Delivering tailored audio segments within live audio streams
An online system tailors audio segments for users accessing a live audio stream such that the audio segments can be presented to users during a break of the live audio stream. The audio segment can include interactive content as well as one or both of an audio clip and a standard message, each of which serves as a type of introduction to the interactive content. For each user, the online system analyzes characteristics of the user to determine whether to include the standard message in addition to the audio clip, or to withhold the standard message from the audio segment. Therefore, different users accessing the live audio stream can be appropriately introduced to the interactive content which can improve the likelihood that the users interact with the interactive content.
1. A method comprising:
determining that a type of a selected content selected to be presented at a break point within an audio stream to a user is an interactive type, the interactive type being determined based on audio within the selected content that is requesting one or more user actions to be taken with respect to a client device other than input supplied using a graphical user interface of the client device;
responsive to determining that the type is the interactive type, determining an interaction score for the user, the interaction score being based on prior interactivity of the user with content of the interactive type that was previously presented to the user;
assembling an audio segment, the audio segment including an additional message based on the interaction score being less than a threshold interaction value, and the audio segment excluding the additional message based on the interaction score being equal to or greater than the threshold interaction value; and
providing the assembled audio segment to be presented at the break point within the audio stream.
2. The method of claim 1 , wherein the assembled audio segment further comprises an audio clip in addition to the additional message.
3. The method of claim 2 , wherein the audio clip in the assembled audio segment is shorter in duration in comparison to the additional message in the assembled audio segment.
4. The method of claim 2 , wherein the additional message precedes the audio clip, and wherein the audio clip further precedes the selected content.
5. The method of claim 2 , wherein the type of the selected content is an interactive content, and wherein the additional message identifies an interaction in association with the interactive content.
6. The method of claim 1 , wherein determining whether to include the additional message with the selected content for the user comprises:
determining whether characteristics of the user satisfy user interaction criteria; and
responsive to determining that the characteristics of the user do not satisfy the user interaction criteria, including the additional message in the assembled audio segment.
7. The method of claim 1 , wherein determining the interaction score for the user further comprises:
accessing user characteristics of the user, the user characteristics comprising characteristics associated with prior voice recordings provided by the user; and
applying a machine learning model to the user characteristics of the user.
8. The method of claim 1 , further comprising:
receiving a device identifier of a device used by the user; and
determining the interaction type based on the device identifier of the device used by the user.
9. A non-transitory computer-readable medium comprising memory with instructions encoded thereon, the instructions, when executed, causing one or more processors to perform operations, the instructions comprising commands to:
determine that a type of a selected content selected to be presented at a break point within an audio stream to a user is an interactive type, the interactive type being determined based on audio within the selected content that is requesting one or more user actions to be taken with respect to a client device other than input supplied using a graphical user interface of the client device;
responsive to determining that the type is the interactive type, determine an interaction score for the user, the interaction score being based on prior interactivity of the user with content of the interactive type that was previously presented to the user;
assemble an audio segment, the audio segment including an additional message based on the interaction score being less than a threshold interaction value, and the audio segment excluding the additional message based on the interaction score being equal to or greater than the threshold interaction value; and
provide the assembled audio segment to be presented at the break point within the audio stream.
10. The non-transitory computer-readable medium of claim 9 , wherein the assembled audio segment further comprises an audio clip in addition to the additional message.
11. The non-transitory computer-readable medium of claim 10 , wherein the audio clip in the assembled audio segment is shorter in duration in comparison to the additional message in the assembled audio segment.
12. The non-transitory computer-readable medium of claim 10 , wherein the additional message precedes the audio clip, and wherein the audio clip further precedes the selected content.
13. The non-transitory computer-readable medium of claim 10 , wherein the type of the selected content is an interactive content, and wherein the additional message identifies an interaction in association with the interactive content.
14. The non-transitory computer-readable medium of claim 9 , wherein the commands to determine whether to include the additional message with the selected content for the user comprise further commands to:
determine whether characteristics of the user satisfy user interaction criteria; and
responsive to determining that the characteristics of the user do not satisfy the user interaction criteria, include the additional message in the assembled audio segment.
15. The non-transitory computer-readable medium of claim 9 , wherein the commands to determine the interaction score for the user further comprise further commands to:
access user characteristics of the user, the user characteristics comprising characteristics associated with prior voice recordings provided by the user; and
apply a machine learning model to the user characteristics of the user.
16. The non-transitory computer-readable medium of claim 9 , wherein the instructions further comprise further commands to:
receive a device identifier of a device used by the user; and
determine the interaction type based on the device identifier of the device used by the user.
17. A system comprising:
memory with instructions encoded thereon; and
one or more processors that, when executing the instructions, are caused to perform operations comprising:
determining that a type of a selected content selected to be presented at a break point within an audio stream to a user is an interactive type, the interactive type being determined based on audio within the selected content that is requesting one or more user actions to be taken with respect to a client device other than input supplied using a graphical user interface of the client device;
responsive to determining that the type is the interactive type, determining an interaction score for the user, the interaction score being based on prior interactivity of the user with content of the interactive type that was previously presented to the user;
assembling an audio segment, the audio segment including an additional message based on the interaction score being less than a threshold interaction value, and the audio segment excluding the additional message based on the interaction score being equal to or greater than the threshold interaction value; and
providing the assembled audio segment to be presented at the break point within the audio stream.
18. The system of claim 17 , wherein the assembled audio segment further comprises an audio clip in addition to the additional message.
19. The system of claim 18 , wherein the audio clip in the assembled audio segment is shorter in duration in comparison to the additional message in the assembled audio segment.
20. The system of claim 18 , wherein the additional message precedes the audio clip, and wherein the audio clip further precedes the selected content.