Speech-to-Text (STT) and Text-to-Speech (TTS) are the two foundational technologies that enable AI voice agents. STT converts spoken audio into text that the AI can process. TTS converts the AI's text responses back into natural-sounding spoken audio.

How STT works

This section covers how stt works in detail. For the complete glossary of AI voice agent terms, see our main glossary page.

How TTS works

This section covers how tts works in detail. For the complete glossary of AI voice agent terms, see our main glossary page.

STT and TTS quality matters

This section covers stt and tts quality matters in detail. For the complete glossary of AI voice agent terms, see our main glossary page.

Premium vs. default voices

This section covers premium vs. default voices in detail. For the complete glossary of AI voice agent terms, see our main glossary page.

Cost considerations

This section covers cost considerations in detail. For the complete glossary of AI voice agent terms, see our main glossary page.

Want the complete glossary?

Our main glossary page defines 24+ AI voice agent terms in plain English.

View complete glossary