Gemini 3.1 Flash Live: Making audio AI more natural and reliable
Gemini 3.1 Flash Live: Making audio AI more natural and reliable
Gemini 3.1 Flash Live:让音频 AI 更自然、更可靠
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. 今天,我们通过 Gemini 3.1 Flash Live 提升了 Gemini 的实时对话能力,这是我们迄今为止质量最高的音频和语音模型。它提供了下一代语音优先 AI 所需的速度和自然节奏,为开发者、企业和普通用户带来了更直观的体验。
3.1 Flash Live is available across Google products: 3.1 Flash Live 现已在 Google 各类产品中上线:
- For developers in preview via the Gemini Live API in Google AI Studio
- 开发者可通过 Google AI Studio 中的 Gemini Live API 进行预览
- For enterprises in Gemini Enterprise for Customer Experience
- 企业可通过 Gemini Enterprise for Customer Experience 使用
- For everyone via Search Live and Gemini Live
- 所有用户均可通过 Search Live 和 Gemini Live 使用
For developers: Robust reasoning and task execution
面向开发者:强大的推理与任务执行能力
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. 我们提升了 3.1 Flash Live 的整体质量,使其在构建能够大规模完成复杂任务的语音优先智能体方面,对开发者和企业而言更加可靠。在衡量多步骤函数调用及各种约束条件的基准测试 ComplexFuncBench Audio 中,该模型以 90.8% 的得分领先于我们之前的模型。在 Scale AI 的 Audio MultiChallenge 测试中,开启“思考”模式的 Gemini 3.1 Flash Live 以 36.1% 的得分领先。该基准测试专门考察在现实世界音频中常见的打断和犹豫情况下,模型对复杂指令的遵循能力及长程推理能力。
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 还改进了对语调的理解,从而实现更自然的对话。在 Gemini Enterprise for Customer Experience 中,它在识别音高和语速等声学细微差别方面,比 2.5 Flash Native Audio 更为出色。它还能更好地根据用户表达的沮丧或困惑情绪,动态调整其回复。
For everyone: More natural and intuitive interactions
面向大众:更自然、更直观的交互
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. 在 Gemini Live 和 Search Live 中,无论你是询问日常琐事还是进行复杂的对话,3.1 Flash Live 模型都能提供更有帮助、更自然的回复。得益于 3.1 Flash Live 模型的底层支持,Gemini Live 的响应速度比上一代模型更快,并且能够保持对话连贯性的时间延长了一倍,确保在长时间的头脑风暴中思路不中断。
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. 3.1 Flash Live 本身具备多语言能力,这也促成了本周 Search Live 的全球扩展。随着此次发布,全球 200 多个国家和地区的用户现在可以使用自己偏好的语言,与搜索进行实时的多模态对话。
Try Gemini 3.1 Flash Live
体验 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. 所有由 3.1 Flash Live 生成的音频都带有 SynthID 水印。这种不可察觉的水印直接嵌入在音频输出中,能够可靠地检测 AI 生成的内容,从而帮助防止虚假信息的传播。有关我们安全与责任方法的更多信息,请参阅模型卡。
Experience the naturalness and reliability of 3.1 Flash Live, starting today. We look forward to seeing how you interact and build with it. 从今天开始,体验 3.1 Flash Live 的自然与可靠吧。我们期待看到您如何与它交互并进行创作。