Conversation assistant

1. A method comprising:

providing, by a processor, a graphical user interface (GUI) on a display of an electronic device, the GUI visually presenting to a user a group of voice bundles that are available for use on the electronic device, each of the voice bundles including instructions executable within an environment provided by an application executed by the processor to perform a call flow that includes a sequence of prompt instructions and grammar instructions executable to result in a simulated multi-step spoken interaction between the electronic device and the user, each of the prompt instructions being executable to ask for information from the user and each of the grammar instructions being executable to interpret information entered through the electronic device by the user, wherein the application is configured to execute, within the environment provided by the application, a plurality of voice bundles that are independent of each other and that are downloaded onto the electronic device, the application being configured to automatically select one of the plurality of voice bundles to execute based on a user voice command by:

receiving the user voice command;

automatically disambiguating and identifying a topic associated with the user voice command; and

automatically selecting the one of the plurality of voice bundles to execute based on the automatically identified topic of the user voice command;

receiving, by the processor, an input from the user indicating a selection of a voice bundle from the group of voice bundles;

in response to the input, identifying, by the processor, a remote server that is configured to store the selected voice bundle;

establishing, by the processor, network communications between the electronic device and the remote server;

locating, by the processor, the selected voice bundle on the remote server; and

downloading, by the processor, a copy of the selected voice bundle from the remote server onto the electronic device,

wherein a voice bundle in the group of voice bundles is directed to enabling the user to perform a particular action through a multi-step spoken interaction between the user and the electronic device,

wherein the particular action is interacting with a social networking site audibly, and

wherein interacting with a social networking site audibly includes at least one of reading a newsfeed, informing the user regarding a number of friend requests that the user has, reading messages to the user, reading friend requests to the user and confirming friends of the user.

2. The method of claim 1 , wherein the GUI visually presenting the group of voice bundles comprises the GUI displaying a group of icons corresponding to voice bundles in the group.

3. The method of claim 2 , wherein receiving an input from the user comprises receiving an indication that the user has selected the icon corresponding to the selected voice bundle from the displayed group of icons.

4. The method of claim 1 , wherein each voice bundle in the group of voice bundles is directed to enabling the user to perform a particular action through a multi-step spoken interaction between the user and the electronic device.

5. The method of claim 1 , wherein the group of voice bundles includes a premium voice bundle that is configured to be used on the electronic device conditioned on receipt of payment of a fee.

6. The method of claim 5 , wherein the fee is displayed along with a graphical representation of the premium voice bundle on the GUI.

7. The method of claim 1 , wherein the group of voice bundles includes a free voice bundle that is configured to be used on the electronic device for free.

8. The method of claim 1 ,

wherein the group of voice bundles includes a private voice bundle that is configured to be accessed on the electronic device by the user conditioned on the user being authorized to receive the private voice bundle, and

wherein the user being authorized to receive the private voice bundle comprises the user entering a valid password or a valid special key through an interface corresponding to the application.

9. The method of claim 1 , further comprising:

based on downloading a copy of the selected voice bundle, executing the selected voice bundle on the electronic device for performing a task in response to information entered by the user.

10. The method of claim 9 , wherein comprises:

upon receiving the information entered by the user through the GUI, performing a call flow that simulates a multi-step interaction between the electronic device and the user and audibly or visually presents a result of executing the selected voice bundle.

11. The method of claim 10 , wherein the selected voice bundle includes media used in the call flow and parameters used to guide the call flow and the media used, the media selected from the group consisting of voice, audio, video, graphics and text.

12. The method of claim 10 , further comprising:

visually presenting, using the GUI, a transcription of the call flow.

13. The method of claim 1 , wherein the selected voice bundle is implemented using State Chart Extensible Markup Language (SCXML).

14. The method of claim 1 , wherein the application is configured to provide an interface between each of the voice bundles and a speech recognition resource, the speech recognition resource configured to recognize speech received from the user via the application.

15. The method of claim 1 , wherein receiving the input from the user indicating the selection of a voice bundle from the group of voice bundles comprises:

receiving, by the processor, an input from the user that is one of a voice input entered through a microphone coupled to the processor or an input through the GUI.

16. The method of claim 1 , wherein the plurality of voice bundles that are independent of each other include a first voice bundle configured to order a first product from a first vendor, and a second voice bundle configured to order a second product from a second vendor that is distinct from the first vendor.

