Text-to-speech
Technology that turns written text into spoken audio, now good enough to be hard to tell from a recording.
Text-to-speech, often shortened to TTS, is the mirror image of speech-to-text: words in, audio out. It has been around for decades in flat robotic form, and it is the layer underneath screen readers, satnav directions and audio versions of articles. What changed recently is quality. Modern systems handle pauses, emphasis and emotion well enough that a short clip is genuinely difficult to distinguish from a person reading aloud.
That improvement moved TTS from an accessibility feature to a publishing format. Platforms now generate spoken versions of written content automatically, and audiobooks, podcasts and video narration increasingly start life as text. The same quality that makes it useful also makes voice cloning a real problem, which is why responsible products label synthetic narration clearly.