System and method for synthetically generated speech describing media content

A system comprising:

• a processor;
• and
• a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
• receiving a gesture from a user during a presentation of media content, wherein the gesture comprises a metadata request associated with the media content;
• accessing a group of metadata from a source that is different from the source of the media content;
• selecting, according to the metadata request, metadata from the group of metadata;
• and
• outputting synthetically generated speech according to the metadata during an audio gap in the presentation of the media content, the synthetically generated speech having an accent, a language, a lexicon, or a combination thereof selected from a plurality of accents, languages, lexicons or combinations thereof.

A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:

• receiving a gesture from a user during a presentation of media content, wherein the gesture comprises a metadata request associated with the media content;
• selecting, according to the metadata request, metadata from a group of metadata;
• accessing a user profile for the user;
• and
• outputting synthetically generated speech according to the metadata and the user profile during an audio gap in the presentation of the media content, the synthetically generated speech having an accent, a language, a lexicon, or a combination thereof selected from a plurality of accents, languages, lexicons or combinations thereof.