What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Amazon Polly turns written text into spoken audio through AWS’s cloud service. You can make a first sample in the Polly console or from the AWS CLI, then add markup and output choices as your needs grow. This guide follows AWS’s Polly documentation. It is not a hands-on benchmark, so confirm voice and feature details for your own account and AWS Region before you build on them.
How Polly turns text into speech
A Polly request has three inputs and one output. The inputs are the text, which can be plain text or SSML; a selected voice, which runs on one of Polly’s engines; and synthesis settings. The output is a speech audio stream in the format you choose, as described in How Amazon Polly works.
As an Amazon Associate I earn from qualifying purchases.
Two boundaries matter from the start. Polly speaks the language associated with the voice you pick; it does not translate your text. And the set of voices and features is not fixed. Availability depends on the engine and the AWS Region, so check the current catalog before you build a workflow around a specific voice.
The Tool Desk
Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →Your first sample in the console
Start with ordinary text so you have a baseline before you add any markup. An AWS account is required first, and the getting started guide covers initial setup.
#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.
- Sign in to your AWS account and open the Amazon Polly console.
- Enter a short paragraph of plain text.
- Choose a language and a voice. Note which engine the voice uses, because the engine determines which features apply to it.
- Listen to the result in the console. If it does not read the way you want, edit the text and synthesize again.
- Save the audio file in the output format you need.
The same sample from the command line
AWS says the console and CLI cover almost the same operations. The main difference is playback: the CLI cannot play speech for you, so you save the output file and open it in an audio application. The command below uses the synthesize-speech operation with the neural engine and the Joanna voice. Confirm that your chosen voice supports the engine you name, and check the catalog for a valid pairing if the request fails.
aws polly synthesize-speech
--engine neural
--voice-id Joanna
--output-format mp3
--text "Welcome to my first Polly sample."
welcome.mp3For application code, AWS recommends using an SDK, because the SDK handles authenticated requests for you.
Shape delivery with SSML
Plain text gets you a working voice. SSML (Speech Synthesis Markup Language) lets you control how that voice reads. Wrap the document in a <speak> element. Polly supports a subset of the W3C SSML 1.1 recommendation. When you send SSML from the CLI, add --text-type ssml to the command.
Quick wins for a faster PC:
Repair Windows errors before they cause bigger problemsFix Now →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Clear out junk files and repair common Windows errorsFree Scan →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.
<speak>
Your order <break time="500ms"/> number is <prosody rate="slow">4 2 7 9</prosody>.
</speak>Controls you can use
According to Generating speech from SSML documents, SSML can guide:
- Pronunciation, including phonetic pronunciation
- Volume, pitch, and pace
- Pauses and emphasis
- Breathing sounds and whispering
Check tag support for your engine
Supported tags differ by engine. Before you rely on a tag, check the tag compatibility for the engine you selected in the SSML documentation and the speech mark types reference.
Choose an output format for the place it will play
Polly can return several formats. Choose based on where the audio will play, not on a single format that is best for everything, as explained in How Amazon Polly works.
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.
- MP3 and Ogg Vorbis: compressed audio files for ordinary playback.
- Raw PCM: uncompressed audio for software that processes the samples directly.
- Mu-law and A-law: formats AWS identifies for telephony applications.
Engines and voices
AWS documents four engines: standard, neural, long-form, and generative. The table shows only the feature differences that AWS states in the voice documentation. Where a source does not state a value, the table says so.
Do these 3 things before closing this tab:
1Scan for outdated or missing drivers - takes under a minute2Clear out junk files and repair common Windows errors3Fix the driver behind crashes, sound loss and screen glitches| Engine | Speech marks | Newscaster style | Notes |
|---|---|---|---|
| Standard | Not stated; see Standard voices | Not stated; see Standard voices | Voice list and feature support vary by Region |
| Neural | Supported; see Neural voices | Supported | Voice list and feature support vary by Region |
| Long-form | Not stated; see Amazon Polly voice engines | Not stated; see Amazon Polly voice engines | Intended for longer-form content, per the engine overview |
| Generative | Not currently supported; see Generative voices | Not supported | Model updates may slightly change how a voice sounds over time |
Because the feature set changes by engine and Region, treat the table as a starting checklist. Confirm the current status for your exact voice before you commit to a production workflow.
Speech marks are metadata, not audio
Speech marks describe timing inside a spoken passage. They are JSON metadata, and a speech mark request does not generate audio. They identify:
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.
- Sentence and word boundaries
- Visemes, the mouth shapes that correspond to phonemes
- SSML
<mark>elements
Speech marks are useful when you want text highlighting or animation to follow the speech. The request method is described in Requesting speech marks. Generative voices do not support speech marks, so if you need them, choose a neural or standard voice.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Keep voices consistent across recordings
AWS notes that updates to generative models may slightly change how a voice sounds over time, as described in Generative voices. This matters if you combine recordings made months apart, such as podcast episodes. Before a long run, generate a short representative sample, compare it with earlier episodes, and keep that comparison in your production checklist.
Cost and access
You need an AWS account to use Polly. AWS says new customers can get started with Polly at no charge, and that charges apply to the services and resources you use. Polly charges for the text it synthesizes, and cached replay has no additional charge, according to What Is Amazon Polly? This article does not list per-character rates or free-tier allowances. Check AWS’s current Polly pricing page before you estimate a budget, because those figures change.
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.
Questions to answer before you choose an approach
- How much voice quality and style does the project need?
- Is the language and voice you want available in your Region?
- Do you need speech marks or SSML tags that your candidate engine supports?
- Where will the audio play, and which output format does that environment accept?
- How much text will you synthesize, and what will that cost at current pricing?
Begin with the feature you cannot give up, such as speech marks or a particular style, and narrow the engine from there.
Where Polly fits
AWS lists several application areas for Polly, including:
- Reading an article aloud
- Generating game dialogue
- Adding narration to an e-learning lesson
- Supporting an accessibility feature
- Creating spoken output for an IoT application
These are use-case examples. Polly generates speech, but your application still needs its own content, storage, and playback logic.
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.
