Systems and methods for a text-to-speech interface

A computing system comprising:

• one or more processors;
• and
• a computer-readable medium having instructions stored thereon that, when executed by the one or more processors, cause performance of operations comprising:
• receiving data descriptive of a gesture input performed by a user, wherein the gesture input comprises a drag and drop gesture that moves a selector to a playback position;
• in response to receiving the data descriptive of the gesture input, generating a text-to-speech request associated with a first document, the request including data associated. with the playback position of the selector associated with a text-to-speech interface overlaid on the first document, wherein the first document is a web page;
• determining first content from the first document based at least in part on the playback position, the first content including content that is displayed in the user interface at the playback position;
• analyzing the first document to identify one or more structural features associated with the first content;
• and
• generating speech data based on the first content and the one or more structural features.

One or more tangible non-transitory computer-readable media storing computer-readable instructions that when executed by one or more processors cause the one or more processors to perform operations, the operations composing:

• receiving data descriptive of a gesture input performed by a user, wherein the gesture input comprises a drag and drop gesture that moves a selector to a playback position;
• in response to receiving the data descriptive of the gesture input, generating a text-to-speech request associated with a first document, the request including data associated. with the playback position of the selector associated with a user text-to-speech interface overlaid on the first document, wherein the first document is a web page;
• determining first content from the first document based at least in part on the playback position, the first content including content that is displayed in the user interface at the playback posh on;
• analyzing the first document to identify one or more structural features associated with the first content;
• and
• generating speech data based on the first content and the one or more structural features.