The disclosure discloses a command based interactive system (100) and a method thereof. The system (100) includes an electronic device (102) and an AI engine (108). The electronic device (102) includes a detection module (206), a switching module (208), and a recording module (210). The detection module (206) detects a call and a user input, first context data of the call, and/or pre-setting information. The switching module (208) enables the electronic device (102) to receive a command from the user. The recording module (210) records the command. The AI engine (108) includes an analyser (222), and a communication module (226). The analyzer (222) analyzes the command, and generates conversational threads based on the analysed command. The communication module (226) transmits the conversational threads to the caller.

A User Equipment (UE) for handling voice or video calls, such as for example a smartphone, PC, laptop, tablet, etc, has a voicemail client integrated in its OS, or in the form of an app, configured to receive an incoming call message causing an alert about the incoming call for at most a pre-set no-answer period of time, after which, if the call is not answered, the call being set to be completed from the calling party towards a network-based voicemail center, and before the expiry of the pre-set no-answer period of time, to answer the incoming call, causing the call to be established between the calling party and the UE's voicemail client, wherein the call is not completed towards the network-based voicemail center. The voicemail client is further configured to play a greeting message for the calling party over the call with the calling party, record a voice message from the calling party, and alert the user of the UE about the voicemail message, using the UE's voicemail client. Voicemail messages are thus saved and accessed locally on the UE avoiding the signaling to a network-based voicemail client.

The present disclosure describes receiving a trigger operation indication that content has been selected by a user device, and determining whether the content offers a recurring audio content data. The operation may also include retrieving a first audio content and transmitting the first audio content to the user device.

A system and method for provisioning communications services. A remote device controlled by a user is linked with a provisioning system. A verbal selection of a menu associated with a library is received for performing one or more actions within the provisioning system. One or more verbal commands associated with the menu are received. A determination is made of an action within the library associated with the one or more verbal commands. The action associated with the one or more verbal commands is performed in the provisioning system to provision the communications services.

The present disclosure describes receiving a trigger operation indication that content has been selected by a user device, and determining whether the content offers a recurring audio content data. The operation may also include retrieving a first audio content and transmitting the first audio content to the user device.

A method includes performing operations as follows on a processor: establishing communication with a second mobile device using a direct point-to-point wireless protocol, obtaining an audio avatar associated with a user of the second mobile device responsive to establishing communication with the second mobile device, and playing the audio avatar on a speaker system associated with the first mobile device.

The present disclosure describes a system, method, and computer-readable medium for providing audio announcement of communications to a called party in a communication network. The method includes receiving communication from a calling party and performing a lookup of information relating to the calling party in a database via an Internet Protocol connection based on an identifier of at least one of the calling party and the called party. The information comprises one or more audio files. The method then provides the audio announcement to a called party based on the audio files.

Methods, systems, and computer-readable media for voice-activated selective memory for voice-capturing devices are disclosed. A first voice input from a voice-capturing device is received, via a network, at a service provider environment comprising one or more services. The first voice input comprises one or more utterances from a user of the voice-capturing device. A representation of the first voice input is stored. A second voice input from the voice-capturing device is received, via the network, at the service provider environment. The second voice input represents a command to disregard the first voice input. Based on the second voice input, the representation of the first voice input is deleted.

The present disclosure describes a system, method, and computer-readable medium for providing audio announcement of communications to a called party in a communication network. The method includes receiving communication from a calling party and performing a lookup of information relating to the calling party in a database via an Internet Protocol connection based on an identifier of at least one of the calling party and the called party. The information comprises one or more audio files. The method then provides the audio announcement to a called party based on the audio files.

Methods, systems, and computer-readable media for voice-activated selective memory for voice-capturing devices are disclosed. A first voice input from a voice-capturing device is received, via a network, at a service provider environment comprising one or more services. The first voice input comprises one or more utterances from a user of the voice-capturing device. A representation of the first voice input is stored. A second voice input from the voice-capturing device is received, via the network, at the service provider environment. The second voice input represents a command to disregard the first voice input. Based on the second voice input, the representation of the first voice input is deleted.