Open architecture for a voice user interface

1. A system for processing voice requests from a user for accessing information on a computerized network and delivering information from a script server and an audio server, the system comprising:

a voice user interface subsystem including:

a dialog engine, wherein the dialog engine is operable to interpret requests from users from the user input, communicate the requests to the script server and the audio server, and receive information from the script server and the audio server;

a media communications server, wherein the media communications server is operable to receive user input via a communication system, and to transfer at least a portion of the user input to the dialog engine; and

a broker coupled between the dialog engine and the media communications server, wherein the broker is operable to establish a session between the media communications server and the dialog engine.

2. The system, as set forth in claim 1 , wherein the broker is further operable to distribute a processing load across two or more of the dialog engines.

3. The system, as set forth in claim 1 , wherein the dialog engine handles a plurality of sessions with the media communications server.

4. The system, as set forth in claim 1 , wherein the information from the script server is transmitted in markup language scripts.

5. The system, as set forth in claim 1 , wherein the information from the audio distribution server is transmitted in audio file format.

6. The system, as set forth in claim 1 , wherein the media communications server includes a text to speech service provider.

7. The system, as set forth in claim 1 , wherein the media communications server includes a communications service provider.

8. The system, as set forth in claim 7 , further comprising a communications channel coupled between the communications service provider and the dialog engine.

9. The system, as set forth in claim 1 , wherein the media communications server includes a media service provider.

10. The system, as set forth in claim 9 , further comprising a play media channel coupled between the media service provider and the dialog engine.

11. The system, as set forth in claim 9 , further comprising a record media channel coupled between the media service provider and the dialog engine.

12. The system, as set forth in claim 6 , further comprising a text to speech channel coupled between the text to speech service provider and the dialog engine.

13. The system, as set forth in claim 1 , wherein the media communications server includes a speech recognition service provider.

14. The system, as set forth in claim 13 , further comprising a speech channel coupled between the speech recognition service provider and the dialog engine.

15. The system, as set forth in claim 13 , wherein the speech recognition service provider includes a grammar list, and the speech recognition service provider identifies key words in the user input according to the grammar list.

16. The system, as set forth in claim 15 , wherein the speech recognition service provider is operable to transmit recognized commands to the dialog engine, and the dialog engine is operable to control output of the scripts to the user based on the user's input.

17. A computer program product for recognizing commands from user speech input, for accessing information from a network, and for presenting the information in audio format, the product comprising:

dialog engine instructions operable to interpret commands from the user input, request the information from a server in the network, and receive the information from the server;

media communications services instructions operable to receive user input via a communication system, and to recognize the commands from the user input, and transfer the commands to the dialog engine; and

broker instructions operable to establish a session between the media communications server and the dialog engine.

18. The program product, as set forth in claim 17 , wherein the dialog engine instructions handle a plurality of sessions with one or more sets of the media communications instructions.

19. The program product, as set forth in claim 18 , wherein the broker instructions are further operable to distribute the sessions across two or more sets of the dialog engine instructions.

20. The program product, as set forth in claim 17 , wherein the dialog engine instructions are operable to request information from the server formatted in markup language documents.

21. The program product, as set forth in claim 17 , wherein the media communications instructions are operable to convert the information from text format to speech format.

22. The program product, as set forth in claim 17 , wherein the media communications instructions are operable to interface with a communication system.

23. The program product, as set forth in claim 17 , wherein the media communications instructions include media service provider instructions.

24. The program product, as set forth in claim 17 , wherein the media communications instructions include a grammar list of the commands that can be recognized from the user input.

25. The program product, as set forth in claim 24 , wherein the media communications instructions are operable to transmit recognized commands to the dialog engine, and the dialog engine instructions are operable to control output of the scripts to the user based on the user's input.