Amazon Transcribe is an automatic speech recognition service that uses machine learning models to convert audio to text.
This connector allows you to:
do batch (and asynchronous) transcription jobs to convert audio to text;
do batch medical transcription jobs to transcribe medical speech to text;
create and use custom vocabularies to improve speech transcription;
create and use medical vocabularies to improve accuracy in medical transcription;
create and use vocabulary filters to exclude words from the transcription (for example, profanity);
create and use custom language models to improve transcription accuracy for your specific use case;
create and use call analytics insights for succinct summaries of the important components in agent-customer calls, including issues, action items, and outcomes for each participant;
create and use call analytics categorization to flag keywords, phrases, sentiment, or actions during a call. The categorization options can help you triage escalations, such as negative-sentiment calls with many interruptions, or organize calls into specific categories, such as company departments;
add tags to a resource in order to make it easier to identify, organize, and find in a search;
This component is based on the AWS SDK for .NET v3.
To use the Amazon Transcribe connector you must have:
an AWS account;
an AWS access key (access key ID and secret access key);
for some connector actions, an S3 bucket, to store required the input file. To use these capabilities, the AWS account must have access to get objects from the specified bucket.
See the AWS documentation for detailed information about getting started and developing apps with Amazon Transcribe.
To configure your connector to access Amazon Transcribe, you need the following AWS authentication information:
The access key ID of your AWS access key
The secret access key of your AWS access key
The AWS Region of the service endpoint to which you want to connect. To reduce latency, choose a region close to your application server. See the API documentation for the list of region names.
Use the above authentication information to fill in the AWSCredentials parameters in all of the public actions available in the AWSTranscribeConnector_IS module. The OutSystems parameters are:
Region
AccessKeyId
SecretAccessKey
For each use case, the connector exposes a set of actions. Find them listed below.
StartTranscriptionJob: Starts an asynchronous job to transcribe speech to text.
GetTranscriptionJob: Returns information about a transcription job.
ListTranscriptionJobs: Lists transcription jobs with the specified status.
DeleteTranscriptionJob: Deletes a previously submitted transcription job along with any other generated results such as the transcription, models, and so on.
StartMedicalTranscriptionJob: Starts a batch job to transcribe medical speech to text.
GetMedicalTranscriptionJob: Retrieves information about a medical transcription job.
ListMedicalTranscriptionJobs: Lists medical transcription jobs with a specified status or substring that matches their names.
DeleteMedicalTranscriptionJob: Deletes a medical transcription job, along with any related information.
CreateVocabulary: Creates a new custom vocabulary that you can use to change the way Amazon Transcribe handles transcription of an audio file.
DeleteVocabulary: Deletes a vocabulary from Amazon Transcribe.
ListVocabularies: Returns a list of vocabularies that match the specified criteria.
GetVocabulary: Gets information about a vocabulary.
UpdateVocabulary: Updates an existing vocabulary with new values.
CreateMedicalVocabulary: Creates a new custom medical vocabulary.
DeleteMedicalVocabulary: Deletes a custom medical vocabulary.
ListMedicalVocabularies: Returns a list of medical vocabularies that match the specified criteria.
GetMedicalVocabulary: Retrieves information about a medical vocabulary.
UpdateMedicalVocabulary: Updates a medical vocabulary with new values that you provide in a different text file from the one you used to create the vocabulary.
CreateVocabularyFilter: Creates a new vocabulary filter that you can use to filter words, such as profane words, from the output of a transcription job.
DeleteVocabularyFilter: Removes a vocabulary filter.
ListVocabularyFilters: Gets information about vocabulary filters.
GetVocabularyFilter: Returns information about a vocabulary filter.
UpdateVocabularyFilter: Updates a vocabulary filter with a new list of filtered words.
CreateLanguageModel: Creates a new custom language model.
DescribeLanguageModel: Provides information about a specific custom language model in your AWS account.
ListLanguageModels: Provides more information about the custom language models you've created.
DeleteLanguageModel: Deletes a custom language model.
StartCallAnalyticsJob: Starts an asynchronous analytics job that not only transcribes the audio recording of a caller and agent, but also returns additional insights.
GetCallAnalyticsJob: Retrieves information about a call analytics job.
ListCallAnalyticsJobs: List call analytics jobs with a specified status or substring that matches their names.
DeleteCallAnalyticsJob: Deletes a call analytics job.
CreateCallAnalyticsCategory: Creates a call analytics category.
UpdateCallAnalyticsCategory: Updates the call analytics category with new values.
ListCallAnalyticsCategories: Provides more information about the call analytics categories that you've created.
GetCallAnalyticsCategory: Retrieves information about a call analytics category.
DeleteCallAnalyticsCategory: Deletes a call analytics category.
ListTagsForResource: Lists all tags associated with a given transcription job, vocabulary, or resource.
TagResource: Tags an Amazon Transcribe resource with the given list of tags.
UntagResource: Removes specified tags from a specified Amazon Transcribe resource.
create and use vocabulary filters to exclude words from the transcription (for example, profanity).