Method for sending multi-media messages with customized audio

1. A method of delivering a multi-media message to a recipient, the multi-media message being created by a sender for delivery by an animated entity, the method comprising:

recording an audio message from the sender;

after recording the audio message from the sender, converting the audio message to a text message and presenting the text message to the sender;

inserting at least one emoticon into the text message;

receiving a choice of one of a plurality of animated entities to deliver the message;

conforming the audio message to movements associated with the animated entity to create a multi-media message; and

delivering the multi-media message to the recipient with the animated entity speaking the recorded audio message from the sender, wherein:

when the animated entity delivers the multi-media message corresponding to the text message, the animated entity exhibits actions associated with a respective one of the at least one emoticon beginning at a point corresponding to a first predetermined amount of time before the respective one of the at least one emoticon and ending at a second point corresponding to a second predetermined amount of time after the respective one of the at least one emoticon, and

the first predetermined amount of time and the second predetermined amount of time are defined based, at least partly, on words surrounding the respective one of the at least one emoticon.

2. The method of delivering a multi-media message to a recipient of claim 1 , wherein the multi-media message is sent as an e-mail to the recipient.

3. The method of delivering a multi-media message to a recipient of claim 1 , wherein the multi-media message is sent as an instant message to the recipient.

4. The method of delivering a multi-media message to a recipient of claim 1 , wherein the multi-media message is sent over the Internet to the recipient.

5. The method of delivering a multi-media message to a recipient of claim 1 , wherein the multi-media message is sent to the recipient via a wireless network.

6. The method of claim 1 , wherein the first predetermined amount of time and the second predetermined amount of time are further defined based, at least partly, on the respective one of the at least one emoticon.

7. A method of sending a multi-media message from a sender to a recipient using an animated entity, the sender choosing the animated entity from a plurality of animated entities, the method comprising:

recording a sender audio message;

associating the sender audio message with the animated entity to create the multi-media message;

using an automatic speech recognition system to convert the audio message to a text message;

presenting the text message to the sender in textual form;

permitting the sender to insert at least one emoticon into the text message;

using the text message to coordinate mouth movements for the animated entity; and

processing the multi-media message for the recipient such that the animated entity speaks the sender audio message, wherein:

when the animated entity speaks the sender audio message corresponding to the text message, the animated entity exhibits actions associated with a respective one of the at least one emoticon beginning at a point corresponding to a first predetermined amount of time before the respective one of the at least one emoticon and ending at a second point corresponding to a second predetermined amount of time after the respective one of the at least one emoticon, and

the first predetermined amount of time and the second predetermined amount of time are defined based, at least partly, on words surrounding the respective one of the at least one emoticon.

8. The method of sending a multi-media message of claim 7 , wherein the multi-media message is sent over the Internet.

9. The method of sending a multi-media message of claim 7 , wherein the multi-media message is sent in an instant message.

10. The method of sending a multimedia message of claim 7 , wherein the multi-media message is sent over a wireless network.

11. The method of claim 7 , wherein the first predetermined amount of time and the second predetermined amount of time are further defined based, at least partly, on the respective one of the at least one emoticon.

12. A method of providing a synthesized voice with sender voice characteristics, the method comprising:

receiving an audio recording, associated with a message, from a sender;

after receiving the audio recording, using an automatic speech recognizer and presenting a text message corresponding to the audio recording to the sender;

permitting the sender to insert at least one emoticon into the text message;

parameterizing the audio recording into audio parameters; and

using the audio parameters, synthesizing a voice that is not the sender's voice but includes at least one sender voice characteristic for delivery of the message with an animated entity speaking the message corresponding to the text message, with the synthesized voice, wherein:

when the animated entity speaks the message the animated entity exhibits actions associated with a respective one of the at least one emoticon beginning at a point corresponding to a first predetermined amount of time before the respective one of the at least one emoticon and ending at a second point corresponding to a second predetermined amount of time after the respective one of the at least one emoticon, and

the first predetermined amount of time and the second predetermined amount of time are defined based, at least partly on words surrounding the respective one of the at least one emoticon.

13. The method of providing a synthesized voice with sender voice characteristics of claim 12 , wherein the at least one sender voice characteristic is one of an accent, voice inflection, pitch, rhythm, or dialect.

14. The method of providing a synthesized voice with sender voice characteristics of claim 12 , wherein parameterizing the audio recording into audio parameters further comprises using an alignment program for segmenting the audio recording into phonemes and labeling the audio recording with the phonemes, duration, pitch, stress and other parameters.

15. The method of claim 12 , wherein the first predetermined amount of time and the second predetermined amount of time are further defined based, at least partly, on the respective one of the at least one emoticon.