Automatic audio playback of displayed textual content

An audio playback system provides intuitive audio playback of textual content in response to a user input action, such as scrolling portions of the textual content on a display. Playback of audio (e.g., text-to-speech audio) including textual content may begin based on user input positioning a portion of the textual content at a particular location on a device display. As one example, a user may simply scroll in a webpage or other content item to cause a text-to-speech system to perform audio playback of textual content displayed in one or more playback segments of a viewport of a device (e.g., without the user performing an additional tap or gesture to specifically select some portion of the textual content). 一种音频回放系统，响应于用户输入动作(诸如在显示器上滚动文本内容的部分)提供文本内容的直观的音频回放。包括文本内容的音频(例如，文本到语音音频)的回放可以基于用户输入将文本内容的一部分定位于设备显示器上的特定位置而开始。作为一个示例，用户可以简单地在网页或其它内容项中滚动来使得文本到语音系统执行在设备的视口的一个或多个回放段中显示的文本内容的音频回放(例如，而不需要用户执行额外的敲击或手势来具体选择文本内容的某一部分)。