Developer voice actions system

1. A computer-implemented method, comprising:

receiving, by a voice action service system, a spoken utterance provided at a computing device of a user, the spoken utterance including a voice command trigger phrase;

processing, by the voice action service system, the spoken utterance to determine an intent associated with the voice command trigger phrase, wherein the intent specifies an activity to be performed via the computing device of the user;

identifying, by the voice action service system, at least a first application and a second application that are each capable of satisfying the intent, wherein identifying at least the first application and the second application is based on determining at least the first application and the second application are associated with the intent in one or more databases;

selecting, by the voice action service system, the first application over the second application,

wherein selecting the first application over the second application is based at least in part on recency of usage of the first application by the user for the activity specified by the intent, the usage being a past usage of the first application by the user for the activity specified by the intent, the past usage being prior to receiving the spoken utterance including the voice command trigger phrase, and

wherein selecting the first application over the second application based at least in part on the recency of usage of the first application by the user comprises determining that the first application was most recently selected, by the user, in response to receiving a prior spoken utterance including the voice command trigger phrase, the prior spoken utterance being received prior to receiving the spoken utterance including the voice command trigger phrase;

providing, to the computing device of the user by the voice action service system and responsive to the spoken utterance, an indication of the selected first application;

receiving, by the voice action service system, an additional spoken utterance at the computing device of the user, the additional spoken utterance including a confirmation of the selected first application; and

in response to receiving the additional spoken utterance, executing the first application to satisfy the intent, wherein executing the first application to satisfy the intent comprises causing the selected first application to perform the activity specified by the intent.

2. The computer-implemented method of claim 1 , wherein selecting the first application over the second application is further based at least in part on a strength of relationship score between the first application and at least one of: the voice command trigger phrase and the intent.

3. The computer-implemented method of claim 1 , wherein selecting the first application over the second application is further based at least in part on the first application being executed on the computing device of the user when the spoken utterance is received.

4. The computer-implemented method of claim 1 , wherein providing the indication of the selected first application comprises providing an audible indication of the selected first application.

5. The computer-implemented method of claim 1 , wherein processing the spoken utterance to determine the intent comprises:

performing, by the voice action service system, speech recognition on the spoken utterance to obtain a transcription of the spoken utterance; and

determining, by the voice action service system, at least a portion of the transcription includes the voice command trigger phrase and that the voice command trigger phrase matches the intent.

6. The method of claim 1 , wherein the activity specified by the intent is a ride booking activity.

7. A system, comprising:

at least one processor; and

at least one memory comprising instructions that when executed, cause the at least one processor to:

receive a spoken utterance provided at a computing device of a user, the spoken utterance including a voice command trigger phrase;

process the spoken utterance to determine the spoken utterance includes the voice command trigger phrase;

identify at least a first application and a second application, wherein identifying at least the first application and the second application is based on determining at least the first application and the second application are mapped to the voice command trigger phrase in one or more databases;

select the first application over the second application,

wherein selecting the first application over the second application is based at least in part on recency of usage of the first application by the user, the usage being a past usage prior to receiving the spoken utterance including the voice command trigger phrase, the past usage being prior to receiving the spoken utterance including the voice command trigger phrase, and

wherein the instructions to select the first application over the second application based at least in part on the recency of usage of the first application by the user comprise instructions to determine that the first application was most recently selected, by the user, in response to receiving a prior spoken utterance including the voice command trigger phrase, the prior spoken utterance being received prior to receiving the spoken utterance including the voice command trigger phrase;

provide, to the computing device of the user and responsive to the spoken utterance, an indication of the selected first application; and

receive an additional spoken utterance at the computing device of the user, the additional spoken utterance including a confirmation of the selected first application; and

in response to receiving the additional spoken utterance, execute the selected first application to satisfy the intent, wherein the instructions to execute the selected first application to satisfy the intent comprise instructions to cause the selected first application to perform the activity specified by the intent.

8. The system of claim 7 , wherein the instructions to select the first application over the second application further comprise instructions to select the first application over the second application based at least in part on a strength of relationship score between the first application and the voice command trigger phrase.

9. The system of claim 7 , wherein the instructions to select the first application over the second application further comprise instructions to select the first application over the second application based at least in part on the first application being executed on the computing device of the user when the spoken utterance is received.

10. The system of claim 7 , wherein the instructions to provide the indication of the selected first application further comprise instructions to provide an audible indication of the selected first application.

11. A non-transitory computer-readable storage medium comprising instructions that, when executed, cause at least one processor to:

receive a spoken utterance provided at a computing device of a user, the spoken utterance including a voice command trigger phrase;

process the spoken utterance to determine an intent associated with the voice command trigger phrase, wherein the intent specifies an activity to be performed via the computing device of the user;

identify at least a first application and a second application that are each capable of satisfying the intent, wherein identifying at least the first application and the second application is based on determining at least the first application and the second application are associated with the intent in one or more databases;

select the first application over the second application,

wherein selecting the first application over the second application is based at least in part on recency of usage of the first application by the user for the activity specified by the intent, the usage being a past usage of the first application by the user for the activity specified by the intent, the past usage being prior to receiving the spoken utterance including the voice command trigger phrase, and

wherein the instructions to select the first application over the second application based at least in part on the recency of usage of the first application by the user further cause the at least one processor to determine that the first application was most recently selected, by the user, in response to receiving a prior spoken utterance including the voice command trigger phrase, the prior spoken utterance being received prior to receiving the spoken utterance including the voice command trigger phrase; and

provide, to the computing device of the user and responsive to the spoken utterance, an indication of the selected first application; and

subsequent to providing the indication of the selected first application, and in response to receiving the spoken utterance, execute the first application to satisfy the intent without requiring any additional user input from the user, wherein the instructions to execute the selected first application to satisfy the intent comprise instructions to cause the selected first application to perform the activity specified by the intent.