Enhancing recorded conversations
In one embodiment, a method includes recording, by a microphone of an electronic device, audio in a vicinity of the device and capturing, by a camera of an electronic device, an image that includes information about a person in the vicinity. The method further includes extracting, based at least on the captured image, identifying information about the person; extracting a portion of the recorded audio corresponding to a conversation between a user and the person; generating a transcription of the extracted portion of the recorded audio; determining, based on the transcription and from an AI model, a summary of the conversation; and storing the summary and the extracted identifying information together in a data store for the user.
1 . A method comprising:
recording, by a microphone of an electronic device, audio in a vicinity of the device;
capturing, by a camera of an electronic device and in response to an explicit image-capture command from a user of the electronic device, an image of an inanimate object comprising information about a person in the vicinity;
extracting, based at least on the captured image, identifying information about the person;
in response to the camera capturing the image of the inanimate object comprising information about the person, then triggering, as a result of the camera capturing the image, a conversation-extraction process from the recorded audio for a particular conversation between the user and the person, comprising:
extracting a portion of the recorded audio corresponding to a conversation between the user and the person;
generating a transcription of the extracted portion of the recorded audio;
determining, based on the transcription and from an artificial intelligence (AI) model, a summary of the conversation; and
storing the summary and the extracted identifying information together in a data store for the user.
2 . The method of claim 1 , wherein:
the microphone and the camera are each part of a mobile device of the user; and
capturing the image comprising information about the person comprises receiving a single user input on a user interface (UI) displayed on the mobile device, the UI comprising an interactive element for capturing the image.
3 . The method of claim 1 , further comprising enriching, based on an internet search query using the extracted identifying information about the person, the identifying information with additional identifying information about the person.
4 . The method of claim 1 , wherein extracting a portion of the recorded audio corresponding to a conversation between a user and the person comprises determining, by an AI model, the portion of the recorded audio corresponding to the conversation.
5 . The method of claim 1 , further comprising determining, based on the transcription and from the AI model, a summary of (1) one or more follow-up action items and (2) one or more personal details of the person.
6 . The method of claim 1 , further comprising generating a uniform resource locator (URL) to a landing page comprising the stored summary and extracted identifying information.
7 . The method of claim 1 , further comprising generating, by an AI model, a draft email to the person from the user based on the summary of the conversation.
8 . The method of claim 1 , further comprising automatically populating an entry, based on the stored summary and identifying information, for the person in a customer relationship management (CRM) of the user.
9 . The method of claim 1 , further comprising:
generating a transcription of each of a plurality of audio recordings from a plurality of electronic devices at a particular event;
determining, based on the generated transcriptions, one or more conversation metrics at the event.
10 . A system comprising one or more non-transitory computer readable storage media storing instructions; and one or more processors operable to execute the instructions to:
record, by a microphone of an electronic device, audio in a vicinity of the device;
capture, by a camera of an electronic device and in response to an explicit image-capture command from a user of the electronic device, an image of an inanimate object;
extract, based at least on the captured image, identifying information about the person;
in response to the camera capturing the image of the inanimate object comprising information about the person, then trigger, as a result of the camera capturing the image, a conversation-extraction process from the recorded audio for a particular conversation between the user and the person, comprising:
extract a portion of the recorded audio corresponding to a conversation between the user and the person;
generate a transcription of the extracted portion of the recorded audio;
determine, based on the transcription and from an artificial intelligence (AI) model, a summary of the conversation; and
store the summary and the extracted identifying information together in a data store for the user.
11 . The system of claim 10 , wherein:
the microphone and the camera are each part of a mobile device of the user;
capturing the image comprising information about the person comprises receiving a single user input on a user interface (UI) displayed on the mobile device, the UI comprising an interactive element for capturing an image.
12 . The system of claim 10 , further comprising one or more processors that are operable to execute the instructions to enrich, based on an internet search query using the extracted identifying information about the person, the identifying information with additional identifying information about the person.
13 . The system of claim 10 , wherein extracting a portion of the recorded audio corresponding to a conversation between a user and the person comprises determining, by an AI model, the portion of the recorded audio corresponding to the conversation.
14 . The system of claim 10 , further comprising one or more processors that are operable to execute the instructions to determine, based on the transcription and from the AI model, a summary of (1) one or more follow-up action items and (2) one or more personal details of the person.
15 . The system of claim 10 , further comprising one or more processors that are operable to execute the instructions to generate a uniform resource locator (URL) to a landing page comprising the stored summary and extracted identifying information.
16 . The system of claim 10 , further comprising one or more processors that are operable to execute the instructions to generate, by an AI model, a draft email to the person from the user based on the summary of the conversation.
17 . The system of claim 10 , further comprising one or more processors that are operable to execute the instructions to automatically populate an entry, based on the stored summary and identifying information, for the person in a customer relationship management (CRM) of the user.
18 . The system of claim 10 , further comprising one or more processors that are operable to execute the instructions to:
generating a transcription of each of a plurality of audio recordings from a plurality of electronic devices at a particular event;
determining, based on the generated transcriptions, one or more conversation metrics at the event.
19 . One or more non-transitory computer readable storage media storing instructions that are operable when executed to:
record, by a microphone of an electronic device, audio in a vicinity of the device;
capture, by a camera of an electronic device and in response to an explicit image-capture command from a user of the electronic device, an image of an inanimate object;
extract, based at least on the captured image, identifying information about the person;
in response to the camera capturing the image of the inanimate object comprising information about the person, then trigger, as a result of the camera capturing the image, a conversation-extraction process from the recorded audio for a particular conversation between the user and the person, comprising:
extract a portion of the recorded audio corresponding to a conversation between the user and the person;
generate a transcription of the extracted portion of the recorded audio;
determine, based on the transcription and from an artificial intelligence (AI) model, a summary of the conversation; and
store the summary and the extracted identifying information together in a data store for the user.
20 . The media of claim 19 , wherein:
the microphone and the camera are each part of a mobile device of the user; and
capturing the image comprising information about the person comprises receiving a single user input on a user interface (UI) displayed on the mobile device, the UI comprising an interactive element for capturing an image.