A text-to-speech (TTS) service that converts text into audio with realistic neural voices in multiple languages, used for voice assistants, content narration, and audio response systems.
In AIF-C01 (Domain 3) it is tested in the Polly (text→speech) vs. Transcribe (speech→text) pair. Question: generating narrated audio from website articles → Amazon Polly.
Amazon Polly is a concept that can show up on the exam. Check the full guide to see it in context.