Text-to-speech

Technology that converts written text into spoken audio output. Text-to-speech is the primary output method used by screen readers to convey digital content to blind and low-vision users. The quality and naturalness of TTS voices has improved significantly with neural speech synthesis. In the context of adaptive content, TTS raises important considerations around synchronization — when a screen reader is generating speech from text, it must manage conflicts with other audio content such as video soundtracks, notification sounds, or earcons.