In the Universal Translator, we are going to translate spoken words from one language to another. The first step of this translation process is to know which words were spoken. For this, we are going to use the Amazon Transcribe service. Amazon Transcribe uses deep learning based Automatic Speech Recognition (ASR) algorithms to generate text from speech.
Let's use the AWS CLI to understand how the Transcribe service works. Issue the following command to start a transcription:
$ aws transcribe start-transcription-job --transcription-job-name <jobname> --language-code en-US --media-format wav --media MediaFileUri=https://s3.amazonaws.com/contents.aws.a/<audio file>.wav --output-bucket-name contents.aws.a ...
