There are more AWS SDK examples available in the [AWS Doc SDK Examples](https://github.com/awsdocs/aws-doc-sdk-examples) GitHub repo. # Scenarios for Amazon Polly using AWS SDKs The following code examples show you how to implement common scenarios in Amazon Polly with AWS SDKs. These scenarios show you how to accomplish specific tasks by calling multiple functions within Amazon Polly or combined with other AWS services. Each scenario includes a link to the complete source code, where you can find instructions on how to set up and run the code. Scenarios target an intermediate level of experience to help you understand service actions in context. **Topics** + [Convert text to speech and back to text](polly_example_cross_Telephone_section.md) + [Create a lip-sync application](polly_example_polly_LipSync_section.md) + [Create an application to analyze customer feedback](polly_example_cross_FSA_section.md) + [Getting started with Amazon Polly](polly_example_polly_GettingStarted_082_section.md) # Convert text to speech and back to text using an AWS SDK The following code example shows how to: + Use Amazon Polly to synthesize a plain text (UTF-8) input file to an audio file. + Upload the audio file to an Amazon S3 bucket. + Use Amazon Transcribe to convert the audio file to text. + Display the text. ------ #### [ Rust ] **SDK for Rust** Use Amazon Polly to synthesize a plain text (UTF-8) input file to an audio file, upload the audio file to an Amazon S3 bucket, use Amazon Transcribe to convert that audio file to text, and display the text. For complete source code and instructions on how to set up and run, see the full example on [GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/blob/main/rustv1/cross_service#code-examples). **Services used in this example** + Amazon Polly + Amazon S3 + Amazon Transcribe ------ # Create a lip-sync application with Amazon Polly using an AWS SDK The following code example shows how to create a lip-sync application with Amazon Polly. ------ #### [ Python ] **SDK for Python (Boto3)** Shows how to use Amazon Polly and Tkinter to create a lip-sync application that displays an animated face speaking along with the speech synthesized by Amazon Polly. Lip-sync is accomplished by requesting a list of visemes from Amazon Polly that match up with the synthesized speech. + Get voice metadata from Amazon Polly and display it in a Tkinter application. + Get synthesized speech audio and matching viseme speech marks from Amazon Polly. + Play the audio with synchronized mouth movements in an animated face. + Submit asynchronous synthesis tasks for long texts and retrieve the output from an Amazon Simple Storage Service (Amazon S3) bucket. For complete source code and instructions on how to set up and run, see the full example on [GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/python/example_code/polly#code-examples). **Services used in this example** + Amazon Polly ------ # Create an application that analyzes customer feedback and synthesizes audio The following code examples show how to create an application that analyzes customer comment cards, translates them from their original language, determines their sentiment, and generates an audio file from the translated text. ------ #### [ .NET ] **SDK for .NET** This example application analyzes and stores customer feedback cards. Specifically, it fulfills the need of a fictitious hotel in New York City. The hotel receives feedback from guests in various languages in the form of physical comment cards. That feedback is uploaded into the app through a web client. After an image of a comment card is uploaded, the following steps occur: + Text is extracted from the image using Amazon Textract. + Amazon Comprehend determines the sentiment of the extracted text and its language. + The extracted text is translated to English using Amazon Translate. + Amazon Polly synthesizes an audio file from the extracted text. The full app can be deployed with the AWS CDK. For source code and deployment instructions, see the project in [ GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/dotnetv3/cross-service/FeedbackSentimentAnalyzer). **Services used in this example** + Amazon Comprehend + Lambda + Amazon Polly + Amazon Textract + Amazon Translate ------ #### [ Java ] **SDK for Java 2.x** This example application analyzes and stores customer feedback cards. Specifically, it fulfills the need of a fictitious hotel in New York City. The hotel receives feedback from guests in various languages in the form of physical comment cards. That feedback