TTS

Text-to-Speech (TTS) is an AI technology: it converts written digital text into natural-sounding, synthesized spoken audio.

TTS converts text input (like an API string or document) into human-like speech output (audio). The technology, originally an assistive tool for users with visual impairments or dyslexia, now leverages deep learning and neural networks (Neural TTS) to produce highly expressive, low-latency voices. Major providers like Google Cloud and Microsoft Azure offer APIs supporting over 99 languages. Core applications include automated customer service (IVR), voice-enabled virtual assistants (Siri, Cortana), and large-scale content creation (audiobooks, video narration); this drives efficiency and accessibility across multiple industries.

https://www.ibm.com/topics/text-to-speech