ScriptSonic Text/Blog/Book Audio Converter using AWS Polly

Automated Blog/Book Audio Converter using AWS Polly and Lambda

 Objective

Develop an automated system that converts text content stored in Amazon S3 into high-quality audio using Amazon Polly. Enhance content accessibility, user engagement, and broaden your audience reach.

 Scope and Use Cases

• Accessibility: Provide audio versions for visually impaired or differently-abled users.
• Education: Enable learners to listen to educational materials anytime.
• Content Distribution: Expand reach of blogs, newsletters, and books via audio.
• User Convenience: Cater to multitaskers who prefer audio while commuting or exercising.

 System Architecture

1️⃣ Amazon S3 (Source Bucket): Stores uploaded .txt files.
2️⃣ Amazon S3 (Destination Bucket): Stores generated .mp3 audio files.
3️⃣ AWS Lambda: Triggered by S3 events to process text and call Amazon Polly.
4️⃣ Amazon Polly: Converts text to lifelike speech.
5️⃣ IAM Roles and Policies: Ensure secure permissions for Lambda to access S3 and Polly.

 Step-by-Step Implementation

AWS Account Setup

• Create a free/paid AWS account.
• Configure AWS CLI or console access for deployment.

Create Two S3 Buckets

• Source Bucket: pixel-source-bucket (for .txt uploads)
• Destination Bucket: pixel-destination-bucket (for .mp3 output)

Create IAM Policy

jsonCopyEdit{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "s3:GetObject",
        "s3:PutObject"
      ],
      "Resource": [
        "arn:aws:s3:::pixel-source-bucket/*",
        "arn:aws:s3:::pixel-destination-bucket/*"
      ]
    },
    {
      "Effect": "Allow",
      "Action": [
        "polly:SynthesizeSpeech"
      ],
      "Resource": "*"
    }
  ]
}

Name it amc-polly-lambda-policy.

Create IAM Role

• Role Name: amc-polly-lambda-role
• Attach Policies:
  • amc-polly-lambda-policy
  • AWSLambdaBasicExecutionRole

Create AWS Lambda Function

• Function Name: TextToSpeechFunction
• Runtime: Python 3.8 (or higher)
• Environment Variables:
  • SOURCE_BUCKET = pixel-source-bucket
  • DESTINATION_BUCKET = pixel-destination-bucket

Configure S3 Event Trigger

• Event Type: Object Created (PUT)
• File Filter: .txt
• Trigger Target: TextToSpeechFunction

Lambda Function Code (Optimized for SEO)

pythonCopyEditimport boto3
import os
import logging
import json

logger = logging.getLogger()
logger.setLevel(logging.INFO)

def lambda_handler(event, context):
    s3 = boto3.client('s3')
    polly = boto3.client('polly')
    source_bucket = os.environ['SOURCE_BUCKET']
    destination_bucket = os.environ['DESTINATION_BUCKET']

    text_file_key = event['Records'][0]['s3']['object']['key']
    audio_key = text_file_key.replace('.txt', '.mp3')

    try:
        logger.info(f"Fetching text file: {text_file_key}")
        text_file = s3.get_object(Bucket=source_bucket, Key=text_file_key)
        text = text_file['Body'].read().decode('utf-8')

        response = polly.synthesize_speech(
            Text=text,
            OutputFormat='mp3',
            VoiceId='Joanna'
        )

        if 'AudioStream' in response:
            temp_audio = '/tmp/audio.mp3'
            with open(temp_audio, 'wb') as file:
                file.write(response['AudioStream'].read())
            s3.upload_file(temp_audio, destination_bucket, audio_key)

        logger.info(f"Audio uploaded: {audio_key}")
        return {'statusCode': 200, 'body': json.dumps('Success')}

    except Exception as e:
        logger.error(f"Conversion failed: {e}")
        return {'statusCode': 500, 'body': json.dumps('Error')}

Testing

• Upload .txt file to pixel-source-bucket.
• Lambda triggers automatically.
• Polly converts text to .mp3.
• Audio available in pixel-destination-bucket.
• Download and test playback.

Expected Outcomes

• Fully automated text-to-speech conversion.
• Support for blogs, newsletters, and book excerpts.
• Instant audio availability for uploaded text.
• Improved accessibility and user engagement.

Future Enhancements

• Multi-language and voice support with Amazon Polly.
• API Gateway integration for on-demand conversions.
• Support for PDF/DOCX conversion to text.
• Web or mobile UI for uploads and playback.

SEO Keywords for Better Reach

• AWS Polly Text to Speech
• Convert Text to Audio AWS
• Blog to Audio Converter AWS
• Amazon Polly Lambda Integration
• AWS Serverless Text-to-Speech
• Accessibility Solutions with AWS
• Automated Audio Generation with AWS

Conclusion

The ScriptSonic AWS project demonstrates how to build an automated text-to-audio converter using Amazon S3, AWS Lambda, and Amazon Polly. It’s a scalable, accessible, and serverless solution, perfect for content creators, educators, and developers.

=