Amazon.TranscribeStreaming.Model

A list of possible alternative transcriptions for the input audio. Each alternative may contain one or more of Items, Entities, or Transcript.

A wrapper for your audio chunks. Your audio stream consists of one or more audio events, which consist of one or more audio chunks.

For more information, see Event stream encoding.

One or more arguments to the StartStreamTranscription, StartMedicalStreamTranscription, or StartCallAnalyticsStreamTranscription operation was not valid. For example, MediaEncoding or LanguageCode used unsupported values. Check the specified parameters and try your request again.

Contains entities identified as personally identifiable information (PII) in your transcription output, along with various associated attributes. Examples include category, confidence score, content, type, and start and end times.

A word, phrase, or punctuation mark in your Call Analytics transcription output, along with various associated attributes, such as confidence score, type, and start and end times.

Contains detailed information about your real-time Call Analytics session. These details are provided in the UtteranceEvent and CategoryEvent objects.

Provides information on any TranscriptFilterType categories that matched your transcription output. Matches are identified for each segment upon completion of that segment.

Makes it possible to specify which speaker is on which audio channel. For example, if your agent is the first participant to speak, you would set ChannelId to 0 (to indicate the first channel) and ParticipantRole to AGENT (to indicate that it's the agent speaking).

Provides the location, using character count, in your transcript where a match is identified. For example, the location of an issue or a category match within a segment.

The details for clinical note generation, including status, and output locations for clinical note and aggregated transcript if the analytics completed, or failure reason if the analytics failed.

The output configuration for aggregated transcript and clinical note generation.

Allows you to set audio channel definitions and post-call analytics settings.

A new stream started with the same session ID. The current stream has been terminated.

Contains entities identified as personally identifiable information (PII) in your transcription output, along with various associated attributes. Examples include category, confidence score, type, stability score, and start and end times.

Container for the parameters to the GetMedicalScribeStream operation. Provides details about the specified Amazon Web Services HealthScribe streaming session. To view the status of the streaming session, check the StreamStatus field in the response. To get the details of post-stream analytics, including its status, check the PostStreamAnalyticsResult field in the response.

This is the response object from the GetMedicalScribeStream operation.

A problem occurred while processing the audio. Amazon Transcribe terminated processing.

Lists the issues that were identified in your audio segment.

A word, phrase, or punctuation mark in your transcription output, along with various associated attributes, such as confidence score, type, and start and end times.

The language code that represents the language identified in your audio, including the associated confidence score. If you enabled channel identification in your request and each channel contained a different language, you will have more than one LanguageWithScore result.

Your client has exceeded one of the Amazon Transcribe limits. This is typically the audio length limit. Break your audio stream into smaller chunks and try your request again.

A list of possible alternative transcriptions for the input audio. Each alternative may contain one or more of Items, Entities, or Transcript.

Contains entities identified as personal health information (PHI) in your transcription output, along with various associated attributes. Examples include category, confidence score, type, stability score, and start and end times.

A word, phrase, or punctuation mark in your transcription output, along with various associated attributes, such as confidence score, type, and start and end times.

The Result associated with a .

Contains a set of transcription results from one or more audio segments, along with additional information per your request parameters. This can include information relating to alternative transcriptions, channel identification, partial result stabilization, language identification, and other transcription-related data.

A wrapper for your audio chunks

For more information, see Event stream encoding.

Makes it possible to specify which speaker is on which channel. For example, if the clinician is the first participant to speak, you would set the ChannelId of the first ChannelDefinition in the list to 0 (to indicate the first channel) and ParticipantRole to CLINICIAN (to indicate that it's the clinician speaking). Then you would set the ChannelId of the second ChannelDefinition in the list to 1 (to indicate the second channel) and ParticipantRole to PATIENT (to indicate that it's the patient speaking).

If you don't specify a channel definition, HealthScribe will diarize the transcription and identify speaker roles for each speaker.

Specify details to configure the streaming session, including channel definitions, encryption settings, post-stream analytics settings, resource access role ARN and vocabulary settings.

Whether you are starting a new session or resuming an existing session, your first event must be a MedicalScribeConfigurationEvent. If you are resuming a session, then this event must have the same configurations that you provided to start the session.

Contains encryption related settings to be used for data encryption with Key Management Service, including KmsEncryptionContext and KmsKeyId. The KmsKeyId is required, while KmsEncryptionContext is optional for additional layer of security.

By default, Amazon Web Services HealthScribe provides encryption at rest to protect sensitive customer data using Amazon S3-managed keys. HealthScribe uses the KMS key you specify as a second layer of encryption.

Your ResourceAccessRoleArn must permission to use your KMS key. For more information, see Data Encryption at rest for Amazon Web Services HealthScribe.

Contains details for the result of post-stream analytics.

The settings for post-stream analytics.

Result stream where you will receive the output events. The details are provided in the MedicalScribeTranscriptEvent object.

Specify the lifecycle of your streaming session.

Contains details about a Amazon Web Services HealthScribe streaming session.

The event associated with MedicalScribeResultStream.

