Google正在测试Gemini 2.5 Pro的新实验模式，该模式增加了更深的推理功能和本机音频输出

新模式称为“深思想”，旨在帮助模型在回答提示之前评估多个假设。根据Google的说法，它基于新的研究方法，目前正在使用有限的Gemini API用户进行测试。

Google is introducing deeper reasoning capabilities and native audio output to its Gemini 2.5 Pro model in an experimental mode called "Deep Think."

Google以一种称为“ Deep Think”的实验模式，将更深的推理功能和本机音频输出引入其Gemini 2.5 Pro模型。

This new mode, which is still under testing with a limited group of Gemini API users, encourages the model to consider multiple hypotheses before arriving at an answer.

这种新模式仍在与有限的Gemini API用户一起进行测试，它鼓励该模型在获得答案之前考虑多个假设。

The technology behind Deep Think is based on new research methods at Google AI, and the company claims that Gemini 2.5 Pro with Deep Think outperforms OpenAI's o3 model on several benchmarks.

Deep Though的技术是基于Google AI的新研究方法，该公司声称Gemini 2.5 Pro具有Deep Think Thinks Proforms Openai在多个基准测试上的O3模型。

These include the USAMO 2025 math test, the LiveCodeBench programming benchmark, and MMMU, a test for multimodal reasoning.

其中包括USAMO 2025数学测试，LiveCodeBench编程基准和MMMU，MMMU是多模式推理的测试。

Gemini 2.5 Flash, optimized for speed and efficiency, has also been updated with improved performance on reasoning, multimodal tasks, and code generation.

Gemini 2.5 Flash（用于速度和效率）进行了优化，还通过推理，多模式任务和代码生成的性能提高了。

The latest version of Flash can perform the same tasks using 20 to 30 percent fewer tokens.

最新版本的Flash可以使用少20％的令牌执行相同的任务。

Both Gemini 2.5 Pro and Flash now support native text-to-speech with multiple speaker profiles. The voice output can capture subtle effects like whispers and emotional tone, and supports more than 24 languages.

Gemini 2.5 Pro和Flash现在都支持具有多个扬声器配置文件的本地文本对语。语音输出可以捕获诸如耳语和情感语调之类的微妙效果，并支持24种以上的语言。

Developers can control accent, tone, and speaking style through the Live API.

开发人员可以通过现场API来控制口音，语气和说话风格。

Two new features—"Affective Dialogue" and "Proactive Audio"—aim to make voice interactions feel more natural.

两个新功能 - “情感对话”和“主动音频” - 使声音互动更自然。

Affective Dialogue allows the model to detect emotion in a user's voice and respond accordingly—whether that’s neutrally, empathetically, or in a cheerful tone.

情感对话使该模型可以在用户的​​声音中检测情绪并相应地做出反应 - 无论是中立，善解人意的还是开朗的语气。

Proactive Audio helps filter out background conversations, so the AI only responds when it's directly addressed. The goal is to reduce accidental interactions and make voice control more reliable.

主动的音频有助于滤除背景对话，因此AI仅在直接解决时响应。目的是减少意外互动并使语音控制更加可靠。

Google is also bringing features from Project Mariner into the Gemini API and Vertex AI, allowing the model to control computer applications like a web browser.

Google还将项目Mariner的功能带入Gemini API和Vertex AI，从而使模型可以控制计算机应用程序，例如Web浏览器。

For developers, Gemini now includes "thought summaries", a structured view of the model’s internal reasoning and the actions it takes.

对于开发人员而言，Gemini现在包括“思想摘要”，这是模型内部推理及其采取行动的结构化观点。

To manage performance, developers can configure "thinking budgets" to limit or disable the number of tokens the model uses for reasoning.

为了管理绩效，开发人员可以配置“思考预算”，以限制或禁用模型用于推理的代币数量。

The Gemini API also now supports Anthropic's Model Context Protocol (MCP), which could make it easier to integrate with open-source tools.

Gemini API现在还支持人类的模型上下文协议（MCP），这可以使与开源工具集成变得更容易。

Google is exploring hosted MCP servers to support agent-based application development.

Google正在探索托管的MCP服务器，以支持基于代理的应用程序开发。