Back to GlossaryCore Technology
TTS — Text-to-Speech
Technology that converts written text into synthetic human speech.
TTS (Text-to-Speech) is the technology that gives a Voice AI agent its "voice." After the system decides what to respond, TTS converts the answer into natural-sounding speech. Modern TTS technologies include Neural TTS (deep, emotional voices), Prosody Control (intonation control), and Emotional TTS (emotion expression). According to Amazon Research, Neural TTS achieves 4.5/5 naturalness score (MOS) compared to 3.5/5 for traditional TTS (Source: Amazon Polly Research, 2024).