is uploaded into the app through a web client. After an image of a comment card is uploaded, the following steps occur: + Text is extracted from the image using Amazon Textract. + Amazon Comprehend determines the sentiment of the extracted text and its language. + The extracted text is translated to English using Amazon Translate. + Amazon Polly synthesizes an audio file from the extracted text. The full app can be deployed with the AWS CDK. For source code and deployment instructions, see the project in [ GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javav2/usecases/creating_fsa_app). **Services used in this example** + Amazon Comprehend + Lambda + Amazon Polly + Amazon Textract + Amazon Translate ------ #### [ JavaScript ] **SDK for JavaScript (v3)** This example application analyzes and stores customer feedback cards. Specifically, it fulfills the need of a fictitious hotel in New York City. The hotel receives feedback from guests in various languages in the form of physical comment cards. That feedback is uploaded into the app through a web client. After an image of a comment card is uploaded, the following steps occur: + Text is extracted from the image using Amazon Textract. + Amazon Comprehend determines the sentiment of the extracted text and its language. + The extracted text is translated to English using Amazon Translate. + Amazon Polly synthesizes an audio file from the extracted text. The full app can be deployed with the AWS CDK. For source code and deployment instructions, see the project in [ GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/javascriptv3/example_code/cross-services/feedback-sentiment-analyzer). The following excerpts show how the AWS SDK for JavaScript is used inside of Lambda functions. ``` import { ComprehendClient, DetectDominantLanguageCommand, DetectSentimentCommand, } from "@aws-sdk/client-comprehend"; /** * Determine the language and sentiment of the extracted text. * * @param {{ source_text: string}} extractTextOutput */ export const handler = async (extractTextOutput) => { const comprehendClient = new ComprehendClient({}); const detectDominantLanguageCommand = new DetectDominantLanguageCommand({ Text: extractTextOutput.source_text, }); // The source language is required for sentiment analysis and // translation in the next step. const { Languages } = await comprehendClient.send( detectDominantLanguageCommand, ); const languageCode = Languages[0].LanguageCode; const detectSentimentCommand = new DetectSentimentCommand({ Text: extractTextOutput.source_text, LanguageCode: languageCode, }); const { Sentiment } = await comprehendClient.send(detectSentimentCommand); return { sentiment: Sentiment, language_code: languageCode, }; }; ``` ``` import { DetectDocumentTextCommand, TextractClient, } from "@aws-sdk/client-textract"; /** * Fetch the S3 object from the event and analyze it using Amazon Textract. * * @param {import("@types/aws-lambda").EventBridgeEvent<"Object Created">} eventBridgeS3Event */ export const handler = async (eventBridgeS3Event) => { const textractClient = new TextractClient(); const detectDocumentTextCommand = new DetectDocumentTextCommand({ Document: { S3Object: { Bucket: eventBridgeS3Event.bucket, Name: eventBridgeS3Event.object, }, }, }); // Textract returns a list of blocks. A block can be a line, a page, word, etc. // Each block also contains geometry of the detected text. // For more information on the Block type, see https://docs.aws.amazon.com/textract/latest/dg/API_Block.html. const { Blocks } = await textractClient.send(detectDocumentTextCommand); // For the purpose of this example, we are only interested in words. const extractedWords = Blocks.filter((b) => b.BlockType === "WORD").map( (b) => b.Text, ); return extractedWords.join(" "); }; ``` ``` import { PollyClient, SynthesizeSpeechCommand } from "@aws-sdk/client-polly"; import { S3Client } from "@aws-sdk/client-s3"; import { Upload } from "@aws-sdk/lib-storage"; /** * Synthesize an audio file from text. * * @param {{ bucket: string, translated_text: string, object: string}} sourceDestinationConfig */ export const handler = async (sourceDestinationConfig) => { const pollyClient = new PollyClient({}); const synthesizeSpeechCommand = new SynthesizeSpeechCommand({ Engine: "neural", Text: sourceDestinationConfig.translated_text, VoiceId: "Ruth", OutputFormat: "mp3", }); const { AudioStream } = await pollyClient.send(synthesizeSpeechCommand); const audioKey = `${sourceDestinationConfig.object}.mp3`; // Store the audio file in S3. const s3Client = new S3Client(); const