Polly - Service to convert Text to Audio
Polly_TextToVoice - An action to convert text to Audio
Inputs:
AmazonToken - Access Key and Access Secret that you define for your IAM user on AWS console. This user needs to have permission to Polly services.
AWSRegionId - Static Values for the AWS Region where you want to use the service. You can also pass the Region as text (the column Region)
TextToConvert - The text you want to convert to audio
TargetLanguageCode - The language code of the voice you want reading the text.
VoiceId - The name of the voice you want to read the text. Needs to align with the Target language code selected . You can consult the available voices in here.
Transcribe - A service to convert audio to text
This service converts audio files store in a S3 bucket storing the result in an output S3 bucket. In this integration we are using the same bucket to pick the audio from and store the result. You can customize the behavior by changing the integration from the component
Transcribe_Wrapper - This action trigger a new Transcribe job. Returns the name of the JSON result stored in the S3 bucket
FileName - The file name of the audio file you want to transcribe. This file must exist on the Bucket defined in Bucket Name
BucketName - Bucket name to pick the audio from and to store the result json
TargetLanguageCode - The language code of the language talked in the audio.
TranscribeJobName - The name you want to give to the transcribe job identifiable on the Transcribe console on AWS.
Translate - Service to translate text from one language to another.
Translate_Wrapper - Action to translate text.
toTranslate - Text you want to translate
sourceLanguageCode - The original text language code
targetLanguageCode - The language you want to translate the text to.
In this component we also include some actions from S3 to manage buckets so we can upload files to an S3 bucket in order to have them transcribed. Also to get the result Transcription JSON from the bucket