On demand guided virtual companion

A computer-implemented method for providing a communications session using a guided character wherein the communications session comprises a first device streaming audio and video of a first user to be presented to a second user of a second device and the second device transmitting a phrase to the first device to be played as audio by the first device using a text-to-speech voice of the guided character, the method comprising:

• receiving, from the first device, information indicative of a request of the first user of the first device to start the communications session with the character;
• identifying the second user among possible guiding users by comparing profile information of the first user with profile information of the second user, wherein the profile information of the second user is retrieved from a data store comprising profile information of the possible guiding users;
• sending, to the second device of the second user, information indicative of a request for the second user to guide the character presented by the first device in the communications session;
• receiving, from the second device, an acceptance of the request;
• after the acceptance of the request has been received, starting, by a computer, the communications session between the first device and the second device wherein, during the communications session, the computer (i) streams an audio signal from the first device to the second device in real time, (ii) streams a video signal from the first device to the second device in real time, (iii) receives information corresponding to the phrase to be spoken by the character from the second device, and (iv) causes the first device to present audio of the character speaking the phrase using the text-to-speech voice of the character, and wherein the communications session comprises multiple audio communications of the first user and multiple phrases spoken by the character;
• adding a third device of a third user to the communications session, wherein the third user is a guiding user;
• streaming the audio signal to the third device in real time;
• streaming the video signal to the third device in real time;
• receiving information about a second phrase to be spoken by the character from the third device;
• and
• causing the first device to present audio of the character speaking the second phrase using the text-to-speech voice of the character.

One or more non-transitory computer-readable media comprising computer executable instructions that, when executed, cause at least one processor to perform actions comprising:

• receiving, from a first device, information indicative of a request of a first user of the first device to start a communications session with a character presented by the first device;
• identifying a second user among possible guiding users by comparing profile information of the first user with profile information of the second user, wherein the profile information of the second user is retrieved from a data store comprising profile information of the possible guiding users;
• sending, to a second device of the second user, information indicative of a request for the second user to guide the character presented by the first device in the communications session;
• receiving, from the second device, an acceptance of the request;
• after the acceptance of the request has been received, starting, by a computer, the communications session between the first device and the second device wherein, during the communications session, the computer (i) streams an audio signal from the first device to the second device in real time, (ii) streams a video signal from the first device to the second device in real time, (iii) receives a information about a phrase to be spoken by the character from the second device, and (iv) causes the first device to present audio of the character speaking the phrase using a text-to-speech voice of the character, and wherein the communications session comprises multiple audio communications of the first user and multiple phrases spoken by the character;
• adding a third device of a third user to the communications session, wherein the third user is a guiding user;
• streaming the audio signal to the third device in real time;
• streaming the video signal to the third device in real time;
• and
• disconnecting (i) the second device from the communications session while the third device is still part of the communications session or (ii) the third device from the communications session while the second device is still part of the communications session.