# Transcribing a medical dictation
You can use Amazon Transcribe Medical to transcribe clinician-dictated medical notes using either a batch transcription job or a real-time stream. Batch transcription jobs enable you to transcribe audio files. You specify the medical specialty of the clinician in your transcription job or stream to ensure that Amazon Transcribe Medical produces transcription results with the highest possible accuracy.
You can transcribe a medical dictation in the following specialties:
+ Cardiology – available in streaming transcription only
+ Neurology – available in streaming transcription only
+ Oncology – available in streaming transcription only
+ Primary Care – includes the following types of medical practice:
+ Family medicine
+ Internal medicine
+ Obstetrics and Gynecology (OB-GYN)
+ Pediatrics
+ Radiology – available in streaming transcription only
+ Urology – available in streaming transcription only
You can improve transcription accuracy by using custom vocabularies. For information on how medical custom vocabularies work, see [Improving transcription accuracy with medical custom vocabularies](vocabulary-med.md).
By default, Amazon Transcribe Medical returns the transcription with the highest confidence level. If you'd like to configure it to return alternative transcriptions, see [Generating alternative transcriptions](alternative-med-transcriptions.md).
For information about how numbers and medical measurements appear in the transcription output, see [Transcribing numbers](how-numbers-med.md) and [Transcribing medical terms and measurements](how-measurements-med.md).
**Topics**
+ [Transcribing an audio file of a medical dictation](batch-medical-dictation.md)
+ [Transcribing a medical dictation in a real-time stream](streaming-medical-dictation.md)
# Transcribing an audio file of a medical dictation
Use a batch transcription job to transcribe audio files of medical conversations. You can use this to transcribe a clinician-patient dialogue. You can start a batch transcription job in either the [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartMedicalTranscriptionJob.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartMedicalTranscriptionJob.html) API or the AWS Management Console.
When you start a medical transcription job with the [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartMedicalTranscriptionJob.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartMedicalTranscriptionJob.html) API, you specify `PRIMARYCARE` as the value of the `Specialty` parameter.
## AWS Management Console
**To transcribe a clinician-patient dialogue (AWS Management Console)**
To use the AWS Management Console to transcribe a clinician-patient dialogue, create a transcription job and choose **Conversation** for **Audio input type**.
1. Sign in to the [AWS Management Console](https://console.aws.amazon.com/transcribe/).
1. In the navigation pane, under Amazon Transcribe Medical, choose **Transcription jobs**.
1. Choose **Create job**.
1. On the **Specify job details** page, under **Job settings **, specify the following.
1. **Name** – the name of the transcription job.
1. **Audio input type** – **Dictation**
1. For the remaining fields, specify the Amazon S3 location of your audio file and where you want to store the output of your transcription job.
1. Choose **Next**.
1. Choose **Create**.
## API
**To transcribe a medical conversation using a batch transcription job (API)**
+ For the [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartMedicalTranscriptionJob.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartMedicalTranscriptionJob.html) API, specify the following.
1. For `MedicalTranscriptionJobName`, specify a name unique in your AWS account.
1. For `LanguageCode`, specify the language code that corresponds to the language spoken in your audio file and the language of your vocabulary filter.
1. In the `MediaFileUri` parameter of the `Media` object, specify the name of the audio file that you want to transcribe.
1. For `Specialty`, specify the medical specialty of the clinician speaking in the audio file.
1. For `Type`, specify `DICTATION`.
1. For `OutputBucketName`, specify the Amazon S3 bucket to store the transcription results.
The following is an example request that uses the AWS SDK for Python (Boto3) to transcribe a medical dictation of a clinician in the `PRIMARYCARE` specialty.
```
from __future__ import print_function
import time
import boto3
transcribe = boto3.client('transcribe')
job_name = "my-first-med-transcription-job"
job_uri = "s3://amzn-s3-demo-bucket/my-input-files/my-audio-file.flac"
transcribe.start_medical_transcription_job(
MedicalTranscriptionJobName = job_name,
Media = {
'MediaFileUri': job_uri
},
OutputBucketName = 'amzn-s3-demo-bucket',
OutputKey = 'my-output-files/',
LanguageCode = 'en-US',
Specialty = 'PRIMARYCARE',
Type = 'DICTATION'
)
while True:
status = transcribe.get_medical_transcription_job(MedicalTranscriptionJobName = job_name)
if status['MedicalTranscriptionJob']['TranscriptionJobStatus'] in ['COMPLETED', 'FAILED']:
break
print("Not ready yet...")
time.sleep(5)
print(status)
```
The following example code shows the transcription results of a medical dictation.
```
{
"jobName": "dictation-medical-transcription-job",
"accountId": "111122223333",
"results": {
"transcripts": [
{
"transcript": "... came for a follow up visit today..."
}
],
"items": [
{
...
"start_time": "4.85",
"end_time": "5.12",
"alternatives": [
{
"confidence": "1.0",
"content": "came"
}
],
"type": "pronunciation"
},
{
"start_time": "5.12",
"end_time": "5.29",
"alternatives": [
{
"confidence": "1.0",
"content": "for"
}
],
"type": "pronunciation"
},
{
"start_time": "5.29",
"end_time": "5.33",
"alternatives": [
{
"confidence": "0.9955",
"content": "a"
}
],
"type": "pronunciation"
},
{
"start_time": "5.33",
"end_time": "5.66",
"alternatives": [
{
"confidence": "0.9754",
"content": "follow"
}
],
"type": "pronunciation"
},
{
"start_time": "5.66",
"end_time": "5.75",
"alternatives": [
{
"confidence": "0.9754",
"content": "up"
}
],
"type": "pronunciation"
},
{
"start_time": "5.75",
"end_time": "6.02",
"alternatives": [
{
"confidence": "1.0",
"content": "visit"
}
]
...
