# Partitioning speakers (diarization)
With speaker diarization, you can distinguish between different speakers in your transcription output. Amazon Transcribe can differentiate between a maximum of 30 unique speakers and labels the text from each unique speaker with a unique value (`spk_0` through `spk_9`).
In addition to the [standard transcript sections](how-input.md#how-it-works-output) (`transcripts` and `items`), requests with speaker partitioning enabled include a `speaker_labels` section. This section is grouped by speaker and contains information on each utterance, including speaker label and timestamps.
```
"speaker_labels": {
"channel_label": "ch_0",
"speakers": 2,
"segments": [
{
"start_time": "4.87",
"speaker_label": "spk_0",
"end_time": "6.88",
"items": [
{
"start_time": "4.87",
"speaker_label": "spk_0",
"end_time": "5.02"
},
...
{
"start_time": "8.49",
"speaker_label": "spk_1",
"end_time": "9.24",
"items": [
{
"start_time": "8.49",
"speaker_label": "spk_1",
"end_time": "8.88"
},
```
To view a complete example transcript with speaker partitioning (for two speakers), see [Example diarization output (batch)](diarization-output-batch.md).
## Partitioning speakers in a batch transcription
To partition speakers in a batch transcription, see the following examples:
### AWS Management Console
1. Sign in to the [AWS Management Console](https://console.aws.amazon.com/transcribe/).
1. In the navigation pane, choose **Transcription jobs**, then select **Create job** (top right). This opens the **Specify job details** page.
![\[Amazon Transcribe console 'Specify job details' page. In the 'Job settings' panel, you can specify a name for your transcription job, select a Model type, and specify your language settings.\]](http://docs.aws.amazon.com/transcribe/latest/dg/images/console-batch-job-details-1.png)
1. Fill in any fields you want to include on the **Specify job details** page, then select **Next**. This takes you to the **Configure job - *optional*** page.
To enable speaker partitioning, in **Audio settings**, choose **Audio identification**. Then choose **Speaker partitioning** and specify the number of speakers.
![\[Amazon Transcribe console 'Configure job' page. In the 'Audio settings' panel, you can enable 'Speaker partitioning'.\]](http://docs.aws.amazon.com/transcribe/latest/dg/images/diarization-batch.png)
1. Select **Create job** to run your transcription job.
### AWS CLI
This example uses the [start-transcription-job](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/transcribe/start-transcription-job.html). For more information, see [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html).
```
aws transcribe start-transcription-job \
--region us-west-2 \
--transcription-job-name my-first-transcription-job \
--media MediaFileUri=s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac \
--output-bucket-name amzn-s3-demo-bucket \
--output-key my-output-files/ \
--language-code en-US \
--settings ShowSpeakerLabels=true,MaxSpeakerLabels=3
```
Here's another example using the [start-transcription-job](https://awscli.amazonaws.com/v2/documentation/api/latest/reference/transcribe/start-transcription-job.html) command, and a request body that enables speaker partitioning with that job.
```
aws transcribe start-transcription-job \
--region us-west-2 \
--cli-input-json file://my-first-transcription-job.json
```
The file *my-first-transcription-job.json* contains the following request body.
```
{
"TranscriptionJobName": "my-first-transcription-job",
"Media": {
"MediaFileUri": "s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac"
},
"OutputBucketName": "amzn-s3-demo-bucket",
"OutputKey": "my-output-files/",
"LanguageCode": "en-US",
"ShowSpeakerLabels": 'TRUE',
"MaxSpeakerLabels": 3
}
```
### AWS SDK for Python (Boto3)
This example uses the AWS SDK for Python (Boto3) to identify channels using the [start\$1transcription\$1job](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/transcribe.html#TranscribeService.Client.start_transcription_job) method. For more information, see [StartTranscriptionJob](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_StartTranscriptionJob.html).
