustic nuances like pitch and pace than 2.5 Flash Native Audio. It’s also better at dynamically adjusting its response to users' expressions of frustration or confusion.
3.1 Flash Live lets you build voice-ready agents that handle complex tasks in noisy environments.
Illustrative demonstration built with Gemini 3.1 Pro, powered by Gemini 3.1 Flash Live.
3.1 Flash Live lets you use your voice to vibe code and quickly iterate.
Illustrative demonstration built with Gemini 3.1 Pro, powered by Gemini 3.1 Flash Live.
Companies like Verizon, LiveKit and The Home Depot have given positive feedback on 3.1 Flash Live in their workflows, highlighting its improved, natural conversation.
For everyone: More natural and intuitive interactions
In Gemini Live and Search Live, the 3.1 Flash Live model delivers more helpful and natural responses, whether you’re asking quick daily questions or engaging in more complex conversations.
With the 3.1 Flash Live model under the hood, Gemini Live delivers faster responses compared to the previous model and it can follow the thread of your conversation for twice as long, keeping your train of thought intact during longer brainstorms.
3.1 Flash Live makes Gemini Live faster and more helpful
3.1 Flash Live is also inherently multilingual, which enables this week’s global expansion of Search Live. With this launch, people in more than 200 countries and territories can now have real-time, multimodal conversations with Search in their preferred language.
Get real-time troubleshooting help using 3.1 Flash Live in Search Live
Try Gemini 3.1 Flash Live
All audio generated by 3.1 Flash Live is watermarked with SynthID. This imperceptible watermark is interwoven directly into the audio output, allowing the reliable detection of AI-generated content to help prevent misinformation. For more information on our approach to safety and responsibility, see the model card.
Experience the naturalness and reliability of 3.1 Flash Live, starting today. We look forward to seeing how you interact and build with it.
Done. Just one step more.
Check your inbox to confirm your subscription.
You are already subscribed to our newsletter.
You can also subscribe with a
Related stories
.
— Originally published at deepmind.google
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from Google DeepMind
See more →
Introducing Gemma 4 12B: a unified, encoder-free
Google DeepMind has introduced Gemma 4 12B, a unified, encoder-free multimodal model designed to enhance performance across various tasks. This model aims to streamline processes in AI applications by eliminating the need for traditional encoders, potentially improving efficiency and reducing costs for developers and researchers in the field.
