Amazon Polly Expands Generative Text-to-Speech Voices and Adds Bidirectional Streaming API

Amazon Polly introduced ten new lifelike voices and enabled streaming synthesis via a bidirectional API for interactive applications.

By Amelia Ross · Editorial pseudonym · 2026-03-20 · 1 min read

AI-ASSISTED REPORTING · RETROSPECTIVE ARCHIVE

Retrospective edition: 2026-03-20. Source published: 2026-03-20. Added to this archive: 2026-11-03. This briefing was prepared later from the linked announcement; it was not published on this website on the historical edition date.

The Generative TTS engine now features expressive voices spanning American, British, New Zealand, Singapore English, and several European languages, enhancing naturalness in speech-enabled services. Its availability extends to new AWS regions in Europe and Canada.

With the Bidirectional Streaming API, developers can send text and receive audio simultaneously, facilitating real-time use cases such as chatbots and game characters. These features support growing demand for conversational AI and dynamic content generation.

Source & further reading

Amazon Polly expands Generative TTS engine with 10 new voices, 2 new regions, and Bidirectional Streaming API ↗

Source published 2026-03-20. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.