```
from __future__ import print_function
import time
import boto3
transcribe = boto3.client('transcribe', 'us-west-2')
job_name = "my-first-transcription-job"
job_uri = "s3://amzn-s3-demo-bucket/my-input-files/my-media-file.flac"
transcribe.start_transcription_job(
TranscriptionJobName = job_name,
Media = {
'MediaFileUri': job_uri
},
OutputBucketName = 'amzn-s3-demo-bucket',
OutputKey = 'my-output-files/',
LanguageCode = 'en-US',
Settings = {
'ShowSpeakerLabels': True,
'MaxSpeakerLabels': 3
}
)
while True:
status = transcribe.get_transcription_job(TranscriptionJobName = job_name)
if status['TranscriptionJob']['TranscriptionJobStatus'] in ['COMPLETED', 'FAILED']:
break
print("Not ready yet...")
time.sleep(5)
print(status)
```
## Partitioning speakers in a streaming transcription
To partition speakers in a streaming transcription, see the following examples:
### Streaming transcriptions
1. Sign in to the [AWS Management Console](https://console.aws.amazon.com/transcribe/).
1. In the navigation pane, choose **Real-time transcription**. Scroll down to **Audio settings** and expand this field if it is minimized.
![\[Amazon Transcribe console screenshot: the 'audio settings' tab on the 'real-time transcription' page.\]](http://docs.aws.amazon.com/transcribe/latest/dg/images/diarization-streaming1.png)
1. Toggle on **Speaker partitioning**.
![\[Amazon Transcribe console screenshot: the expanded 'audio settings' tab with speaker partitioning enabled.\]](http://docs.aws.amazon.com/transcribe/latest/dg/images/diarization-streaming2.png)
1. You're now ready to transcribe your stream. Select **Start streaming** and begin speaking. To end your dictation, select **Stop streaming**.
### HTTP/2 stream
This example creates an HTTP/2 request that partitions speakers in your transcription output. For more information on using HTTP/2 streaming with Amazon Transcribe, see [Setting up an HTTP/2 stream](streaming-setting-up.md#streaming-http2). For more detail on parameters and headers specific to Amazon Transcribe, see [StartStreamTranscription](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html).
```
POST /stream-transcription HTTP/2
host: transcribestreaming.us-west-2.amazonaws.com
X-Amz-Target: com.amazonaws.transcribe.Transcribe.StartStreamTranscription
Content-Type: application/vnd.amazon.eventstream
X-Amz-Content-Sha256: string
X-Amz-Date: 20220208T235959Z
Authorization: AWS4-HMAC-SHA256 Credential=access-key/20220208/us-west-2/transcribe/aws4_request, SignedHeaders=content-type;host;x-amz-content-sha256;x-amz-date;x-amz-target;x-amz-security-token, Signature=string
x-amzn-transcribe-language-code: en-US
x-amzn-transcribe-media-encoding: flac
x-amzn-transcribe-sample-rate: 16000
x-amzn-transcribe-show-speaker-label: true
transfer-encoding: chunked
```
Parameter definitions can be found in the [API Reference](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_Reference.html); parameters common to all AWS API operations are listed in the [Common Parameters](https://docs.aws.amazon.com/transcribe/latest/APIReference/CommonParameters.html) section.
### WebSocket stream
This example creates a presigned URL that separates speakers in your transcription output. Line breaks have been added for readability. For more information on using WebSocket streams with Amazon Transcribe, see [Setting up a WebSocket stream](streaming-setting-up.md#streaming-websocket). For more detail on parameters, see [https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_streaming_StartStreamTranscription.html).
```
GET wss://transcribestreaming.us-west-2.amazonaws.com:8443/stream-transcription-websocket?
&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=string
&X-Amz-SignedHeaders=content-type%3Bhost%3Bx-amz-date
&language-code=en-US
&specialty=PRIMARYCARE
&type=DICTATION
&media-encoding=flac
&sample-rate=16000
&show-speaker-label=true
```
Parameter definitions can be found in the [API Reference](https://docs.aws.amazon.com/transcribe/latest/APIReference/API_Reference.html); parameters common to all AWS API operations are listed in the [Common Parameters](https://docs.aws.amazon.com/transcribe/latest/APIReference/CommonParameters.html) section.
# Example diarization output (batch)
Here's an output example for a batch transcription with diarization enabled.
```
{
"jobName": "my-first-transcription-job",
"accountId": "111122223333",
"results": {
"transcripts": [
{
"transcript": "I've been on hold for an hour. Sorry about that."
