{"id":1097,"date":"2021-10-28T08:40:22","date_gmt":"2021-10-28T08:40:22","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2021\/10\/28\/optimize-your-budget-and-time-by-submitting-amazon-polly-voice-synthesis-tasks-in-bulk\/"},"modified":"2021-10-28T08:40:22","modified_gmt":"2021-10-28T08:40:22","slug":"optimize-your-budget-and-time-by-submitting-amazon-polly-voice-synthesis-tasks-in-bulk","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2021\/10\/28\/optimize-your-budget-and-time-by-submitting-amazon-polly-voice-synthesis-tasks-in-bulk\/","title":{"rendered":"Optimize your budget and time by submitting Amazon Polly voice synthesis tasks in bulk"},"content":{"rendered":"
\n

Amazon Polly<\/a> is a service that turns text into natural-sounding speech, using dozens of voices in more than 30 languages. You can use it for all sorts of applications, ranging from talking animated avatars, to lifelike virtual agents that answer customer support requests, to automated newscasters reading stories aloud. You can have Amazon Polly return synthesized speech as a live stream, or download it as a standard audio file for playback later. Like many AWS services, you pay only for what you actually use: with Amazon Polly, you pay for the number of characters in the synthesized phrase<\/a>. Just playing a saved audio file is free, whether you play it a single time or multiple times.<\/p>\n

If you know exactly which phrases you need ahead of time, you can optimize your AWS spend. Just take every phrase you need voiced and send it to Amazon Polly at build time, storing the generated audio file until you\u2019re ready to play it back at runtime. Common use cases for this approach include public address systems at airports or bus stations, video games, and quick-service restaurant automated order-takers. Just pay once to synthesize your text, and then replay the resulting audio files as needed for free.<\/p>\n

In this post, we share a fully automated, event-driven, serverless solution that you can use to turn large numbers of text phrases to lifelike speech asynchronously. You can trigger the jobs by manually uploading a file of phrases to a private Amazon Simple Storage Service<\/a> (Amazon S3) bucket, and then be notified by email or instant message when they\u2019re ready. Or, make the process part of your AWS CodeBuild<\/a> continuous integration system, by automatically triggering the synthesis work whenever your source phrases change.<\/p>\n

Overview of the solution<\/h2>\n

The solution is fully serverless, consisting chiefly of a set of AWS Lambda<\/a> functions. These functions track the items to be synthesized. Submit them to Amazon Polly for synthesis, and process the results as they\u2019re completed. The functions use shared Amazon DynamoDB<\/a> tables to manage the state of the work over time. An AWS Step Functions<\/a> workflow tracks each submitted set, and notifies interested parties of its completion via an Amazon Simple Notification Service<\/a> (Amazon SNS) topic.<\/p>\n

The solution employs an event-driven architecture<\/a>: rather than a single process running from beginning to end, the process is distributed across Lambda invocations, run only when triggered to do so from some event.<\/p>\n

The following diagram illustrates the solution architecture.<\/p>\n

\"\"<\/p>\n

Deploy and configure the solution<\/h2>\n

You deploy the solution into your AWS account using the AWS Serverless Application Model<\/a> (AWS SAM). You can do this from any computer with command line access to your account, but for the sake of simplicity, we use AWS CloudShell<\/a>.<\/p>\n

    \n
  1. Sign in to the CloudShell console.<\/li>\n
  2. When your shell has been initialized, make a local copy of the solution source code and prepare the AWS SAM stack by issuing the following commands:<\/li>\n<\/ol>\n
    \n
    $ git clone https:\/\/github.com\/aws-samples\/amazon-polly-async-batch.git\n$ cd amazon-polly-async-batch\n$ sam build\n<\/code><\/pre>\n<\/p><\/div>\n
      \n
    1. Use AWS SAM to deploy the solution, with deploy \u2013guided. Provide a stack name (like amazon-polly-async-batch<\/code>), your preferred Region, an email address for notifications, and the name of a non-existent S3 bucket for the generated audio files. Accept the other defaults.<\/li>\n<\/ol>\n
      \n
      $ sam deploy --guided\n        Setting default arguments for 'sam deploy'\n        =========================================\n        Stack Name [amazon-polly-async-batch]: \n        AWS Region [us-east-1]: \n        Parameter NotificationEmail []: *YOUR EMAIL ADDRESS*\n        Parameter WorkBucket []: *YOUR WORK BUCKET NAME*\n        #Shows you resources changes to be deployed and require a 'Y' to initiate deploy\n        Confirm changes before deploy [y\/N]:  \n        #SAM needs permission to be able to create roles to connect to the resources in your template\n        Allow SAM CLI IAM role creation [Y\/n]:  \n        Save arguments to configuration file [Y\/n]: \n        SAM configuration file [samconfig.toml]: \n        SAM configuration environment [default]: \n<\/code><\/pre>\n<\/p><\/div>\n
      Deployment of all the components should take only a few minutes. If installation is successful, you should see a message like the following:<\/p>\n
      \n
      Successfully created\/updated stack - amazon-polly-async-batch in us-east-1<\/code><\/pre>\n<\/p><\/div>\n
        \n
      1. Check your email for a message from Amazon SNS and confirm the subscription.<\/li>\n<\/ol>\n
        How the solution works<\/h2>\n
        In this section, we describe in detail how to use the solution to synthesize your text, and how each major component works.<\/p>\n
        The set file: Specifying the text to synthesize<\/h3>\n
        You define the set of text phrases you want Amazon Polly to voice in a file named a set file<\/em>. This is a YAML file<\/a> consisting of the set details, a collection of defaults, and a list of items to synthesize:<\/p>\n