Dynamically generated audio in advertisements

A non-transitory computer-readable storage medium comprising computer program instructions executable by a processor, the instructions for:

• receiving, from a client device associated with a user, a request for audio content;
• retrieving message content;
• obtaining user information about the user of the client device;
• generating personalized text according to a template specifying an ordered combination of text components, the personalized text comprising the message content, user information text selected from the obtained user information, and template text;
• identifying audio features of an item of audio content provided to the client device for playback immediately adjacent to the audio message;
• selecting a voice for a text-to-speech algorithm, the selected voice having vocal parameters determined based on the identified audio features of the item of audio content;
• and
• causing an audio message based on an audio version of the personalized text to play on the client device, the audio version generated by the text-to-speech algorithm using the selected voice, the audio message played adjacent to the item of audio content in a stream of audio content provided to the client device responsive to the request for audio content.

A system for generating an audio advertisement using personalized text, the system comprising:

• a processor;
• and
• a non-transitory computer-readable storage medium comprising computer program instructions executable by a processor, the instructions for:
• receiving, from a client device associated with a user, a request for audio content;
• retrieving message content;
• obtaining user information about the user of the client device;
• generating personalized text according to a template specifying an ordered combination of text components, the personalized text comprising the message content, user information text selected from the obtained user information, and template text;
• identifying audio features of an item of audio content provided to the client device for playback immediately adjacent to the audio message;
• selecting a voice for a text-to-speech algorithm, the selected voice having vocal parameters determined based on the identified audio features of the item of audio content;
• and
• causing an audio message based on an audio version of the personalized text to play on the client device, the audio version generated by the text-to-speech algorithm using the selected voice, the audio message played adjacent to the item of audio content in a stream of audio content provided to the client device responsive to the request for audio content.