}
],
"speaker_labels": {
"channel_label": "ch_0",
"speakers": 2,
"segments": [
{
"start_time": "4.87",
"speaker_label": "spk_0",
"end_time": "6.88",
"items": [
{
"start_time": "4.87",
"speaker_label": "spk_0",
"end_time": "5.02"
},
{
"start_time": "5.02",
"speaker_label": "spk_0",
"end_time": "5.17"
},
{
"start_time": "5.17",
"speaker_label": "spk_0",
"end_time": "5.29"
},
{
"start_time": "5.29",
"speaker_label": "spk_0",
"end_time": "5.64"
},
{
"start_time": "5.64",
"speaker_label": "spk_0",
"end_time": "5.84"
},
{
"start_time": "6.11",
"speaker_label": "spk_0",
"end_time": "6.26"
},
{
"start_time": "6.26",
"speaker_label": "spk_0",
"end_time": "6.88"
}
]
},
{
"start_time": "8.49",
"speaker_label": "spk_1",
"end_time": "9.24",
"items": [
{
"start_time": "8.49",
"speaker_label": "spk_1",
"end_time": "8.88"
},
{
"start_time": "8.88",
"speaker_label": "spk_1",
"end_time": "9.05"
},
{
"start_time": "9.05",
"speaker_label": "spk_1",
"end_time": "9.24"
}
]
}
]
},
"items": [
{
"id": 0,
"start_time": "4.87",
"speaker_label": "spk_0",
"end_time": "5.02",
"alternatives": [
{
"confidence": "1.0",
"content": "I've"
}
],
"type": "pronunciation"
},
{
"id": 1,
"start_time": "5.02",
"speaker_label": "spk_0",
"end_time": "5.17",
"alternatives": [
{
"confidence": "1.0",
"content": "been"
}
],
"type": "pronunciation"
},
{
"id": 2,
"start_time": "5.17",
"speaker_label": "spk_0",
"end_time": "5.29",
"alternatives": [
{
"confidence": "1.0",
"content": "on"
}
],
"type": "pronunciation"
},
{
"id": 3,
"start_time": "5.29",
"speaker_label": "spk_0",
"end_time": "5.64",
"alternatives": [
{
"confidence": "1.0",
"content": "hold"
}
],
"type": "pronunciation"
},
{
"id": 4,
"start_time": "5.64",
"speaker_label": "spk_0",
"end_time": "5.84",
"alternatives": [
{
"confidence": "1.0",
"content": "for"
}
],
"type": "pronunciation"
},
{
"id": 5,
"start_time": "6.11",
"speaker_label": "spk_0",
"end_time": "6.26",
"alternatives": [
{
"confidence": "1.0",
"content": "an"
}
],
"type": "pronunciation"
},
{
"id": 6,
"start_time": "6.26",
"speaker_label": "spk_0",
"end_time": "6.88",
"alternatives": [
{
"confidence": "1.0",
"content": "hour"
}
],
"type": "pronunciation"
},
{
"id": 7,
"speaker_label": "spk_0",
"alternatives": [
{
"confidence": "0.0",
"content": "."
}
],
"type": "punctuation"
},
{
"id": 8,
"start_time": "8.49",
"speaker_label": "spk_1",
"end_time": "8.88",
"alternatives": [
{
"confidence": "1.0",
"content": "Sorry"
}
],
"type": "pronunciation"
},
{
"id": 9,
"start_time": "8.88",
"speaker_label": "spk_1",
"end_time": "9.05",
"alternatives": [
{
"confidence": "0.902",
"content": "about"
}
],
"type": "pronunciation"
},
{
"id": 10,
"start_time": "9.05",
"speaker_label": "spk_1",
"end_time": "9.24",
"alternatives": [
{
"confidence": "1.0",
"content": "that"
}
],
"type": "pronunciation"
},
{
"id": 11,
"speaker_label": "spk_1",
"alternatives": [
{
"confidence": "0.0",
"content": "."
}
],
"type": "punctuation"
}
],
"audio_segments": [
{
"id": 0,
"transcript": "I've been on hold for an hour.",
"start_time": "4.87",
"end_time": "6.88",
"speaker_label": "spk_0",
"items": [
0,
1,
2,
3,
4,
5,
6,
7
]
},
{
"id": 1,
"transcript": "Sorry about that.",
"start_time": "8.49",
"end_time": "9.24",
"speaker_label": "spk_1",
"items": [
8,
9,
10,
11
]
}
]
},
"status": "COMPLETED"
}
```