AWS Step Functionsで、音声ファイルがS3バケットに保存される度にAmazon Transcribeで文字起こしし、内容をメール送信してみた

https://sns.ap-northeast-1.amazonaws.com/confirmation.html?TopicArn=arn:aws:sns:ap-northeast-1:xxxxxxxxxxxx:cm-hirai&Token=aaaaaaaaa&[email protected]

$ aws sns confirm-subscription \
 --topic-arn arn:aws:sns:ap-northeast-1:xxxxxxxxxxxx:cm-hirai \
 --token aaaaaaaaa \
 --authenticate-on-unsubscribe true \
 --region ap-northeast-1

{
    "SubscriptionArn": "arn:aws:sns:ap-northeast-1:xxxxxxxxxxxx:cm-hirai:xxxxxx"
}

$ aws sns get-subscription-attributes\
   --subscription-arn arn:aws:sns:ap-northeast-1:xxxxxxxxxxxx:cm-hirai:xxxxxx

{
    "Attributes": {
        "SubscriptionPrincipal": "arn:aws:iam::xxxxxxxxxxxx:role/xxxx",
        "Owner": "xxxxxxxxxxxx",
        "RawMessageDelivery": "false",
        "TopicArn": "arn:aws:sns:ap-northeast-1:xxxxxxxxxxxx:cm-hirai",
        "Endpoint": "[email protected]",
        "Protocol": "email",
        "PendingConfirmation": "false",
        "ConfirmationWasAuthenticated": "true",
        "SubscriptionArn": "arn:aws:sns:ap-northeast-1:xxxxxxxxxxxx:cm-hirai:xxxxxx"
    }
}

{
  "version": "0",
  "id": "17793124-05d4-b198-2fde-7ededc63b103",
  "detail-type": "Object Created",
  "source": "aws.s3",
  "account": "111122223333",
  "time": "2021-11-12T00:00:00Z",
  "region": "ca-central-1",
  "resources": [
    "arn:aws:s3:::DOC-EXAMPLE-BUCKET1"
  ],
  "detail": {
    "version": "0",
    "bucket": {
      "name": "DOC-EXAMPLE-BUCKET1"
    },
    "object": {
      "key": "example-key",
      "size": 5,
      "etag": "b1946ac92492d2347c6235b4d2611184",
      "version-id": "IYV3p45BT0ac8hjHg1houSdS1a.Mro8e",
      "sequencer": "617f08299329d189"
    },
    "request-id": "N4N7GDK58NMKJ12R",
    "requester": "123456789012",
    "source-ip-address": "1.2.3.4",
    "reason": "PutObject"
  }
}  

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Action": "s3:PutObject",
            "Resource": "arn:aws:s3:::cm-hirai-transcription-output/*"
        },
        {
            "Effect": "Allow",
            "Action": "s3:GetObject",
            "Resource": [
                "arn:aws:s3:::cm-hirai-transcription-output/*",
                "arn:aws:s3:::cm-hirai-audio-for-transcription/*"
            ]
        },
        {
            "Effect": "Allow",
            "Action": "transcribe:GetTranscriptionJob",
            "Resource": "arn:aws:transcribe:ap-northeast-1:xxxxxxxxxxxx:transcription-job/*"
        },
        {
            "Effect": "Allow",
            "Action": "transcribe:StartTranscriptionJob",
            "Resource": "*"
        }
    ]
}

