AWS Polly Getting Started: Account, Keys, and First Request (2026)

Getting started overview

Integrating AWS Polly involves a series of steps that establish access and enable programmatic interaction with the service. This guide outlines the process from account creation and credential setup to executing a basic text-to-speech request. The primary method for interaction is through the AWS Software Development Kits (SDKs) or the AWS Command Line Interface (CLI), which abstract the underlying RESTful API calls. A foundational understanding of AWS Identity and Access Management (IAM) is beneficial for securing access to AWS services, including Polly AWS IAM overview.

Before making your first API call, you will:

1. Create an AWS account (if you don't have one).
2. Set up an IAM user with specific permissions for AWS Polly.
3. Generate access keys for the IAM user.
4. Configure your development environment with the AWS SDK or CLI.

Getting Started Quick Reference

Create an account and get keys

Accessing AWS Polly requires an AWS account and programmatic credentials. If you do not already have an AWS account, you will need to create one. This process typically involves providing an email address, password, and billing information AWS Polly product page.

Creating an IAM User

For security best practices, it is recommended to create an IAM user for programmatic access instead of using the root account credentials. This allows for granular control over permissions and reduces the risk associated with compromised credentials AWS IAM best practices.

1. Log in to the AWS Management Console as the root user or an IAM user with administrative permissions.
2. Navigate to the IAM dashboard.
3. In the navigation pane, choose Users, then select Add user.
4. Enter a User name (e.g., PollyUser).
5. For AWS access type, select Access key - Programmatic access. This generates an access key ID and secret access key.
6. Click Next: Permissions.
7. On the Set permissions page, choose Attach existing policies directly.
8. In the search box, type Polly and select the policy named AmazonPollyFullAccess. This policy grants full access to AWS Polly actions. For production environments, consider creating a custom policy with only the necessary permissions (e.g., polly:SynthesizeSpeech) AWS Polly identity-based policies.
9. Click Next: Tags (optional), then Next: Review.
10. Review the user details and click Create user.
11. On the Success page, note down the Access key ID and Secret access key. These credentials are shown only once. You will need them to configure your environment.

Configuring Credentials

After obtaining your access keys, you need to configure your development environment to use them. The AWS SDKs and CLI look for credentials in a specific order, typically starting with environment variables, shared credential files, or IAM role profiles AWS SDKs and Tools Reference Guide on credentials.

AWS CLI Configuration

If you are using the AWS CLI, run the following command and enter your access key ID, secret access key, and desired default region (e.g., us-east-1, eu-west-1):

aws configure
AWS Access Key ID [None]: YOUR_ACCESS_KEY_ID
AWS Secret Access Key [None]: YOUR_SECRET_ACCESS_KEY
Default region name [None]: us-east-1
Default output format [None]: json

Environment Variables

Alternatively, you can set environment variables. This is often used in CI/CD pipelines or temporary development setups:

export AWS_ACCESS_KEY_ID=YOUR_ACCESS_KEY_ID
export AWS_SECRET_ACCESS_KEY=YOUR_SECRET_ACCESS_KEY
export AWS_DEFAULT_REGION=us-east-1

Your first request

Once your credentials are configured, you can make your first request to AWS Polly. This example uses the AWS SDK for Python (Boto3) to synthesize speech from text and save it as an MP3 file. The AWS SDK for Python (Boto3) is a common choice for integrating with AWS services due to its extensive documentation and community support Boto3 Polly documentation.

Prerequisites for Python

1. Install Python 3.x.
2. Install Boto3: pip install boto3

Synthesize Speech Example (Python)

import boto3
import os

# Ensure your AWS credentials and region are configured (e.g., via aws configure or environment variables)

polly_client = boto3.client('polly', region_name='us-east-1') # Replace with your desired region

text_to_synthesize = "Hello, this is your first speech synthesis using AWS Polly."
output_file_name = "hello_polly.mp3"

try:
    response = polly_client.synthesize_speech(
        Text=text_to_synthesize,
        OutputFormat='mp3',
        VoiceId='Joanna' # Choose a voice, e.g., Joanna, Matthew, Salli. See AWS Polly Voices documentation.
    )

    # The audio stream is contained in the 'AudioStream' key of the response
    if "AudioStream" in response:
        with open(output_file_name, 'wb') as file:
            file.write(response['AudioStream'].read())
        print(f"Speech synthesized successfully and saved to {output_file_name}")
    else:
        print("Could not find audio stream in response.")

except Exception as e:
    print(f"Error synthesizing speech: {e}")

This script initializes the Polly client, defines the text to be spoken, and specifies the output format and voice. It then calls the synthesize_speech method and writes the returned audio stream to an MP3 file. You can play this MP3 file using any standard media player.

Common next steps

After successfully making your first request, consider these common next steps to further integrate and optimize your use of AWS Polly:

• Explore different voices and languages: AWS Polly offers a range of standard, neural, and long-form voices across multiple languages. Experiment with different VoiceId parameters to find the best fit for your application. You can find a list of available voices in the AWS Polly Voices documentation.
• Use Speech Synthesis Markup Language (SSML): For more control over speech output, such as pauses, pronunciation, and speaking rate, integrate SSML tags into your text. SSML allows for richer and more natural-sounding speech AWS Polly SSML guide.
• Integrate with other AWS services: Combine Polly with services like Amazon S3 for storing generated audio files, Amazon Transcribe for speech-to-text, or AWS Lambda for serverless audio generation. For example, you could set up a Lambda function to process text inputs and generate audio files in S3.
• Monitor usage and costs: Keep track of your character usage and understand the pricing model to manage costs effectively. AWS offers a free tier for new customers, but charges apply beyond that based on characters processed AWS Polly pricing details. Use AWS Cost Explorer to monitor your spending.
• Implement error handling and retry mechanisms: In production environments, implement robust error handling and retry logic for API calls to ensure application resilience.

Troubleshooting the first call

Encountering issues during the initial setup or first API call is common. Here are some troubleshooting steps:

• Check credentials: Verify that your AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY are correct and have not expired. Ensure they are configured in your environment variables or ~/.aws/credentials file.
• Verify IAM permissions: Confirm that the IAM user or role used has the necessary permissions (e.g., AmazonPollyFullAccess or a more specific policy like polly:SynthesizeSpeech) to interact with AWS Polly. You can check attached policies in the IAM console AWS IAM Access Analyzer.
• Region mismatch: Ensure the region specified in your code (e.g., region_name='us-east-1') matches the region where you intend to use Polly and where your credentials are valid.
• Network connectivity: Confirm that your development environment has outbound network access to the AWS Polly service endpoints. Proxy settings or firewalls can sometimes block these connections.
• SDK version: Ensure you are using a recent version of the AWS SDK. Older versions might not support certain features or have known bugs. Update your SDK (e.g., pip install --upgrade boto3).
• Error messages: Carefully read the error messages returned by the SDK or CLI. They often provide specific details about what went wrong, such as invalid parameters or authentication failures.
• AWS Service Health Dashboard: Check the AWS Service Health Dashboard for any ongoing issues with the AWS Polly service in your region.