Amazon Polly is an advanced text-to-speech solution designed for developers and businesses looking to enhance their applications with lifelike voice experiences. With support for multiple languages and customisation features, Polly stands out by offering real-time speech synthesis and a variety of voices.

What are the main features of Amazon Polly?

Realistic Text-to-Speech Capabilities

Amazon Polly converts written text into lifelike speech, enhancing the user experience by offering natural-sounding voices.

• Wide Voice Selection: Choose from a broad selection of voices in various languages to match the tone and style of your content.
• Neural Text-to-Speech: Utilise advanced machine learning models to achieve highly natural speech output.

Multi-language Support

Amazon Polly supports numerous languages and dialects, allowing you to reach a global audience.

• Extensive Language Options: Engage listeners worldwide with more than 60 voices spanning over 30 languages.
• Dialect Variability: Access multiple dialects to cater to local audiences effectively.

Customisation and Personalisation

Tailor the speech output to fit the specific needs of your application or service, providing an enhanced user experience.

• Speech Marks: Synchronise speech with visual aids or animations through detailed speech timing data.
• Lexicon and SSML Support: Customise pronunciation and control speech aspects through simplified speech markup.