{
  "Comment": "Audio transcription and notification workflow",
  "StartAt": "StartTranscriptionJob",
  "States": {
    "StartTranscriptionJob": {
      "Type": "Task",
      "Resource": "arn:aws:states:::aws-sdk:transcribe:startTranscriptionJob",
      "Parameters": {
        "TranscriptionJobName.$": "$$.Execution.Name",
        "LanguageCode": "ja-JP",
        "Media": {
          "MediaFileUri.$": "States.Format('s3://{}/{}', $.detail.bucket.name, $.detail.object.key)"
        },
        "OutputBucketName": "cm-hirai-transcription-output",
        "OutputKey.$": "States.Format('{}.json', $$.Execution.Name)",
        "Settings": {
          "ShowSpeakerLabels": true,
          "MaxSpeakerLabels": 2
        }
      },
      "ResultPath": "$.TranscriptionJob",
      "Next": "Wait"
    },
    "Wait": {
      "Type": "Wait",
      "Seconds": 1,
      "Next": "GetTranscriptionJob"
    },
    "GetTranscriptionJob": {
      "Type": "Task",
      "Resource": "arn:aws:states:::aws-sdk:transcribe:getTranscriptionJob",
      "Parameters": {
        "TranscriptionJobName.$": "$.TranscriptionJob.TranscriptionJob.TranscriptionJobName"
      },
      "ResultPath": "$.GetTranscriptionJobResult",
      "Next": "CheckStatus"
    },
    "CheckStatus": {
      "Type": "Choice",
      "Choices": [
        {
          "Variable": "$.GetTranscriptionJobResult.TranscriptionJob.TranscriptionJobStatus",
          "StringEquals": "COMPLETED",
          "Next": "GetTranscriptionContent"
        },
        {
          "Variable": "$.GetTranscriptionJobResult.TranscriptionJob.TranscriptionJobStatus",
          "StringEquals": "FAILED",
          "Next": "TranscriptionJobFailed"
        }
      ],
      "Default": "Wait"
    },
    "GetTranscriptionContent": {
      "Type": "Task",
      "Resource": "arn:aws:states:::aws-sdk:s3:getObject",
      "Parameters": {
        "Bucket": "cm-hirai-transcription-output",
        "Key.$": "States.Format('{}.json', $.GetTranscriptionJobResult.TranscriptionJob.TranscriptionJobName)"
      },
      "ResultSelector": {
        "Content.$": "States.StringToJson($.Body)"
      },
      "ResultPath": "$.TranscriptionContent",
      "Next": "PrepareNotification"
    },
    "PrepareNotification": {
      "Type": "Pass",
      "Parameters": {
        "subject": "【自動通知】音声ファイルの文字起こし完了",
        "message.$": "States.Format('音声ファイルが保存されましたので、文字起こし内容をお知らせいたします。\n\n■ トランスクリプションジョブ詳細\n・TranscribeジョブとStep Functionsステートマシン実行名: {}\n・音声ファイル: s3://{}/{}\n・文字起こしテキストファイル: s3://cm-hirai-transcription-output/{}.json\n\n■ 文字起こし内容\n{}\n\n■ 注意事項\n1. 上記の文字起こし内容は自動生成されたものです。正確性を要する場合は、音声ファイルの内容をご確認ください。\n2. 音声ファイルと文字起こしテキストファイルは、それぞれ指定されたS3バケット内に保存されています。必要に応じてダウンロードしてご利用ください。\n\n本通知は自動生成されています。\nご不明な点やお問い合わせは、システム管理者までご連絡ください。', $.GetTranscriptionJobResult.TranscriptionJob.TranscriptionJobName, $.detail.bucket.name, $.detail.object.key, $.GetTranscriptionJobResult.TranscriptionJob.TranscriptionJobName, $.TranscriptionContent.Content.results.transcripts[0].transcript)"
      },
      "Next": "SendNotification"
    },
    "SendNotification": {
      "Type": "Task",
      "Resource": "arn:aws:states:::sns:publish",
      "Parameters": {
        "TopicArn": "arn:aws:sns:ap-northeast-1:xxxxxxxxxxxx:cm-hirai",
        "Subject.$": "$.subject",
        "Message.$": "$.message"
      },
      "Next": "TranscriptionJobSucceeded"
    },
    "TranscriptionJobSucceeded": {
      "Type": "Succeed"
    },
    "TranscriptionJobFailed": {
      "Type": "Fail",
      "Cause": "Transcription job failed",
      "Error": "TranscriptionJobFailedException"
    }
  }
}

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "VisualEditor0",
            "Effect": "Allow",
            "Action": "sns:Publish",
            "Resource": "arn:aws:sns:ap-northeast-1:xxxxxxxxxxxx:cm-hirai"
        }
    ]
}

{
  "source": ["aws.s3"],
  "detail-type": ["Object Created"],
  "detail": {
    "bucket": {
      "name": ["cm-hirai-audio-for-transcription"]
    },
    "object": {
      "key": [{
        "suffix": ".wav"
      }]
    }
  }
}

【自動通知】音声ファイルの文字起こし完了

音声ファイルが保存されましたので、文字起こし内容をお知らせいたします。

■ トランスクリプションジョブ詳細
・TranscribeジョブとStep Functionsステートマシン実行名: ee9c2644-ab6b-4da0-80b7-203521bb751a
・音声ファイル: s3://cm-hirai-audio-for-transcription/test1.wav
・文字起こしテキストファイル: s3://cm-hirai-transcription-output/ee9c2644-ab6b-4da0-80b7-203521bb751a.json

■ 文字起こし内容
あこんにちは。もしもし？クラスメソッドテテストです

■ 注意事項
1. 上記の文字起こし内容は自動生成されたものです。正確性を要する場合は、音声ファイルの内容をご確認ください。
2. 音声ファイルと文字起こしテキストファイルは、それぞれ指定されたS3バケット内に保存されています。必要に応じてダウンロードしてご利用ください。

本通知は自動生成されています。
ご不明な点やお問い合わせは、システム管理者までご連絡ください。

--
If you wish to stop receiving notifications from this topic, please click or visit the link below to unsubscribe:
https://sns.ap-northeast-1.amazonaws.com/unsubscribe.html?SubscriptionArn=arn:aws:sns:ap-northeast-1:xxxxxxxxxxxx:cm-hirai:xxxxx&[email protected]

Please do not reply directly to this email. If you have any questions or comments regarding this email, please contact us at https://aws.amazon.com/support