Bot group messaging using bot-specific voice libraries

Abstract

A method includes receiving, by a group messaging service, a message including recorded audio and a first group identifier, and determining that the group includes a bot. The method also includes determining whether the bot is a user bot responsive to a user node in the group or a group bot responsive to each of the one or more user nodes, selecting a bot voice library to process the recorded audio, sending, by the group messaging service, the recorded audio to the determined user bot or group bot, processing the recorded audio to produce enhanced text, performing, by the determined user bot or group bot, one or more designated actions corresponding to one of the recorded audio and the enhanced text, and sending, by the determined user bot or group bot, an audio reply to the group messaging service.

1 - 20 . (canceled) 
     
     
         21 . A method comprising:
 receiving, at a group messaging service configured to manage messaging between a plurality of user nodes in a group, a message from a user node of the group to a bot member of the group;   in response to the message, accessing a bot entry in a data structure for the group maintained by the group messaging service, the bot entry including an indicator of a selected voice library corresponding to the bot member, voice libraries including a set of processing elements configured to convert an audio message into a target format;   processing, by the selected voice library from a plurality of available voice libraries, the message to produce a modified message in the target format suited to the bot member; and   sending, by the group messaging service, the modified message to the bot member.   
     
     
         22 . The method of  claim 21  further comprising:
 the message includes a bot identifier corresponding to the bot member; and 
 searching, at the group messaging service, the data structure based on the bot identifier to determine whether the bot member is a member of the group. 
 
     
     
         23 . The method of  claim 21  further comprising:
 the message includes recorded audio; and 
 processing the recorded audio via the selected voice library to produce the modified message. 
 
     
     
         24 . The method of  claim 23  further comprising:
 the selected voice library includes a text-to-speech engine; and 
 processing the recorded audio includes converting the recorded audio into a text format message via the text-to-speech engine. 
 
     
     
         25 . The method of  claim 24  further comprising:
 the selected voice library includes a natural language processing unit; and 
 processing the recorded audio includes converting the text format message into an enhanced text message suited for processing by the bot member via the natural language processing unit. 
 
     
     
         26 . The method of  claim 23  further comprising:
 the selected voice library includes an audio format converter module; and 
 processing the recorded audio includes converting the recorded audio from a first format to a second format via the audio format converter module. 
 
     
     
         27 . The method of  claim 21  further comprising:
 the plurality of available voice libraries include:
 a general voice library applicable to a plurality of bots; 
 a bot-specific voice library applicable to only the bot member; and 
 
 determining the selected voice library is the bot-specific voice library based on the bot entry. 
 
     
     
         28 . The method of  claim 21  further comprising:
 receiving, by the group messaging service, a reply from the bot member in response to sending the modified message; and 
 sending the reply from the group messaging service to the user node. 
 
     
     
         29 . The method of  claim 21  wherein at least a portion of the selected voice library is external to the group messaging service. 
     
     
         30 . An apparatus comprising:
 a processor configured to execute a group a group messaging service configured to manage messaging between a plurality of user nodes in a group, including:
 receive a message from a user node of the group to a bot member of the group; 
 in response to the message, access a bot entry in a data structure for the group, the bot entry including an indicator of a selected voice library corresponding to the bot member, voice libraries including a set of processing elements configured to convert an audio message into a target format; 
 process, by the selected voice library from a plurality of available voice libraries, the message to produce a modified message in the target format suited to the bot member; and 
 send the modified message to the bot member. 
   
     
     
         31 . The apparatus of  claim 30  further comprising:
 the message includes a bot identifier corresponding to the bot member; and 
 the processor further configured to search the data structure based on the bot identifier to determine whether the bot member is a member of the group. 
 
     
     
         32 . The apparatus of  claim 30  further comprising:
 the message includes recorded audio; and 
 the processor further configured to process the recorded audio via the selected voice library to produce the modified message. 
 
     
     
         33 . The apparatus of  claim 32  further comprising:
 the selected voice library includes:
 a text-to-speech engine; and 
 a natural language processing unit; 
 
 the processor further configured to process the recorded audio to produce the modified message, further including:
 convert the recorded audio into a text format message via the text-to-speech engine; and 
 convert the text format message into an enhanced text message suited for processing by the bot member via the natural language processing unit. 
 
 
     
     
         34 . The apparatus of  claim 32  further comprising:
 the selected voice library includes an audio format converter module; and 
 the processor further configured to convert the recorded audio from a first format to a second format via the audio format converter module. 
 
     
     
         35 . The apparatus of  claim 30  further comprising:
 the plurality of available voice libraries include:
 a general voice library applicable to a plurality of bots; 
 a bot-specific voice library applicable to only the bot member; and 
 
 the processor further configured to determine the selected voice library is the bot-specific voice library based on the bot entry. 
 
     
     
         36 . The apparatus of  claim 30  further comprising:
 at least a portion of the selected voice library is external to the group messaging service; and 
 the processor further configured to access the at least a portion of the selected voice library via a gateway processing unit. 
 
     
     
         37 . A memory device storing instructions that, when executed, cause a processor to perform a method comprising:
 receiving, at a group messaging service configured to manage messaging between a plurality of user nodes in a group, a message from a user node of the group to a bot member of the group;   in response to the message, accessing a bot entry in a data structure for the group maintained by the group messaging service, the bot entry including an indicator of a selected voice library corresponding to the bot member, voice libraries including a set of processing elements configured to convert an audio message into a target format;   processing, via the selected voice library from a plurality of available voice libraries, the message to produce a modified message in the target format suited to the bot member; and   sending, by the group messaging service, the modified message to the bot member.   
     
     
         38 . The memory device of  claim 37  storing instructions that, when executed, cause the processor to perform the method further comprising:
 the message includes a bot identifier corresponding to the bot member; and 
 searching, at the group messaging service, the data structure based on the bot identifier to determine whether the bot member is a member of the group. 
 
     
     
         39 . The memory device of  claim 38  storing instructions that, when executed, cause the processor to perform the method further comprising:
 the message includes recorded audio; 
 the selected voice library includes:
 a text-to-speech engine; 
 a natural language processing unit; 
 
 processing the recorded audio via the selected voice library to produce the modified message further including:
 converting the recorded audio into a text format message via the text-to-speech engine; and 
 converting the text format message into an enhanced text message suited for processing by the bot member via the natural language processing unit. 
 
 
     
     
         40 . The memory device of  claim 37  storing instructions that, when executed, cause the processor to perform the method further comprising:
 the plurality of available voice libraries include:
 a general voice library applicable to a plurality of bots; 
 a bot-specific voice library applicable to only the bot member; and 
 
 determining the selected voice library is the bot-specific voice library based on the bot entry.