Contains MedicalScribeTranscriptSegment, which contains segment related information.

A word, phrase, or punctuation mark in your transcription output, along with various associated attributes, such as confidence score, type, and start and end times.

Contains a set of transcription results, along with additional information of the segment.

The MedicalTranscript associated with a .

MedicalTranscript contains Results, which contains a set of transcription results from one or more audio segments, along with additional information per your request parameters.

The MedicalTranscriptEvent associated with a MedicalTranscriptResultStream.

Contains a set of transcription results from one or more audio segments, along with additional information per your request parameters.

Contains detailed information about your streaming session.

Contains the timestamps of matched categories.

Allows you to specify additional settings for your Call Analytics post-call request, including output locations for your redacted transcript, which IAM role to use, and which encryption key to use.

DataAccessRoleArn and OutputLocation are required fields.

PostCallAnalyticsSettings provides you with the same insights as a Call Analytics post-call transcription. Refer to Post-call analytics for more information on this feature.

The request references a resource which doesn't exist.

The Result associated with a .

Contains a set of transcription results from one or more audio segments, along with additional information per your request parameters. This can include information relating to alternative transcriptions, channel identification, partial result stabilization, language identification, and other transcription-related data.

The service is currently unavailable. Try your request later.

Container for the parameters to the StartCallAnalyticsStreamTranscription operation. Starts a bidirectional HTTP/2 or WebSocket stream where audio is streamed to Amazon Transcribe and the transcription results are streamed to your application. Use this operation for Call Analytics transcriptions.

The following parameters are required:

• language-code

• media-encoding

• sample-rate

For more information on streaming with Amazon Transcribe, see Transcribing streaming audio.

This is the response object from the StartCallAnalyticsStreamTranscription operation.

Container for the parameters to the StartMedicalScribeStream operation. Starts a bidirectional HTTP/2 stream, where audio is streamed to Amazon Web Services HealthScribe and the transcription results are streamed to your application.

When you start a stream, you first specify the stream configuration in a MedicalScribeConfigurationEvent. This event includes channel definitions, encryption settings, and post-stream analytics settings, such as the output configuration for aggregated transcript and clinical note generation. These are additional streaming session configurations beyond those provided in your initial start request headers. Whether you are starting a new session or resuming an existing session, your first event must be a MedicalScribeConfigurationEvent.

After you send a MedicalScribeConfigurationEvent, you start AudioEvents and Amazon Web Services HealthScribe responds with real-time transcription results. When you are finished, to start processing the results with the post-stream analytics, send a MedicalScribeSessionControlEvent with a Type of END_OF_SESSION and Amazon Web Services HealthScribe starts the analytics.

You can pause or resume streaming. To pause streaming, complete the input stream without sending the MedicalScribeSessionControlEvent. To resume streaming, call the StartMedicalScribeStream and specify the same SessionId you used to start the stream.

The following parameters are required:

• language-code

• media-encoding

• media-sample-rate-hertz

For more information on streaming with Amazon Web Services HealthScribe, see Amazon Web Services HealthScribe.

This is the response object from the StartMedicalScribeStream operation.

Container for the parameters to the StartMedicalStreamTranscription operation. Starts a bidirectional HTTP/2 or WebSocket stream where audio is streamed to Amazon Transcribe Medical and the transcription results are streamed to your application.

The following parameters are required:

• language-code

• media-encoding

• sample-rate

For more information on streaming with Amazon Transcribe Medical, see Transcribing streaming audio.

This is the response object from the StartMedicalStreamTranscription operation.

Container for the parameters to the StartStreamTranscription operation. Starts a bidirectional HTTP/2 or WebSocket stream where audio is streamed to Amazon Transcribe and the transcription results are streamed to your application.

The following parameters are required:

• language-code or identify-language or identify-multiple-language

• media-encoding

• sample-rate

For more information on streaming with Amazon Transcribe, see Transcribing streaming audio.

This is the response object from the StartStreamTranscription operation.

Contains the timestamp range (start time through end time) of a matched category.

The Transcript associated with a .

Transcript contains Results, which contains a set of transcription results from one or more audio segments, along with additional information per your request parameters.

The TranscriptEvent associated with a TranscriptResultStream.

Contains a set of transcription results from one or more audio segments, along with additional information per your request parameters.

Contains detailed information about your streaming session.

Contains set of transcription results from one or more audio segments, along with additional information about the parameters included in your request. For example, channel definitions, partial result stabilization, sentiment, and issue detection.

Interface used to distinguish the events that can be sent to the service using the StartStreamTranscription service operation. The types that implement this interface are: Amazon.TranscribeStreaming.Model.AudioEvent Amazon.TranscribeStreaming.Model.ConfigurationEvent

Interface used to distinguish the events that can be sent to the service using the StartMedicalScribeStream service operation. The types that implement this interface are: Amazon.TranscribeStreaming.Model.MedicalScribeAudioEvent Amazon.TranscribeStreaming.Model.MedicalScribeConfigurationEvent Amazon.TranscribeStreaming.Model.MedicalScribeSessionControlEvent