Real time popularity based audible content acquisition
A personalized news service provides personalized news programs for its users by generating personalized combinations of audible versions of news stories derived from text-based based versions of the news stories. The audible versions may be generated from the text-based version by a text-to-speech system, or may by recording a person reading aloud the text-based version. To acquire recordings, the personalized news service can make a determination that a particular news story has a threshold extent of popularity. The news service can then transmit a request to a remote recording station for a recording of a verbal reading of the particular news story. The news service can then receive the requested recording from the remote recording station.
1. A method comprising:
analyzing, by a computing device, generated playlists for a plurality of client devices, wherein the generated playlists contain ordered references to text-to-speech-generated audio files of media content items respectively customized for the client devices;
determining, by the computing device, that a media content item has a threshold level of popularity based on a number of references to a text-to-speech-generated audio file of the media content item that are included in the generated playlists;
responsive to determining that the media content item has the threshold level of popularity, transmitting, by the computing device and to a remote recording station, a request for a human verbal reading of the media content item;
receiving, by the computing device and from the remote recording station, an audio file of the human verbal reading;
updating, by the computing device, the references to the text-to-speech-generated audio file of the media content item to refer to the audio file of the human verbal reading; and
transmitting, by the computing device, a playlist to a client device of the plurality of client devices, wherein the playlist includes a plurality of ordered references to audio files of media content items, including the audio file of the human verbal reading.
2. The method of claim 1 , wherein the client device is configured to (i) traverse the playlist, (ii) based on the references, retrieve the audio files, including the audio file of the human verbal reading, and (iii) play out the audio files, including the audio file of the human verbal reading.
3. The method of claim 1 , wherein the media content item comprises a news story, and wherein the remote recording station comprises a remote news studio.
4. The method of claim 1 , further comprising:
determining that the audio file of the media content item was automatically generated by a text-to-speech (TTS) system, wherein transmitting, to the remote recording station, the request for the human verbal reading is also based on the audio file of the media content item having been automatically generated by the TTS system.
5. The method of claim 1 , further comprising:
associating the audio file of the human verbal reading with the text-to-speech-generated audio file of the media content item.
6. The method of claim 1 , further comprising:
receiving, from the client device, a request to retrieve the audio file of the human verbal reading; and
transmitting, to the client device, the audio file of the human verbal reading.
7. The method of claim 1 , wherein the client device begins playing out the audio file of the human verbal reading before the retrieval thereof completes.
8. The method of claim 1 , wherein the remote recording station is selected from a plurality of remote recording stations based on a correspondence between a feature of the remote recording station and an attribute associated with the media content item.
9. The method of claim 1 , further comprising:
selecting the remote recording station from a plurality of remote recording stations based on a correspondence between a geographic location of the remote recording station and an attribute associated with the media content item.
10. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause performance of operations comprising:
analyzing generated playlists for a plurality of client devices, wherein the generated playlists contain ordered references to text-to-speech-generated audio files of media content items respectively customized for the client devices;
determining that a media content item has a threshold level of popularity based on a number of references to a text-to-speech-generated audio file of the media content item that are included in the generated playlists;
responsive to determining that the media content item has the threshold level of popularity, transmitting, to a remote recording station, a request for a human verbal reading of the media content item;
receiving, from the remote recording station, an audio file of the human verbal reading;
updating the references to the text-to-speech-generated audio file of the media content item to refer to the audio file of the human verbal reading; and
transmitting a playlist to a client device of the plurality of client devices, wherein the playlist includes a plurality of ordered references to audio files of media content items, including the audio file of the human verbal reading.
11. The non-transitory computer-readable medium of claim 10 , wherein the client device is configured to (i) traverse the playlist, (ii) based on the references, retrieve the audio files, including the audio file of the human verbal reading, and (iii) play out the audio files, including the audio file of the human verbal reading.
12. The non-transitory computer-readable medium of claim 10 , wherein the media content item comprises a news story, and wherein the remote recording station comprises a remote news studio.
13. The non-transitory computer-readable medium of claim 10 , wherein the operations further comprise:
determining that the audio file of the media content item was automatically generated by a text-to-speech (TTS) system, wherein transmitting, to the remote recording station, the request for the human verbal reading is also based on the audio file of the media content item having been automatically generated by the TTS system.
14. The non-transitory computer-readable medium of claim 10 , wherein the operations further comprise:
associating the audio file of the human verbal reading with the text-to-speech-generated audio file of the media content item.
15. The non-transitory computer-readable medium of claim 10 , wherein the operations further comprise:
receiving, from the client device, a request to retrieve the audio file of the human verbal reading; and
transmitting, to the client device, the audio file of the human verbal reading.
16. The non-transitory computer-readable medium of claim 10 , wherein the client device begins playing out the audio file of the human verbal reading before the retrieval thereof completes.
17. The non-transitory computer-readable medium of claim 10 , wherein the remote recording station is selected from a plurality of remote recording stations based on a correspondence between a feature of the remote recording station and an attribute associated with the media content item.
18. A computing system comprising:
a processor;
a memory; and
program instructions, stored in the memory, that when executed by the processor, cause the computing system to perform operations comprising:
analyzing generated playlists for a plurality of client devices, wherein the generated playlists contain ordered references to text-to-speech-generated audio files of media content items respectively customized for the client devices;
determining that a media content item has a threshold level of popularity based on a number of references to a text-to-speech-generated audio file of the media content item that are included in the generated playlists;
responsive to determining that the media content item has the threshold level of popularity, transmitting, to a remote recording station, a request for a human verbal reading of the media content item;
receiving, from the remote recording station, an audio file of the human verbal reading;
updating the references to the text-to-speech-generated audio file of the media content item to refer to the audio file of the human verbal reading; and
transmitting a playlist to a client device of the plurality of client devices, wherein the playlist includes a plurality of ordered references to audio files of media content items, including the audio file of the human verbal reading.
19. The computing system of claim 18 , wherein the client device is configured to (i) traverse the playlist, (ii) based on the references, retrieve the audio files, including the audio file of the human verbal reading, and (iii) play out the audio files, including the audio file of the human verbal reading.
20. The computing system of claim 18 , wherein the media content item comprises a news story, and wherein the remote recording station comprises a remote news studio.