AWS Upgrades Amazon Polly's Generative Engine With 14 New Voices

Amazon Web Services has rolled out a general-availability upgrade to the Amazon Polly Generative engine, the text-to-speech technology behind its Amazon Polly service. According to AWS, the update delivers more expressive and accurate speech output with low latency and is now live in production.

What changed

AWS says the upgrade adds 14 new voices across 9 locales. The new voices include Kenneth and Nate for US English, Russell and Curtis for Australian English, Kiara and Arjun for Indian English, Tina for German, Carlos for US Spanish, Leo and Carolina for Brazilian Portuguese, Hyunduk for Korean, and Kiara and Arjun again for Hindi.

The company says Hindi and Finnish are generally available on the Generative engine for the first time. The Finnish voice is named Suvi. With this release, AWS says the Amazon Polly Generative engine now totals 57 generative voices across 11 languages and 25 locales.

AWS also says the upgrade expands Region availability to AWS GovCloud (US-West), bringing the total to 11 AWS Regions.

Accuracy and speech delivery

AWS says the upgraded engine improves accuracy when reading back structured information such as order numbers, dates, currency amounts, and addresses. The company also says the voices can now reflect different styles of speech delivery, such as neutral, uncertain, or surprised tones, based on the text input alone, without manual setup.

No changes required for existing users

AWS describes the release as a drop-in upgrade. The company says voice names and API calls are unchanged, so applications already using Amazon Polly Generative voices will receive the improved output automatically, with no code changes required.

For new applications, AWS says the same SynthesizeSpeech API provides access to the expanded voice catalog. The company also points to its Bi-Di Streaming API, StartSpeechSynthesisStream, which allows text to be streamed to Amazon Polly while synthesized audio is returned simultaneously. AWS says this is suited to real-time applications such as voice agents and game characters.

AWS says Amazon Polly continues to use standard AWS patterns, including access management through AWS Identity and Access Management (IAM), and integration with existing contact-center flows and monitoring tools.

Pricing

AWS says the Amazon Polly Generative engine remains on a pay-as-you-go pricing model and that this upgrade carries no cost increase, no new SKU, and no changes to existing integrations. The company says synthesized static prompts can be cached and replayed at no additional cost.

Amazon Polly is described by AWS as a fully managed service used for converting text into speech in contact centers, large language model-based agentic applications, media and entertainment, e-learning, and accessibility applications.

Source: AWS Machine Learning Blog, "Amazon Polly delivers a major upgrade to its Generative engine," published October 22, 2026.