upload = new Upload({ client: s3Client, params: { Bucket: sourceDestinationConfig.bucket, Key: audioKey, Body: AudioStream, ContentType: "audio/mp3", }, }); await upload.done(); return audioKey; }; ``` ``` import { TranslateClient, TranslateTextCommand, } from "@aws-sdk/client-translate"; /** * Translate the extracted text to English. * * @param {{ extracted_text: string, source_language_code: string}} textAndSourceLanguage */ export const handler = async (textAndSourceLanguage) => { const translateClient = new TranslateClient({}); const translateCommand = new TranslateTextCommand({ SourceLanguageCode: textAndSourceLanguage.source_language_code, TargetLanguageCode: "en", Text: textAndSourceLanguage.extracted_text, }); const { TranslatedText } = await translateClient.send(translateCommand); return { translated_text: TranslatedText }; }; ``` **Services used in this example** + Amazon Comprehend + Lambda + Amazon Polly + Amazon Textract + Amazon Translate ------ #### [ Ruby ] **SDK for Ruby** This example application analyzes and stores customer feedback cards. Specifically, it fulfills the need of a fictitious hotel in New York City. The hotel receives feedback from guests in various languages in the form of physical comment cards. That feedback is uploaded into the app through a web client. After an image of a comment card is uploaded, the following steps occur: + Text is extracted from the image using Amazon Textract. + Amazon Comprehend determines the sentiment of the extracted text and its language. + The extracted text is translated to English using Amazon Translate. + Amazon Polly synthesizes an audio file from the extracted text. The full app can be deployed with the AWS CDK. For source code and deployment instructions, see the project in [ GitHub](https://github.com/awsdocs/aws-doc-sdk-examples/tree/main/ruby/cross_service_examples/feedback_sentiment_analyzer). **Services used in this example** + Amazon Comprehend + Lambda + Amazon Polly + Amazon Textract + Amazon Translate ------ # Getting started with Amazon Polly The following code example shows how to: + Clean up resources ------ #### [ Bash ] **AWS CLI with Bash script** There's more on GitHub. Find the complete example and learn how to set up and run in the [Sample developer tutorials](https://github.com/aws-samples/sample-developer-tutorials/tree/main/tuts/082-amazon-polly-gs) repository. ``` #!/bin/bash # Amazon Polly Getting Started Script # This script demonstrates how to use Amazon Polly with the AWS CLI # Set up logging LOG_FILE="polly-tutorial.log" echo "Starting Amazon Polly tutorial at $(date)" > "$LOG_FILE" # Function to log commands and their output log_cmd() { echo "Running: $1" | tee -a "$LOG_FILE" eval "$1" 2>&1 | tee -a "$LOG_FILE" return ${PIPESTATUS[0]} } # Function to check for errors check_error() { if echo "$1" | grep -i "error" > /dev/null; then echo "ERROR detected in output. Exiting script." | tee -a "$LOG_FILE" echo "$1" | tee -a "$LOG_FILE" exit 1 fi } # Function to handle errors and cleanup handle_error() { echo "Error occurred. Attempting cleanup..." | tee -a "$LOG_FILE" cleanup exit 1 } # Function to clean up resources cleanup() { echo "" | tee -a "$LOG_FILE" echo "===========================================================" | tee -a "$LOG_FILE" echo "CLEANUP PROCESS" | tee -a "$LOG_FILE" echo "===========================================================" | tee -a "$LOG_FILE" # Delete lexicon if it exists if [ -n "$LEXICON_NAME" ]; then echo "Deleting lexicon: $LEXICON_NAME" | tee -a "$LOG_FILE" log_cmd "aws polly delete-lexicon --name $LEXICON_NAME" fi echo "Cleanup complete." | tee -a "$LOG_FILE" } # Trap errors trap 'handle_error' ERR # Step 1: Verify Amazon Polly is available echo "Step 1: Verifying Amazon Polly availability" | tee -a "$LOG_FILE" POLLY_CHECK=$(aws polly help 2>&1) if echo "$POLLY_CHECK" | grep -i "not.*found\|invalid\|error" > /dev/null; then echo "Amazon Polly is not available in your AWS CLI installation." | tee -a "$LOG_FILE" echo "Please update your AWS CLI to the latest version." | tee -a "$LOG_FILE" exit 1 else echo "Amazon Polly is available. Proceeding with tutorial." | tee -a "$LOG_FILE" fi # Step 2: List available voices echo "" | tee -a "$LOG_FILE" echo "Step 2: Listing available voices" | tee -a "$LOG_FILE" log_cmd "aws polly describe-voices --language-code en-US --output text --query 'Voices[0:3].[Id, LanguageCode, Gender]'" # Step 3: Basic text-to-speech conversion echo "" | tee -a "$LOG_FILE" echo "Step 3: Converting text to speech" | tee -a "$LOG_FILE" log_cmd "aws polly synthesize-speech --output-format mp3 --voice-id Joanna --text \"Hello, welcome to Amazon Polly. This is a sample text to speech conversion.