asmitabudhiraja

How to Convert Text to Speech Using Amazon Polly

Text-to-Speech (TTS) technology has become a powerful feature in modern applications — from voice assistants and chatbots to accessibility tools and e-learning platforms. Amazon Polly, a fully managed AWS service, allows developers to convert text into lifelike speech using advanced neural voices.

What is Amazon Polly?

Amazon Polly is a cloud-based service that transforms text into natural-sounding speech. It supports multiple languages and offers both Standard and Neural voices.

The basic workflow looks like this:

Text → Amazon Polly → Audio File (MP3, WAV, OGG)

Polly can generate speech files for:

  • IVR systems
  • E-learning content
  • AI chatbots
  • Accessibility features
  • SaaS products

Step 1: Configure AWS

Before using Polly, configure AWS credentials:

aws configure

Provide:

  • Access Key
  • Secret Key
  • Default region
  • Output format

To verify your identity:

aws sts get-caller-identity

Method 1: Convert Text to Speech Using AWS CLI

The fastest way to test Polly is via the CLI.

aws polly synthesize-speech \
  --text "Hello, welcome to Amazon Polly." \
  --output-format mp3 \
  --voice-id Joanna \
  output.mp3

This generates an output.mp3 file in your directory.

List Available Voices

aws polly describe-voices

Use Neural Voice (Higher Quality)

--engine neural

Neural voices provide more natural intonation and human-like delivery.

Method 2: Using Node.js

Install AWS SDK

npm install @aws-sdk/client-polly

Example Code

import { PollyClient, SynthesizeSpeechCommand } from "@aws-sdk/client-polly";
import fs from "fs";const client = new PollyClient({ region: "us-east-1" });const params = {
  OutputFormat: "mp3",
  Text: "Welcome to our platform.",
  VoiceId: "Joanna"
};const command = new SynthesizeSpeechCommand(params);
const response = await client.send(command);fs.writeFileSync("speech.mp3", response.AudioStream);

This approach is ideal for backend services and APIs.

Method 3: Using .NET

For .NET developers, Polly integrates seamlessly with the AWS SDK.

Install the Package

dotnet add package AWSSDK.Polly

Example Code

using Amazon;
using Amazon.Polly;
using Amazon.Polly.Model;
using System.IO;
using System.Threading.Tasks;class Program
{
    static async Task Main()
    {
        var client = new AmazonPollyClient(RegionEndpoint.USEast1);        var request = new SynthesizeSpeechRequest
        {
            Text = "Hello from Amazon Polly",
            OutputFormat = OutputFormat.Mp3,
            VoiceId = VoiceId.Joanna
        };        var response = await client.SynthesizeSpeechAsync(request);        using (var fileStream = File.Create("speech.mp3"))
        {
            await response.AudioStream.CopyToAsync(fileStream);
        }
    }
}

This is ideal for enterprise backend systems and microservices.

Advanced Feature: SSML (Speech Control)

Polly supports SSML (Speech Synthesis Markup Language), which lets you control tone, pauses, emphasis, and pronunciation.

Example:

aws polly synthesize-speech \
  --text-type ssml \
  --text "<speak>Hello <break time='500ms'/> World</speak>" \
  --voice-id Joanna \
  --output-format mp3 \
  output.mp3

With SSML, you can:

  • Add pauses
  • Adjust speaking rate
  • Emphasize words
  • Modify pitch
  • Spell out acronyms

This is especially useful for production-grade applications.

Leave a comment