Free tools Windows power users keep installed
One-click scans. No signup required.
Amazon Polly is AWS’s managed text-to-speech service. You send it text, choose a voice, engine, and output format, and it returns synthesized speech audio. It reads the text aloud in the language of the voice you pick. It does not translate, so Polly is not the tool to use if you need one language turned into another before it is spoken.
AWS’s own documentation puts it this way: “Amazon Polly converts input text into life-like speech.” (How Amazon Polly works, AWS documentation) That sentence describes the product. The details that decide whether it suits your project, including which engine you can use, which Regions support it, and what it costs at your volume, are covered below.
As an Amazon Associate I earn from qualifying purchases.
This guide is based on AWS’s published documentation. It is not a report from hands-on listening tests, so check the live AWS tables before you commit to a voice or Region.
How a Polly request works
Every synthesis request answers the same few questions: what text should be spoken, whether that text is plain or SSML markup, which voice should speak it, which engine should generate it, and what audio format should come back. Polly returns a speech audio stream in the format you asked for.
#1 Best Overall
- Your favorite music and content – Play music, audiobooks, and podcasts from Amazon Music, Apple Music, Spotify and others or via Bluetooth throughout your home.
- Alexa is happy to help – Ask Alexa for weather updates and to set hands-free timers, get answers to your questions and even hear jokes. Need a few extra minutes in the morning? Just tap your Echo Dot to snooze your alarm.
- Keep your home comfortable – Control compatible smart home devices with your voice and routines triggered by built-in motion or indoor temperature sensors. Create routines to automatically turn on lights when you walk into a room, or start a fan if the inside temperature goes above your comfort zone.
- Do more with device pairing – Fill your home with music using compatible Echo devices in different rooms, or create a home theatre system with Fire TV.
- Say goodbye to drop-offs and buffering - With eero Built-in, Echo Dot doubles as a mesh wifi extender, adding up to 1,000 sq. ft. of wifi coverage to your existing eero network.
- Choose the text and its type. Send plain text, or send SSML (Speech Synthesis Markup Language) if you need to control pronunciation, pauses, volume, pitch, or speaking rate.
- Choose a voice ID. The voice determines the language and accent of the output. A voice that speaks English will read Spanish text with English pronunciation, so match the voice to the content.
- Choose an engine. The engine sets the synthesis approach and affects which voices, features, and Regions are available. More on this below.
- Choose an output format. The format determines the file type and sample quality you receive, and it should match where the audio will be played or sent.
- Receive the audio stream and either save it, play it in an application, or pass it to a telephony or other pipeline.
In the AWS API these map to the request fields Text, TextType (text or ssml), VoiceId, Engine, and OutputFormat. Check the SynthesizeSpeech API reference for the exact field names and any optional parameters before you write code against them.
Output formats
AWS documents MP3 and Ogg Vorbis for application playback, which is the usual choice for audio that a listener will hear in an app or on a website. For other uses, AWS documents PCM and telephony formats. PCM is uncompressed and suits audio that another system will process further. Telephony formats suit phone systems and interactive voice response. Pick the format before you build playback code, because changing it later means changing the handling downstream.
Rank #2
- Your favorite music and content – Play music, audiobooks, and podcasts from Amazon Music, Apple Music, Spotify and others or via Bluetooth throughout your home.
- Alexa is happy to help – Ask Alexa for weather updates and to set hands-free timers, get answers to your questions and even hear jokes. Need a few extra minutes in the morning? Just tap your Echo Dot to snooze your alarm.
- Keep your home comfortable – Control compatible smart home devices with your voice and routines triggered by built-in motion or indoor temperature sensors. Create routines to automatically turn on lights when you walk into a room, or start a fan if the inside temperature goes above your comfort zone.
- Do more with device pairing – Fill your home with music using compatible Echo devices in different rooms, or create a home theatre system with Fire TV.
- Say goodbye to drop-offs and buffering - With eero Built-in, Echo Dot doubles as a mesh wifi extender, adding up to 1,000 sq. ft. of wifi coverage to your existing eero network.
Engines and voices
The API reference lists four engine values: standard, neural, long-form, and generative. AWS describes Standard and Neural as distinct synthesis approaches, and it documents that voice availability and supported features differ between them. The table below shows what the sources establish and where you still have to check.
PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware match| Engine value | What AWS documentation establishes | What to check before you use it |
|---|---|---|
standard |
A distinct synthesis approach with its own voice list and feature support. | Confirm that your chosen voice and the SSML tags you need are supported for this engine in your Region. |
neural |
A distinct synthesis approach from Standard, with its own voice list and feature support. Priced separately (see the pricing section). | Confirm voice, language, and Region availability in AWS’s live tables. Confirm the price on the AWS pricing page. |
long-form |
Listed as an engine value in the API reference. | Not stated in the sources reviewed for this guide: its supported voices, Regions, and intended content length. Check the Polly voice and Region documentation. |
generative |
Listed as an engine value. Generative voice availability is limited by AWS Region, and some SSML tags are not supported. | Confirm the Region you need is on AWS’s generative-voice list, and test the SSML you plan to use, since some tags will not work. |
The practical point is that engine, voice, and Region are tied together. A voice you like in one Region may not be offered in yours, and an engine that supports the SSML you want may not offer the voice you need. Do not assume that every voice and feature is available everywhere. Use AWS’s live voice and Region tables for your specific deployment, and check them again before launch, because availability can change.
Rank #3
- Meet Echo Dot Max: Experience rich room-filling sound that automatically adapts to your space and fine-tunes playback. Features a built-in smart home hub and Omnisense technology for highly personalized experiences.