\" output.mp3" if [ -f "output.mp3" ]; then echo "Successfully created output.mp3 file." | tee -a "$LOG_FILE" echo "You can play this file with your preferred audio player." | tee -a "$LOG_FILE" else echo "Failed to create output.mp3 file." | tee -a "$LOG_FILE" exit 1 fi # Step 4: Using SSML for enhanced speech echo "" | tee -a "$LOG_FILE" echo "Step 4: Using SSML for enhanced speech" | tee -a "$LOG_FILE" log_cmd "aws polly synthesize-speech --output-format mp3 --voice-id Matthew --text-type ssml --text \"Hello! This is a sample of SSML enhanced speech.\" ssml-output.mp3" if [ -f "ssml-output.mp3" ]; then echo "Successfully created ssml-output.mp3 file." | tee -a "$LOG_FILE" echo "You can play this file with your preferred audio player." | tee -a "$LOG_FILE" else echo "Failed to create ssml-output.mp3 file." | tee -a "$LOG_FILE" exit 1 fi # Step 5: Working with lexicons echo "" | tee -a "$LOG_FILE" echo "Step 5: Working with lexicons" | tee -a "$LOG_FILE" # Generate a random identifier for the lexicon (max 20 chars, alphanumeric only) LEXICON_NAME="example$(openssl rand -hex 6)" echo "Using lexicon name: $LEXICON_NAME" | tee -a "$LOG_FILE" # Create a lexicon file echo "Creating lexicon file..." | tee -a "$LOG_FILE" cat > example.pls << 'EOF' AWS Amazon Web Services EOF # Upload the lexicon echo "Uploading lexicon..." | tee -a "$LOG_FILE" log_cmd "aws polly put-lexicon --name $LEXICON_NAME --content file://example.pls" # List available lexicons echo "Listing available lexicons..." | tee -a "$LOG_FILE" log_cmd "aws polly list-lexicons --output text --query 'Lexicons[*].[Name]'" # Get details about the lexicon echo "Getting details about the lexicon..." | tee -a "$LOG_FILE" log_cmd "aws polly get-lexicon --name $LEXICON_NAME --output text --query 'Lexicon.Name'" # Use the lexicon when synthesizing speech echo "Using the lexicon for speech synthesis..." | tee -a "$LOG_FILE" log_cmd "aws polly synthesize-speech --output-format mp3 --voice-id Joanna --lexicon-names $LEXICON_NAME --text \"I work with AWS every day.\" lexicon-output.mp3" if [ -f "lexicon-output.mp3" ]; then echo "Successfully created lexicon-output.mp3 file." | tee -a "$LOG_FILE" echo "You can play this file with your preferred audio player." | tee -a "$LOG_FILE" else echo "Failed to create lexicon-output.mp3 file." | tee -a "$LOG_FILE" exit 1 fi # Summary of created resources echo "" | tee -a "$LOG_FILE" echo "===========================================================" | tee -a "$LOG_FILE" echo "TUTORIAL SUMMARY" | tee -a "$LOG_FILE" echo "===========================================================" | tee -a "$LOG_FILE" echo "Created resources:" | tee -a "$LOG_FILE" echo "1. Lexicon: $LEXICON_NAME" | tee -a "$LOG_FILE" echo "2. Audio files:" | tee -a "$LOG_FILE" echo " - output.mp3" | tee -a "$LOG_FILE" echo " - ssml-output.mp3" | tee -a "$LOG_FILE" echo " - lexicon-output.mp3" | tee -a "$LOG_FILE" echo "" | tee -a "$LOG_FILE" # Prompt for cleanup echo "" | tee -a "$LOG_FILE" echo "===========================================================" | tee -a "$LOG_FILE" echo "CLEANUP CONFIRMATION" | tee -a "$LOG_FILE" echo "===========================================================" | tee -a "$LOG_FILE" echo "Do you want to clean up all created resources? (y/n): " | tee -a "$LOG_FILE" read -r CLEANUP_CHOICE if [[ "$CLEANUP_CHOICE" =~ ^[Yy] ]]; then cleanup else echo "Skipping cleanup. Resources will remain in your account." | tee -a "$LOG_FILE" echo "To manually delete the lexicon later, run:" | tee -a "$LOG_FILE" echo "aws polly delete-lexicon --name $LEXICON_NAME" | tee -a "$LOG_FILE" fi echo "" | tee -a "$LOG_FILE" echo "Tutorial completed successfully!" | tee -a "$LOG_FILE" echo "Log file: $LOG_FILE" | tee -a "$LOG_FILE" ``` + For API details, see the following topics in *AWS CLI Command Reference*. + [DeleteLexicon](https://docs.aws.amazon.com/goto/aws-cli/polly-2016-06-10/DeleteLexicon) + [DescribeVoices](https://docs.aws.amazon.com/goto/aws-cli/polly-2016-06-10/DescribeVoices) + [GetLexicon](https://docs.aws.amazon.com/goto/aws-cli/polly-2016-06-10/GetLexicon) + [Help](https://docs.aws.amazon.com/goto/aws-cli/polly-2016-06-10/Help) + [ListLexicons](https://docs.aws.amazon.com/goto/aws-cli/polly-2016-06-10/ListLexicons) + [PutLexicon](https://docs.aws.amazon.com/goto/aws-cli/polly-2016-06-10/PutLexicon) + [SynthesizeSpeech](https://docs.aws.amazon.com/goto/aws-cli/polly-2016-06-10/SynthesizeSpeech) ------