Once we have the translation text, we are going to leverage the Amazon Polly service to generate a spoken version of the translation.
Before we dive into the implementation, let's generate a short audio speech using this service with the following AWS CLI command:
$ aws polly start-speech-synthesis-task --output-format mp3 --output-s3-bucket-name <bucket> --text "testing testing 1 2 3" --voice-id Ivy{ "SynthesisTask": { "TaskId": "e68d1b6a-4b7f-4c79-9483-2b5a5932e3d1", "TaskStatus": "scheduled", "OutputUri": "https://s3.us-east-1.amazonaws.com/<bucket>/<task id>.mp3", "CreationTime": 1552754991.114, "RequestCharacters": 21, "OutputFormat": "mp3", "TextType": "text", "VoiceId": "Ivy" }}
This command has four ...
