CONTEXT-AWARE AUDIO INTERFACING
A redirection and messaging system receives telephony information identifying a caller and call context from a telephony system. The system selects one of a plurality of messaging operators based on the call context, optionally sends an introductory message to the caller via a messaging service, and generates a message interface for the selected message operator. The message interface includes the caller and call context and any messages sent between the caller and the selected message operator, with an input interface allowing the selected message operator to input and send messages to the caller.
1 . A method of context-aware interfacing, the method comprising:
receiving a recording of a voice of a user from a telephone call;
interpreting the recording of the voice of the user using a voice recognition algorithm to generate a transcript of the telephone call; and
outputting the transcript of the telephone call.
2 . The method of claim 1 , further comprising:
continuing a conversation involving the user over a messaging platform, wherein the telephone call includes a portion of the conversation, and wherein outputting the transcript of the telephone call includes outputting the transcript to the artificially intelligent chatbot associated with the messaging platform.
3 . The method of claim 1 , further comprising:
continuing a conversation involving the user over a messaging platform, wherein the telephone call includes a portion of the conversation, and wherein outputting the transcript of the telephone call includes outputting the transcript to a device of a messaging operator associated with the messaging platform.
4 . The method of claim 1 , wherein interpreting the recording of the voice of the user using the voice recognition algorithm is based on previous transcriptions of previous audio including the voice of the user.
5 . The method of claim 1 , wherein interpreting the recording of the voice of the user using the voice recognition algorithm is based on previous transcriptions of previous audio including another voice of another user.
6 . The method of claim 1 , wherein outputting the transcript includes outputting a link to the transcript.
7 . The method of claim 1 , wherein outputting the transcript includes attaching the transcript to a message as an attachment.
8 . The method of claim 1 , wherein outputting the transcript includes including at least a portion of the transcript within a message.
9 . The method of claim 1 , wherein the recording also includes a second voice of a second user who is part of the telephone call, wherein interpreting the recording to generate the transcript includes interpreting the second voice of the second user in the recording to generate the transcript, and wherein the transcript includes a representation of the voice of the user and a representation of the second voice of the second user.
10 . The method of claim 1 , wherein the recording also includes audio of a second voice that is played by a telephony system as part of the telephone call, wherein interpreting the recording to generate the transcript includes interpreting the audio of the second voice in the recording to generate the transcript, and wherein the transcript includes a representation of the voice of the user and a representation of the second voice.
11 . The method of claim 1 , further comprising:
combining the transcript of the telephone call with a second transcript of a second telephone call, wherein the second telephone call is associated with the user.
12 . The method of claim 1 , further comprising:
combining the transcript of the telephone call with a message history, wherein the message history is associated with the user.
13 . The method of claim 1 , wherein the telephone call is part of a conversation involving the user, wherein the conversation includes an artificially intelligent chatbot that communicates with the user.
14 . The method of claim 1 , wherein the telephone call is part of a conversation involving the user, wherein the conversation involves transfer of at least one of image data or video data.
15 . A system for context-aware interfacing, the system comprising:
a memory that stores instructions; and
a processor coupled to the memory, wherein execution of the instructions by the processor causes the processor to:
receive a recording of a voice of a user from a telephone call;
interpret the recording of the voice of the user using a voice recognition algorithm to generate a transcript of the telephone call; and
output the transcript of the telephone call.
16 . The method of claim 15 , wherein the execution of the instructions by the processor causes the processor to:
continue a conversation involving the user over a messaging platform, wherein the telephone call includes a portion of the conversation, and wherein outputting the transcript of the telephone call includes outputting the transcript to the artificially intelligent chatbot associated with the messaging platform.
17 . The method of claim 15 , wherein the execution of the instructions by the processor causes the processor to:
continue a conversation involving the user over a messaging platform, wherein the telephone call includes a portion of the conversation, and wherein outputting the transcript of the telephone call includes outputting the transcript to a device of a messaging operator associated with the messaging platform.
18 . The method of claim 15 , wherein interpreting the recording of the voice of the user using the voice recognition algorithm is based on previous transcriptions of previous audio including the voice of the user.
19 . The method of claim 15 , wherein interpreting the recording of the voice of the user using the voice recognition algorithm is based on previous transcriptions of previous audio including another voice of another user.
20 . The method of claim 15 , wherein outputting the transcript includes outputting a link to the transcript.
21 . The method of claim 15 , wherein outputting the transcript includes attaching the transcript to a message as an attachment.
