Device with intelligent voice system for temporary management of content

1 . A smart speaker including an intelligent voice system, comprising:

a processor;

a non-transitory computer readable medium storing instructions that are executable by the processor to:

receive an audible request from a user to set up a temporary session between the smart speaker and a user device for accessing content from a digital service running on a remote system;

process, by the intelligent voice system, the audible request;

establish communication with the user device, wherein the user device stores account credentials for accessing the digital service;

create the temporary session with the user device for accessing content from the digital service;

automatically send a request, to the user device, for content information provided by the digital service, wherein the content information comprises data retrieved by the user device from the digital service running on the remote system using the account credentials stored on the user device;

receive, from the user device, requested content information provided by the digital service;

store the requested content information in memory of the smart speaker;

receive, from the user, a second audible request for at least some of the content information;

process, by the intelligent voice system, the second audible request; and

audibly provide, by the intelligent voice system, at least some of the requested content information stored in the memory of the smart speaker in response to the second audible request without sending the second audible request to the user device.

2 . The smart speaker according to claim 1 , wherein the instructions are further executable by the processor to establish a vocal identity and to confirm the vocal identity of the user before processing the second audible request.

3 . The smart speaker according to claim 1 , wherein the instructions are further executable to detect a trigger and delete the requested content information from the memory upon detecting the trigger.

4 . The smart speaker according to claim 3 , wherein the trigger includes detecting a third audible request for content from someone other than the user.

5 . The smart speaker according to claim 1 , wherein the instructions are further executable to set a content removal timer and remove the requested content information from local memory when the content removal timer expires.

6 . The smart speaker according to claim 1 , wherein the digital service is an online streaming service that is accessible using the account credentials stored on the user device.

7 . The smart speaker according to claim 6 , wherein the requested content information includes digital music information that is stored in the memory of the smart speaker.

8 . The smart speaker according to claim 1 , wherein the digital service is an online banking service that is accessible using the account credentials stored on the user device.

9 . The smart speaker according to claim 8 , wherein the requested content information includes bank account information for the user that is stored in the memory of the smart speaker.

10 . A computer-implemented method, comprising:

receiving an audible request from a user to set up a temporary session between a smart speaker and a user device for accessing content from a digital service running on a remote system;

processing, by an intelligent voice system, the audible request;

establishing communication with the user device, wherein the user device stores account credentials for accessing the digital service;

creating the temporary session with the user device for accessing content from the digital service;

automatically sending a request, to the user device, for content information provided by the digital service, wherein the content information comprises data retrieved by the user device from the digital service running on the remote system using the account credentials stored on the user device;

receiving, from the user device, requested content information provided by the digital service;

storing the requested content information in memory of the smart speaker;

receiving, from the user, a second audible request for at least some of the content information;

processing, by the intelligent voice system, the second audible request; and

audibly providing, by the intelligent voice system, at least some of the requested content information stored in the memory of the smart speaker in response to the second audible request without sending the second audible request to the user device.

11 . The computer-implemented method according to claim 10 , wherein the method further includes establishing a vocal identity and confirming the vocal identity of the user before processing the second audible request.

12 . The computer-implemented method according to claim 10 , wherein the method further includes detecting a trigger and deleting the requested content information from the memory upon detecting the trigger.

13 . The computer-implemented method according to claim 12 , wherein detecting the trigger includes detecting a third audible request for content from someone other than the user.

14 . The computer-implemented method according to claim 10 , wherein the digital service is an online streaming service that is accessible using the account credentials stored on the user device.

15 . The computer-implemented method according to claim 10 , wherein the requested content information includes digital music information that is stored in the memory of the smart speaker.

16 . The computer-implemented method according to claim 10 , wherein the digital service is an online banking service that is accessible using the account credentials stored on the user device.

17 . The computer-implemented method according to claim 10 , wherein the requested content information includes bank account information for the user that is stored in the memory of the smart speaker.

18 . The computer-implemented method according to claim 10 , wherein the method further includes setting a content removal timer and removing the requested content information from local memory when the content removal timer expires.

19 . A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to:

receive an audible request from a user to set up a temporary session between a smart speaker and a user device for accessing content from a digital service running on a remote system;

process, by an intelligent voice system, the audible request;

establish communication with the user device, wherein the user device stores account credentials for accessing the digital service;

create the temporary session with the user device for accessing content from the digital service;

automatically send a request, to the user device, for content information provided by the digital service, wherein the content information comprises data retrieved by the user device from the digital service running on the remote system using the account credentials stored on the user device;

receive, from the user device, requested content information provided by the digital service;

store the requested content information in memory of a smart speaker;

receive, from the user, a second audible request for at least some of the content information;

process, by the intelligent voice system, the second audible request; and

audibly provide, by the intelligent voice system, at least some of the requested content information stored in the memory of the smart speaker in response to the second audible request without sending the second audible request to the user device.

20 . The non-transitory computer-readable medium according to claim 19 , wherein the instructions are further executable to cause the one or more computers to establish a vocal identity and to confirm the vocal identity of the user before processing the second audible request.