17. A system comprising:

a processor; and

instructions encoded in a non-transitory machine-readable medium for execution by the processor, the instructions, when executed, configured to cause the processor to perform operations comprising:

providing a graphical user interface (GUI) on a display of an electronic device, the GUI visually presenting to a user a group of voice bundles that are available for use on the electronic device, each of the voice bundles including instructions executable within an environment provided by an application executed by the processor to perform a call flow that includes a sequence of prompt instructions and grammar instructions executable to result in a simulated multi-step spoken interaction between the electronic device and the user, each of the prompt instructions being executable to ask for information from the user and each of the grammar instructions being executable to interpret information entered through the electronic device by the user,

wherein the application is configured to execute, within the environment provided by the application, a plurality of voice bundles that are independent of each other and that are downloaded onto the electronic device, each of the voice bundles comprising instructions, the application being configured to automatically select one of the plurality of voice bundles to execute based on a user voice command by:

receiving the user voice command;

automatically disambiguating and identify a topic associated with the user command; and

automatically selecting the one of the plurality of voice bundles to execute based on the instructions of the voice bundles and the automatically identified topic of the user voice command;

receiving an input from the user indicating a selection of a voice bundle from the group of voice bundles;

in response to the input, identifying a remote server that is configured to store the selected voice bundle;

establishing network communications between the electronic device and the remote server;

locating the selected voice bundle on the remote server; and

downloading a copy of the selected voice bundle from the remote server onto the electronic device,

wherein each voice bundle in the group of voice bundles is directed to enabling the user to perform a particular action through a multi-step spoken interaction between the user and the electronic device,

wherein the particular action is one of ordering a product, requesting a service or interacting with a social networking site audibly, and

wherein interacting with a social networking site audibly includes at least one of reading a newsfeed, informing the user regarding a number of friend requests that the user has, reading messages to the user, reading friend requests to the user and confirming friends of the user.

18. The system of claim 17 , wherein the GUI visually presenting the group of voice bundles comprises the GUI displaying a group of icons corresponding to voice bundles in the group.

19. The system of claim 18 , wherein receiving an input from the user comprises receiving an indication that the user has selected the icon corresponding to the selected voice bundle from the displayed group of icons.

20. The system of claim 17 , wherein the group of voice bundles includes a premium voice bundle that is configured to be used on the electronic device conditioned on receipt of payment of a fee.

21. The system of claim 20 , wherein the fee is displayed along with a graphical representation of the premium voice bundle on the GUI.

22. The system of claim 17 , wherein the group of voice bundles includes a free voice bundle that is configured to be used on the electronic device for free.

23. The system of claim 17 , wherein the group of voice bundles includes a private voice bundle that is configured to be accessed on the electronic device upon the user entering a password or a special key through an interface corresponding to the application.

24. The system of claim 17 , including instructions that are configured to cause the processor to perform operations comprising:

based on downloading a copy of the selected voice bundle, executing the selected voice bundle on the electronic device for performing a task in response to information entered by the user.

25. The system of claim 24 , wherein the instructions that are configured to cause the processor to perform operations comprising executing the selected voice bundle includes instructions that are configured to cause the processor to perform operations comprising:

upon receiving the information entered by the user through the GUI, performing a call flow that simulates a multi-step interaction between the electronic device and the user and audibly or visually presents a result of executing the selected voice bundle.

26. The system of claim 25 , wherein the selected voice bundle includes media used in the call flow and parameters used to guide the call flow and the media used, the media selected from the group consisting of voice, audio, video, graphics and text.

27. The system of claim 25 , including instructions that are configured to cause the processor to perform operations comprising:

visually presenting, using the GUI, a transcription of the call flow.

28. The system of claim 17 , wherein the selected voice bundle is implemented using State Chart Extensible Markup Language (SCXML).

29. The system of claim 17 , wherein the application is configured to provide an interface between each of the voice bundles and a speech recognition resource, the speech recognition resource configured to recognize speech received from the user via the application.

30. The system of claim 17 , wherein receiving the input from the user indicating the selection of a voice bundle from the group of voice bundles comprises:

receiving an input from the user that is one of a voice input entered through a microphone coupled to the processor or an input through the GUI.

31. The system of claim 17 , wherein the plurality of voice bundles that are independent of each other include a first voice bundle configured to order a first product from a first vendor, and a second voice bundle configured to order a second product from a second vendor that is distinct from the first vendor.