Amazon Polly FAQs

Amazon Polly is a service that turns text into lifelike speech. Amazon Polly enables existing applications to speak as a first class feature and creates the opportunity for entirely new categories of speech-enabled products, from mobile apps and cars, to devices and appliances. Amazon Polly includes dozens of lifelike voices and support for multiple languages, so you can select the ideal voice and distribute your speech-enabled applications in many geographies. Amazon Polly is easy to use – you just send the text you want converted into speech to the Amazon Polly API, and Amazon Polly immediately returns the audio stream to your application so you can play it directly or store it in a standard audio file format, such as MP3. Amazon Polly supports Speech Synthesis Markup Language (SSML) tags like prosody so you can adjust the speech rate, pitch, or volume. Amazon Polly is a secure service that delivers all of these benefits at high scale and at low latency. You can cache and replay Amazon Polly’s generated speech at no additional cost. Amazon Polly lets you convert millions of characters per month for free during the first year, upon sign-up. Amazon Polly’s pay-as-you-go pricing, low cost per request, and lack of restrictions on storage and reuse of voice output make it a cost-effective way to enable speech synthesis everywhere.

You can use Amazon Polly to power your application with high-quality spoken output. This cost-effective service has very low response times, and is available for virtually any use case, with no restrictions on storing and reusing generated speech.

You can control various aspects of speech such as pronunciation, volume, pitch, speech rate, etc. using standardized Speech Synthesis Markup Language (SSML). You can synthesize speech for certain Neural voices using the Newscaster style, to make them sound like a TV or Radio newscaster. You can detect when specific words or sentences in the text are being spoken to the user based on the metadata included in the audio stream. This allows the developer to synchronize graphical highlighting and animations, such as the lip movements of an avatar, with the synthesized speech. You can modify the pronunciation of particular words, such as company names, acronyms, foreign words and neologisms, e.g. “P!nk”, “ROTFL”, “C’est la vie” (when spoken in a non-French voice) using custom lexicons.

Speech Marks are designed to complement the synthesized speech that is generated from the input text. Using this metadata alongside the synthesized speech audio stream, customers can provide their application with an enhanced visual experience such as speech-synchronized animation or karaoke-style highlighting.

Amazon Polly generates Speech Marks using the following four elements:

1. Sentence, which indicates a sentence element in the input text to be spoken;
2. Word, which Indicates a word element in the text;
3. Viseme, which describes the shape of the lips that corresponds to the sound that is spoken;
4. SSML, which describes an SSML element used in the text.

Speech Marks are delivered in form of a JSON stream -- specifically, a set of standalone JSON objects delimited with new lines -- containing anywhere from one to all four of these elements, when using the synthesize-speech method with the speech-mark-types parameter. You can find more information in the Amazon Polly Developer Guide.

With Amazon Polly, you can bring your applications to life, by adding life-like speech capabilities. For example, in E-learning and education, you can build applications leveraging Amazon Polly’s Text-to-Speech (TTS) capability to help people with reading disabilities. Amazon Polly can be used to help the blind and visually impaired consume digital content (eBooks, news etc). Amazon Polly can be used in announcement systems in public transportation and industrial control systems for notifications and emergency announcements. There are a wide range of devices such as set-top boxes, smart watches, tablets, smartphones and IoT devices, which can leverage Amazon Polly for providing audio output. Amazon Polly can be used in telephony solutions to voice Interactive Voice Response systems. Applications such as quiz games, animations, avatars or narration generation are common use-cases for cloud-based TTS solution like Amazon Polly.

When combined with Amazon Lex, developers can create full-blown Voice User Interfaces for their applications. Within Amazon Connect, Amazon Polly speech is used to create self-service, cloud-based contact center services. On top of that, developers of mobile applications and Internet-of-Things (IoT) solutions can leverage Amazon Polly to add spoken output to their own systems.

On-device text-to-speech solutions require significant computing resources, notably CPU power, RAM, and disk space to be available on the device. This can result in higher development cost and higher power consumption on devices such as tablets, smartphones, etc. In contrast, text-to-speech conversion done in the cloud dramatically reduces local resource requirements. This makes it possible to support all of the available languages and voices at the highest possible quality. Moreover, speech corrections and enhancements are instantly available to all end-users and do not require additional updates for all devices. Cloud-based text-to-speech (TTS) is platform independent, so it minimizes development time and effort.

Simply login to your AWS account and navigate to the Amazon Polly console (which is a part of the AWS Console). You can then use the console to type in any text and listen to generated speech or save it as an audio file.

Please refer to the AWS Regional Services List for all regions supporting Amazon Polly’s Standard voices. Neural voices are supported in the following subset of these regions: US East (N. Virginia), US West (Oregon), Canada (Central), Asia Pacific (Malaysia), Asia Pacific (Tokyo), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Africa (Cape Town), EU (London), EU (Frankfurt), EU (Ireland) and AWS GovCloud (US-West).

Amazon Polly supports all the programming languages included in the AWS SDK (Java, Node.js, .NET, PHP, Python, Ruby, Go, and C++) and AWS Mobile SDK (iOS/Android). Amazon Polly also supports an HTTP API so you can implement your own access layer.

With Amazon Polly, you can stream audio to your users in near real time. You can also choose from various sampling rates to optimize bandwidth and audio quality for your application. Amazon Polly supports MP3, Vorbis, and raw PCM audio stream formats.

Please refer to  documentation for the complete list of languages supported by Amazon Polly.

To help guarantee the availability of AWS resources and to minimize billing risk for new customers, AWS maintains service limits for each account. When using Amazon Polly to power your application with high-quality spoken output, there are default service limits including limitations on throttling, operations, and Speech Synthesis Markup Language (SSML) use. For details, see Limits in Amazon Polly in the Amazon Polly Developer Guide. Combining Amazon Polly with other AWS services, such as AWS Batch for efficient batch processing, can help you make the most of Amazon Polly within those service limits.

A: Amazon Polly is a HIPAA Eligible Service covered under the AWS Business Associate Addendum (AWS BAA). If you have an AWS BAA in place, Amazon Polly will use, disclose, and maintain your Protected Health Information (PHI) only as permitted by the terms of your AWS BAA, and not as specified in the Data Privacy section of the Amazon Polly FAQ.

If you are interested in building a Brand Voice using Amazon Polly, please reach out to your AWS Account Manager or contact us for more information.

Every voice is unique, so it’s important that we learn more about your goals to accurately scope a Brand Voice engagement. If you are interested in building a Brand Voice using Amazon Polly, please reach out to your AWS Account Manager or contact us for more information.