Customized voice action system

1. A system to command a computing device, comprising:

one or more servers comprising one or more processors and memory;

a voice action system executed by the one or more servers to:

receive, via a network from a first provider device, a first voice action that includes a first plurality of triggering phrases and a first action;

receive, via the network from a second provider device, a second voice action that includes a second plurality of triggering phrases and a second action;

select, based on a predetermined criteria, the first voice action from a set comprising the first voice action and the second voice action;

increase, via modification of a voice action language model and responsive to selection of the first voice action based on the predetermined criteria, a likelihood that a voice input matches at least one of the first plurality of triggering phrases relative to at least one of the second plurality of triggering phrases; and

configure the first voice action selected based on the predetermined criteria to perform, via the computing device, the first action of the first voice action responsive to the voice input matching the at least one of the first plurality of triggering phrases of the first voice action.

2. The system of claim 1 , comprising the voice action system to:

receive, from the computing device comprising a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

cause, responsive to receipt of the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to perform the first action.

3. The system of claim 1 , comprising the voice action system to:

cause the computing device to perform the first action comprising a series of actions.

4. The system of claim 1 , comprising the voice action system to:

cause the computing device to perform the first action comprising searching a directory, identifying a match in the directory, initiating a call to a phone number corresponding to the match, or presenting a plurality of options to the computing device.

5. The system of claim 1 , comprising the voice action system to:

receive from a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

cause, responsive to receipt of the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to perform the first action comprising displaying a website in a browser application.

6. The system of claim 1 , comprising the voice action system to:

configure the first voice action to cause the computing device to perform the first action comprising at least two of displaying a website in a browser application, calling a telephone number, displaying a location via a mapping application, downloading a data file, presenting media content, sending an electronic message to a recipient device, performing a search via a search engine, or launching a chat application.

7. The system of claim 1 , comprising the voice action system to:

receive from a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

cause, responsive to receipt of the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to display a location via a mapping application executed by the computing device.

8. The system of claim 1 , comprising the voice action system to:

receive from a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

cause, by the one or more servers responsive to receipt of the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to present media content.

9. The system of claim 1 , comprising the voice action system to:

receive from a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

cause, by the one or more servers responsive to receipt of the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to send an electronic message to a recipient device.

10. The system of claim 1 , comprising the voice action system to:

receive from a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

cause, by the one or more servers responsive to receipt of the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to launch a chat application executed by the computing device.

11. The system of claim 1 , comprising the voice action system to:

receive from a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

cause, responsive to receipt of the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to perform a search via a search engine.

12. The system of claim 1 , comprising the voice action system to:

configure the first voice action for a limited time interval.

13. The system of claim 1 , comprising the voice action system to:

configure the first voice action for the computing device responsive to the computing device located in a limited geographical area.

14. A method of commanding a computing device, comprising:

receiving, by one or more servers via a network from a first provider device, a first voice action that includes a first plurality of triggering phrases and a first action;

receiving, by the one or more servers via the network from a second provider device, a second voice action that includes a second plurality of triggering phrases and a second action;

selecting, by the one or more servers based on a predetermined criteria, the first voice action from a set comprising the first voice action and the second voice action;

increasing, via modification of a voice action language model and responsive to selection of the first voice action based on the predetermined criteria, a likelihood that a voice input matches at least one of the first plurality of triggering phrases relative to at least one of the second plurality of triggering phrases; and

configuring, by the one or more servers, the first voice action selected based on the predetermined criteria, the first voice action configured to perform, via the computing device, the first action of the first voice action responsive to the voice input matching at least one of the first plurality of triggering phrases of the first voice action.

15. The method of claim 14 , comprising:

identifying, via the computing device comprising a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

causing, responsive to identifying the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to perform the first action.

16. The method of claim 14 , comprising:

causing the computing device to perform the first action comprising a series of actions.

17. The method of claim 14 , comprising;

causing the computing device to perform the first action comprising a series of actions comprising at least two of searching a directory, identifying a match in the directory, initiating a call to a phone number corresponding to the match, or presenting a plurality of options to the computing device.

18. The method of claim 14 , comprising:

receiving, via a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

causing, by the one or more servers responsive to receiving the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to perform the first action comprising displaying a website in a browser application.

19. The method of claim 14 , comprising:

receiving, via a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

causing, by the one or more servers responsive to receiving the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to display a location via a mapping application executed by the computing device.

20. The method of claim 14 , comprising:

receiving, via a digital assistant, the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action; and

causing, by the one or more servers responsive to receiving the voice input corresponding to the at least one of the first plurality of triggering phrases of the first voice action, the computing device to perform a search via a search engine.