},
"status": "COMPLETED"
}
```
## AWS CLI
**To enable speaker partitioning in a batch transcription job (AWS CLI)**
+ Run the following code.
```
aws transcribe start-medical-transcription-job \
--region us-west-2 \
--cli-input-json file://example-start-command.json
```
The following code shows the contents of `example-start-command.json`.
```
{
"MedicalTranscriptionJobName": "my-first-med-transcription-job",
"Media": {
"MediaFileUri": "s3://amzn-s3-demo-bucket/my-input-files/my-audio-file.flac"
},
"OutputBucketName": "amzn-s3-demo-bucket",
"OutputKey": "my-output-files/",
"LanguageCode": "en-US",
"Specialty": "PRIMARYCARE",
"Type": "DICTATION"
}
```
# Transcribing a medical dictation in a real-time stream
Use a WebSocket stream to transcribe a medical dictation as an audio stream. You can also use the AWS Management Console to transcribe speech that you or others speak directly into a microphone.
For an HTTP/2 or a WebSocket stream, you can transcribe audio in the following medical specialties:
+ Cardiology
+ Oncology
+ Neurology
+ Primary Care
+ Radiology
+ Urology
Each medical specialty includes many types of procedures and appointments. Clinicians therefore dictate many different types of notes. Use the following examples as guidance to help you specify the value of the `specialty` URI parameter of the WebSocket request, or the `Specialty` parameter of the [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartMedicalStreamTranscription.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartMedicalStreamTranscription.html) API:
+ For a dictation after electrophysiology or echocardiogram procedure, choose `CARDIOLOGY`.
+ For a dictation after a surgical oncology or radiation oncology procedure, choose `ONCOLOGY`.
+ For a physician dictating notes indicating a diagnosis of encephalitis, choose `NEUROLOGY`.
+ For a dictation of procedure notes to break up a bladder stone, choose `UROLOGY`.
+ For a dictation of clinician notes after an internal medicine consultation, choose `PRIMARYCARE`.
+ For a dictation of a physician communicating the findings of a CT scan, PET scan, MRI, or radiograph, choose `RADIOLOGY`.
+ For a dictation of physician notes after a gynecology consultation, choose `PRIMARYCARE`.
To improve transcription accuracy of specific terms in a real-time stream, use a custom vocabulary. To enable a custom vocabulary, set the value of `vocabulary-name` to the name of the custom vocabulary you want to use.
## Transcribing a dictation spoken into your microphone with the AWS Management Console
To use the AWS Management Console to transcribe streaming audio of a medical dictation, choose the option to transcribe a medical dictation, start the stream, and begin speaking into the microphone.
**To transcribe streaming audio of a medical dictation (AWS Management Console)**
1. Sign in to the [AWS Management Console](https://console.aws.amazon.com/transcribe/).
1. In the navigation pane, under Amazon Transcribe Medical, choose **Real-time transcription**.
1. Choose **Dictation**.
1. For **Medical specialty**, choose the medical specialty of the clinician speaking in the stream.
1. Choose **Start streaming**.
1. Speak into the microphone.
## Transcribing a dictation in an HTTP/2 stream
To transcribe an HTTP/2 stream of a medical dictation, use the [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartMedicalStreamTranscription.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartMedicalStreamTranscription.html) API and specify the following:
+ `LanguageCode` – The language code. The valid value is `en-US`
+ `MediaEncoding` – The encoding used for the input audio. Valid values are `pcm`, `ogg-opus`, and `flac`.
+ `Specialty` – The specialty of the medical professional.
+ `Type` – `DICTATION`
For more information on setting up an HTTP/2 stream to transcribe a medical dictation, see [Setting up an HTTP/2 stream](streaming-setting-up.md#streaming-http2).
## Using a WebSocket streaming request to transcribe a medical dictation
To transcribe a medical dictation in a real-time stream using a WebSocket request, you create a presigned URI. This URI contains the information needed to set up the audio stream between your application and Amazon Transcribe Medical. For more information on creating WebSocket requests, see [Setting up a WebSocket stream](streaming-setting-up.md#streaming-websocket).
Use the following template to create your presigned URI.
```
GET wss://transcribestreaming.us-west-2.amazonaws.com:8443/medical-stream-transcription-websocket
?language-code=languageCode
&X-Amz-Algorithm=AWS4-HMAC-SHA256
&X-Amz-Credential=AKIAIOSFODNN7EXAMPLE%2F20220208%2Fus-west-2%2Ftranscribe%2Faws4_request
&X-Amz-Date=20220208T235959Z
&X-Amz-Expires=300
&X-Amz-Security-Token=security-token
&X-Amz-Signature=Signature Version 4 signature
&X-Amz-SignedHeaders=host
&media-encoding=flac
&sample-rate=16000
&session-id=sessionId
&specialty=medicalSpecialty
&type=DICTATION
&vocabulary-name=vocabularyName
&show-speaker-label=boolean
```
For more information on creating pre-signed URIs, see [Setting up a WebSocket stream](streaming-setting-up.md#streaming-websocket).