Text-to-speech (TTS) is technology that converts written text into synthesized spoken audio.
Why it matters
It gives a voice agent its voice, and it strongly shapes how clear, well paced, and natural the conversation feels. A caller’s trust is built or lost in how the agent sounds, and in whether it says their name and the product names correctly.
What it looks like
The agent says a customer’s name the way they say it, reads back an address at a steady pace, and stops talking the moment the caller interrupts, instead of finishing a recorded sentence first.
Related terms
Automatic speech recognition · Natural-sounding voice · Latency