22 . The method of claim 15 , wherein outputting the transcript includes including at least a portion of the transcript within a message.
23 . The method of claim 15 , wherein the recording also includes a second voice of a second user who is part of the telephone call, wherein interpreting the recording to generate the transcript includes interpreting the second voice of the second user in the recording to generate the transcript, and wherein the transcript includes a representation of the voice of the user and a representation of the second voice of the second user.
24 . The method of claim 15 , wherein the recording also includes audio of a second voice that is played by a telephony system as part of the telephone call, wherein interpreting the recording to generate the transcript includes interpreting the audio of the second voice in the recording to generate the transcript, and wherein the transcript includes a representation of the voice of the user and a representation of the second voice.
25 . The method of claim 15 , wherein the execution of the instructions by the processor causes the processor to:
combine the transcript of the telephone call with a second transcript of a second telephone call, wherein the second telephone call is associated with the user.
26 . The method of claim 15 , wherein the execution of the instructions by the processor causes the processor to:
combine the transcript of the telephone call with a message history, wherein the message history is associated with the user.
27 . The method of claim 15 , wherein the telephone call is part of a conversation involving the user, wherein the conversation includes an artificially intelligent chatbot that communicates with the user.
28 . The method of claim 15 , wherein the telephone call is part of a conversation involving the user, wherein the conversation involves transfer of at least one of image data or video data.
29 . A non-transitory computer readable storage medium having embodied thereon a program, wherein the program is executable by a processor to perform a method of context-aware interfacing, the method comprising:
receiving a recording of a voice of a user from a telephone call;
interpreting the recording of the voice of the user using a voice recognition algorithm to generate a transcript of the telephone call; and
outputting the transcript of the telephone call.
30 . The non-transitory computer readable storage medium of claim 29 , further comprising:
continuing a conversation involving the user over a messaging platform, wherein the telephone call includes a portion of the conversation, and wherein outputting the transcript of the telephone call includes outputting the transcript to the artificially intelligent chatbot associated with the messaging platform.
31 . The non-transitory computer readable storage medium of claim 29 , further comprising:
continuing a conversation involving the user over a messaging platform, wherein the telephone call includes a portion of the conversation, and wherein outputting the transcript of the telephone call includes outputting the transcript to a device of a messaging operator associated with the messaging platform.
32 . The non-transitory computer readable storage medium of claim 29 , wherein interpreting the recording of the voice of the user using the voice recognition algorithm is based on previous transcriptions of previous audio including the voice of the user.
33 . The non-transitory computer readable storage medium of claim 29 , wherein interpreting the recording of the voice of the user using the voice recognition algorithm is based on previous transcriptions of previous audio including another voice of another user.
34 . The non-transitory computer readable storage medium of claim 29 , wherein outputting the transcript includes outputting a link to the transcript.
35 . The non-transitory computer readable storage medium of claim 29 , wherein outputting the transcript includes attaching the transcript to a message as an attachment.
36 . The non-transitory computer readable storage medium of claim 29 , wherein outputting the transcript includes including at least a portion of the transcript within a message.
37 . The non-transitory computer readable storage medium of claim 29 , wherein the recording also includes a second voice of a second user who is part of the telephone call, wherein interpreting the recording to generate the transcript includes interpreting the second voice of the second user in the recording to generate the transcript, and wherein the transcript includes a representation of the voice of the user and a representation of the second voice of the second user.
38 . The non-transitory computer readable storage medium of claim 29 , wherein the recording also includes audio of a second voice that is played by a telephony system as part of the telephone call, wherein interpreting the recording to generate the transcript includes interpreting the audio of the second voice in the recording to generate the transcript, and wherein the transcript includes a representation of the voice of the user and a representation of the second voice.
39 . The non-transitory computer readable storage medium of claim 29 , further comprising:
combining the transcript of the telephone call with a second transcript of a second telephone call, wherein the second telephone call is associated with the user.
40 . The non-transitory computer readable storage medium of claim 29 , further comprising:
combining the transcript of the telephone call with a message history, wherein the message history is associated with the user.
41 . The non-transitory computer readable storage medium of claim 29 , wherein the telephone call is part of a conversation involving the user, wherein the conversation includes an artificially intelligent chatbot that communicates with the user.
42 . The non-transitory computer readable storage medium of claim 29 , wherein the telephone call is part of a conversation involving the user, wherein the conversation involves transfer of at least one of image data or video data.