Dynamically generated audio in advertisements

1. A computer-implemented method for providing an audio message using personalized text, the method comprising:

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.

2. The method of claim 1 , wherein generating the personalized text comprises:

retrieving content data describing the item of audio content provided to the client device for playback immediately adjacent to the audio message; and

generating the personalized text according to the template, the personalized text comprising content text describing the item of audio content.

3. The method of claim 2 , wherein generating the personalized text further comprises:

retrieving targeting criteria received from a provider of the message content, the targeting criteria specifying bibliographic information about the item of audio content, the targeting criteria associated with the message content;

determining whether the item of audio content matches the bibliographic information specified by the targeting criteria; and

generating the personalized text comprising the content text and the message content responsive to determining that the item of audio content matches the bibliographic information.

4. The method of claim 1 , wherein generating the personalized text further comprises:

retrieving content data describing the item of audio content provided to the client device for playback immediately adjacent to the audio message;

identifying supplemental content information relevant to the content data; and

generating the personalized text according to the template, the personalized text comprising content text derived from the supplemental content information.

5. The method of claim 4 , wherein identifying supplemental content information relevant to the content data comprises:

obtaining a location of the client device; and

identifying an informational notice relevant to the content data and relevant to a geographic area comprising the location.

6. The method of claim 1 , further comprising:

identifying previous personalized text provided to the client device;

determining whether the previous personalized text include the personalized text; and

selecting the personalized text responsive to determining that the previous personalized text do not include the personalized text.

7. 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.

8. The computer-readable medium of claim 7 , wherein instructions for generating the personalized text comprise instructions for:

retrieving content data describing the item of audio content provided to the client device for playback immediately adjacent to the audio message; and

generating the personalized text according to the template, the personalized text comprising content text describing the item of audio content.

9. The computer-readable medium of claim 8 , wherein the instructions for generating the personalized text further comprise instructions for:

retrieving targeting criteria received from a provider of the message content, the targeting criteria specifying bibliographic information about the item of audio content, the targeting criteria associated with the message content;

determining whether the item of audio content matches the bibliographic information specified by the targeting criteria; and

generating the personalized text comprising the content text and the message content responsive to determining that the item of audio content matches the bibliographic information.

10. The computer-readable medium of claim 7 , wherein instructions for generating the personalized text ad comprise instructions for:

retrieving content data describing the item of audio content provided to the client device for playback immediately adjacent to the audio message;

identifying supplemental content information relevant to the content data; and

generating the personalized text according to the template, the personalized text comprising content text derived from the supplemental content information.

11. The computer-readable medium of claim 10 , wherein instructions for identifying the supplemental content information relevant to the content data comprise instructions for:

obtaining a location of the client device; and

identifying an informational notice relevant to the content data and relevant to a geographic area comprising the location.

12. The computer-readable medium of claim 7 , wherein the instructions further comprise instructions for:

identifying previous personalized text provided to the client device;

determining whether the previous personalized text include the personalized text; and

selecting the personalized text responsive to determining that the previous personalized text do not include the personalized text.

13. 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.

14. The system of claim 13 , wherein instructions for generating the personalized text comprise instructions for:

retrieving content data describing the item of audio content provided to the client device for playback immediately adjacent to the audio message; and

generating the personalized text according to the template, the personalized text comprising content text describing the item of audio content.

15. The system of claim 14 , wherein the instructions for generating the personalized text further comprise instructions for:

retrieving targeting criteria received from a provider of the message content, the targeting criteria specifying bibliographic information about the item of audio content, the targeting criteria associated with the message content;

determining whether the item of audio content matches the bibliographic information specified by the targeting criteria; and

generating the personalized text comprising the content text and the message content responsive to determining that the item of audio content matches the bibliographic information.

16. The system of claim 13 , wherein instructions for generating the personalized text comprise instructions for:

retrieving content data describing the item of audio content provided to the client device for playback immediately adjacent to the audio message;

identifying supplemental content information relevant to the content data; and

generating the personalized text according to the template, the personalized text comprising content text derived from the supplemental content information.

17. The system of claim 16 , wherein instructions for identifying the supplemental content information relevant to the content data comprise instructions for:

obtaining a location of the client device; and

identifying an informational notice relevant to the content data and relevant to a geographic area comprising the location.

18. The method of claim 1 , wherein selecting the voice for the text-to-speech algorithm comprises:

determining audio features describing a vocalist in the identified item of audio content; and

determining the vocal parameters for the selected voice responsive to the audio features describing the vocalist.

19. The method of claim 1 , further comprising:

determining preferences of the user for audio features in the stream of audio content; and

determining the vocal preferences for the selected voice responsive to the preferences of the user for audio features.

20. The method of claim 1 , further comprising:

inferring profile vocal parameters of the user responsive at least in part to user profile data describing demographic information about the user;

inferring content vocal parameters of the user responsive at least in part to content data describing the stream of audio content provided to the client device; and

determining the vocal preferences for the selected voice responsive to a weighted combination of the profile vocal parameters and the content vocal parameters, wherein the weighted combination weighs the content vocal parameters more heavily than the profile vocal parameters.