Gemini 2.5: Enhancements to our smartest models make them even more advanced.

Sure! Here’s the rewritten content with promotional call-to-actions replaced:

<h1>New Gemini 2.5 Capabilities</h1>

<h2>Native Audio Output and Improvements to Live API</h2>
<p>Today, the Live API is introducing a preview version of audio-visual input and a native audio out dialogue, allowing you to build conversational experiences with a more natural and expressive Gemini. Users can also steer the model's tone, accent, and speaking style. For example, you can instruct the model to adopt a dramatic voice when telling a story. Additionally, it supports tool use to search on your behalf.</p>

<p>You can experiment with a set of early features, including:</p>
<ul>
    <li><strong>Affective Dialogue</strong>, where the model detects emotion in the user's voice and responds appropriately.</li>
    <li><strong>Proactive Audio</strong>, allowing the model to disregard background conversations and determine when to respond.</li>
    <li><strong>Thinking in the Live API</strong>, utilizing Gemini’s cognitive capabilities to support more complex tasks.</li>
</ul>

<p>We’re also releasing new previews for text-to-speech in 2.5 Pro and 2.5 Flash. These features offer first-of-its-kind support for multiple speakers, enabling text-to-speech with two voices via native audio out. Similar to Native Audio dialogue, text-to-speech is expressive and can capture subtle nuances, such as whispers. It works in over 24 languages and can seamlessly switch between them.</p>