Device, system and method for summarizing agreements

1. A computer system for automatically generating and playing an audio file of an agreement between two or more parties, the system comprising one or more processors configured to:

capture data via a real time client running on a computer that monitors an interaction between the two or more parties, the captured data relating to the agreement in successive capture operations, each capture operation executed in response to a detected event, wherein the real time client captures data from video display screen elements of one party of the two or more parties facing the application of the computer, one or more webservices of the computer, or any combination thereof and wherein the captured data comprises at least one piece of information that is specific to at least one of the parties;

insert, via the real time client, the captured data into a template, wherein the template comprises text;

use the template with the inserted captured data to prepare a continuous text of the agreement;

transmit, from the real time client operating on the computer, the continuous text of the agreement via an application program interface to a text-to-speech mechanism;

generate, via the text-to-speech mechanism, an audio file from the continuous text;

transmit the audio file from the text-to-speech mechanism, via the application program interface to the real time client operating on the computer;

present a screen pop-up to the display of the computer, wherein the screen pop-up includes an indication to play the audio file;

upon receipt of the indication to play the audio file, play to at least one of the parties the audio file, wherein the audio file represents the agreement as indicated by the template with the inserted captured data; and

receive a keypad confirmation or a verbal confirmation captured from voice recognition software.

2. A system as claimed in claim 1 further comprising one or more data stores providing buffer storage, wherein the one or more processors are further configured to:

buffer the data in multiple store operations, one for each event;

receive a signal indicating that the agreement is complete; and

prepare the continuous text in response to said signal.

3. A system as claimed in claim 1 further comprising a display screen, wherein capturing data relating to the agreement comprises capturing screen data relating to each detected event.

4. A system as claimed in claim 1 wherein the one or more processors are configured to send a request for conversion of the continuous text to a text to speech convertor and wherein the audio file comprises the continuous text converted into speech.

5. A system as claimed in claim 1 wherein the playing of the audio file comprises streaming the file to audio equipment associated with at least one of the parties.

6. A system as claimed in claim 1 wherein the one or more processors are configured to pause and resume the audio file in response to user input by at least one of the parties.

7. A system as claimed in claim 1 further comprising one or more data stores and wherein the one or more processors are further configured to receive a verification indication originating from at least one of the parties and to store the verification indication such that the indication is associated with the agreement.

8. A system as claimed in claim 1 wherein the one or more processors are configured to capture data during an interaction between two or more parties and to store a record of the interaction and wherein the indication is stored as metadata attached to the interaction data.

9. A system as claimed in claim 1 in which the data relating to the agreement comprises any of data defining multiple events, the text, and the audio file.

10. The system of claim 1 wherein the captured data is data captured from one or more databases of the computer, one or more interactive voice response systems of the computer, or any combination thereof.

11. A method for automatically generating and playing an audio file of an agreement between two or more parties, comprising:

capturing data via a real time client running on a computer that monitors an interaction between the two or more parties, the captured data relating to the agreement in successive capture operations, each capture operation executed in response to a detected event, wherein the real time client captures data from video display screen elements of one party of the two or more parties facing the application of the computer, one or more webservices of the computer, or any combination thereof and wherein the captured data comprises at least one piece of information that is specific to at least one of the parties;

inserting, via the real time client, the captured data into a template, wherein the template comprises text;

using the template with the inserted captured data to prepare a continuous text of the agreement;

transmitting, from the real time client operating on the computer, the continuous text of the agreement via an application program interface to a text-to-speech mechanism;

generating, via the text-to-speech mechanism, an audio file from the continuous text;

transmitting the audio file from the text-to-speech mechanism, via the application program interface to the real time client operating on the computer;

presenting a screen pop-up to the display of the computer, wherein the screen pop-up includes an indication to play the audio file;

upon receipt of the indication to play the audio file, playing to at least one of the parties the audio file, wherein the audio file represents the agreement as indicated by the template with the inserted captured data; and

receiving a keypad confirmation or a verbal confirmation captured from voice recognition software.

12. A method as in claim 11 further comprising one or more data stores providing buffer storage, wherein the one or more processors are further configured to:

buffer the data in multiple store operations, one for each event;

receive a signal indicating that the agreement is complete; and

prepare the continuous text in response to said signal.

13. A method as in claim 11 further comprising a display screen, wherein capturing data relating to the agreement comprises capturing screen data relating to each detected event.

14. A method as in claim 11 wherein the one or more processors are configured to send a request for conversion of the continuous text to a text to speech convertor and wherein the audio file comprises the continuous text converted into speech.

15. A method as in claim 11 wherein the playing of the audio file comprises streaming the file to audio equipment associated with at least one of the parties.

16. A method as in claim 11 wherein the one or more processors are configured to pause and resume the audio file in response to user input by at least one of the parties.

17. A method as in claim 11 further comprising one or more data stores and wherein the one or more processors are further configured to receive a verification indication originating from at least one of the parties and to store the verification indication such that the indication is associated with the agreement.

18. A method as in claim 11 wherein the one or more processors are configured to capture data during an interaction between two or more parties and to store a record of the interaction and wherein the indication is stored as metadata attached to the interaction data.

19. A method as in claim 11 in which the data relating to the agreement comprises any of data defining multiple events, the text, and the audio file.

20. A method as in claim 11 wherein the captured data is data captured from one or more databases of the computer, one or more interactive voice response systems of the computer, or any combination thereof.