- Music to your ears: With nearly 3x the bass versus Echo Dot (2022 release), it fits beautifully in any space, delivering your personal sound stage with deep bass and enhanced clarity. Listen to streaming services, such as Amazon Music, Apple Music, Spotify, and SiriusXM. Encore!
- Do more with device pairing: Connect compatible Echo smart speakers and smart displays in different rooms, or pair with a second Echo Dot Max to enjoy even richer sound
- Simple smart home control: Set routines, pair and control lights, locks, and thousands of smart home devices that work with Alexa without needing a separate smart home hub. With Omnisense technology, you can activate routines via temperature or presence detection.
- Say goodbye to drop-offs and buffering - With eero Built-in, Echo Dot Max doubles as a mesh wifi extender, adding up to 1,000 sq. ft. of wifi coverage to your existing eero network.
SSML and what it controls
SSML gives the author control over how text is spoken. AWS documents control over aspects such as pronunciation, volume, pitch, and speech rate. That control depends on the engine. An SSML tag that works with one engine may be ignored or rejected by another, so write your markup against the engine you will actually deploy, not the one you tested first.
Consistency across a long-running series
Generative voices can sound slightly different over time. AWS’s generative-voice documentation says that updates to the model or its training data may cause small changes in how a voice sounds. For a podcast, an audiobook, or a course that is produced in batches over months, this can mean the later episodes do not sound quite like the early ones.
Rank #4
- Your favorite music and content – Play music, audiobooks, and podcasts from Amazon Music, Apple Music, Spotify and others or via Bluetooth throughout your home.
- Alexa is happy to help – Ask Alexa for weather updates and to set hands-free timers, get answers to your questions and even hear jokes. Need a few extra minutes in the morning? Just tap your Echo Dot to snooze your alarm.
- Keep your home comfortable – Control compatible smart home devices with your voice and routines triggered by built-in motion or indoor temperature sensors. Create routines to automatically turn on lights when you walk into a room, or start a fan if the inside temperature goes above your comfort zone.
- Do more with device pairing – Fill your home with music using compatible Echo devices in different rooms, or create a home theatre system with Fire TV.
- Say goodbye to drop-offs and buffering - With eero Built-in, Echo Dot doubles as a mesh wifi extender, adding up to 1,000 sq. ft. of wifi coverage to your existing eero network.
AWS’s AI service card also notes that engines and voices can respond differently to the same input. A sentence that sounds natural in one voice may sound stilted in another. If consistency matters, synthesize a representative sample of your real content, listen to it, and keep a human review step for generated output before it is published.
Do these 3 things before closing this tab:
1Fix the driver behind crashes, sound loss and screen glitches2Clear out junk files and repair common Windows errors3Scan for outdated or missing drivers - takes under a minutePricing
Polly is a usage-priced cloud service. You pay for the characters you synthesize, and the rate depends on the engine. A 2026 snapshot of AWS’s pricing page listed $19.20 per one million characters for Neural speech and Speech Marks requests outside the free tier. Treat that as a point-in-time figure rather than a current quote. Before you budget, check the AWS pricing page for the current rate, your free-tier eligibility, and the rate for the engine and Region you plan to use.
Best Value
- MEET ECHO SPOT - A sleek smart alarm clock with Alexa and big vibrant sound. Ready to help you wake up, wind down, and so much more.
- CUSTOMIZABLE SMART CLOCK - See time, weather, and song titles at a glance, control smart home devices, and more. Personalize your display with your favorite clock face and fun colors.
- BIG VIBRANT SOUND - Enjoy rich sound with clear vocals and deep bass. Just ask Alexa to play music, podcasts, and audiobooks. See song titles and touch to control your music.
- EASE INTO THE DAY - Set up an Alexa routine that gently wakes you with music and gradual light. Glance at the time, check reminders, or ask Alexa for weather updates.
- KEEP YOUR HOME COMFORTABLE - Control compatible smart home devices. Just ask Alexa to turn on lights or touch the screen to dim. Create routines that use motion detection to turn down the thermostat as you head out or open the blinds when you walk into a room.
To estimate cost, count the characters you will send per month, including the SSML markup itself, then multiply by the rate for your engine. For example, at the snapshot rate, one million characters would cost $19.20 before any free-tier allowance, and ten million would cost $192.00. These figures are arithmetic on the snapshot rate, not a forecast for your account.
The sources reviewed for this guide did not provide a complete price comparison across every engine, so compare engines directly on the pricing page rather than relying on a single number.
A first-test checklist
- Match the voice language and engine to the content and to the Region where the request will run.
- Test names, numbers, abbreviations, dates, and punctuation from your real content, since these are where synthesized speech most often sounds wrong.
- Confirm that every SSML tag you plan to use is supported by your chosen engine.
- Choose the output format that matches your playback or integration path.
- Synthesize a sample from each voice you are considering, and listen to the whole sample rather than the opening sentence.
- Check the current price for your expected character volume before you launch.
Bottom line
Use Amazon Polly when you need reliable speech generated from text inside an application, a pipeline, or a telephony system, and when you can accept the voice, engine, and Region limits that AWS publishes. Polly is a good fit for content you can test in advance. It is a poor fit if you need translation, or if you need a single voice to sound identical across a long series without a listening check. Confirm the live voice, Region, SSML, and pricing details on AWS’s pages before you build.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
The Bottom Line
Use Amazon Polly when you need speech generated from text inside an application, a pipeline, or a telephony system, and when you can accept the voice, engine, and Region limits AWS publishes. Confirm the live voice, Region, SSML, and pricing details on AWS’s pages before you build.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
