Amazon Polly generative engine upgraded with enhanced voices and languages
Amazon Polly’s Generative engine has been upgraded to include more natural-sounding voices, 14 new voices across nine locales, and two new languages, Hindi and Finnish, enhancing its speech output capabilities.
Amazon has announced a significant upgrade to its Polly Generative engine, enhancing its capability to deliver more natural-sounding and accurate speech output with minimal delay. This new model introduces an expanded and improved voice portfolio, featuring 14 new voices across nine locales and two additional languages—Hindi and Finnish—now available on the Generative engine for the first time.
The new voices include Kenneth and Nate for US English, Russell and Curtis for Australian English, Kiara and Arjun for Hindi and Indian English, Tina for German, Carlos for US Spanish, Leo and Carolina for Brazilian Portuguese, Hyunduk for Korean, and Suvi for Finnish. These additions aim to provide users with a more diverse and realistic auditory experience.
Amazon Polly, a fully managed service that transforms text into natural-sounding speech, benefits from this model upgrade by making its Generative voices more lifelike and precise. The engine is designed to handle complex content such as numbers, email addresses, and street addresses more reliably, minimizing the need for additional adjustments to speech output. Users can still employ Speech Synthesis Markup Language (SSML) tags to manage speech output on the Generative engine as before.
The low-latency streaming API of Amazon Polly facilitates the development of contact center experiences, chatbots, and large language model (LLM) based agentic voice applications for real-time interactions. The variety and richness of voice options make it suitable for applications in news, media, entertainment, e-learning, and accessibility.
This expansion also extends the reach of the Amazon Polly Generative offering to AWS GovCloud, providing more options for public sector and regulated industries. The new Generative voices are now available in several AWS Regions, including US East (N. Virginia), US West (Oregon), Europe (Frankfurt), Europe (Zurich), Europe (London), Asia Pacific (Sydney), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Tokyo), Canada (Central), and AWS GovCloud (US-West).
For those interested in experiencing the new Polly voices, Amazon invites users to explore the Amazon Polly Features page. Additional information on the offerings and pricing is available in the Amazon Polly documentation.