Methods, systems, and media for presenting interactive audio content

摘要

Methods, systems, and media for presenting interactive audio content are provided. In some embodiments, the method includes: receiving narrative content that includes action points, wherein each of the action points provides user actions and a narrative portion corresponding to each of the user actions; determining a user engagement density associated with the narrative content, wherein the user engagement density modifies the number of the action points to provide within the narrative content; causing the narrative content to be presented to a user based on the user engagement density; determining that a speech input has been received at one of the action points in the narrative content; converting the speech input to a text input; determining whether the user action associated with the text input corresponds to one of the user actions; selecting the narrative portion corresponding to the text input in response to determining that the user action corresponds to one of the user actions; converting the selected narrative portion to an audio output; and causing the narrative content with the converted audio output of the selected narrative portion to be presented to the user.

主权项

1. A method for presenting interactive audio content, the method comprising:
receiving, using a computing device that includes a hardware processor, an audio input device, and an audio output device, an interactive audiobook having narrative content that includes a plurality of action points, wherein each of the plurality of action points provides a plurality of user actions and a narrative portion corresponding to each of the plurality of user actions; receiving, using the hardware processor of the computing device, a selection of a user engagement density from a user, wherein the selection determines a number of the plurality of action points in the narrative content of the interactive audiobook, and wherein a higher-selected user engagement density increases the number of the plurality of action points and a lower-selected user engagement density decreases the number of action points in the narrative content; causing, using the hardware processor of the computing device, the narrative content with the determined number of the plurality of action points to be presented via the audio output device to the user based on the selected user engagement density; determining, using the hardware processor of the computing device, that a speech input has been received by the audio input device at one of the plurality of action points during the playback of the narrative content of the interactive audiobook; converting, using the hardware processor of the computing device, the speech input to a text input; determining, using the hardware processor of the computing device, whether the user action associated with the text input corresponds to one of the plurality of user actions; selecting, using the hardware processor of the computing device, the narrative portion corresponding to the text input in response to determining that the user action corresponds to one of the plurality of user actions; converting, using the hardware processor of the computing device, the selected narrative portion to an audio output; modifying, using the hardware processor of the computing device, the narrative content of the interactive audiobook with the converted audio output of the selected narrative portion; and causing, using the hardware processor of the computing device, the narrative content with the converted audio output of the selected narrative portion to be presented to the user via the audio output device.