What is TTS?

Text to speech — generating the agent's voice.

Text-to-speech synthesises spoken audio from written text. Modern neural TTS models produce natural prosody and pacing, and are the reason a voice agent no longer sounds like a recorded menu.

This is an industry glossary. A term defined here is not a statement that Drop AI provides it — see the pricing page for what is included.

Voice cloning

Synthesising a specific person's voice.

Prosody

Rhythm, stress and intonation in speech.

Voice agent

Software that holds a spoken conversation on a call.

Voice AI

More in this category

Voice agent Conversational AI ASR STT LLM System prompt Function calling Tool use Knowledge base RAG Grounding Hallucination

Transform every customer conversation.

Start free, or talk to us about what a custom rollout looks like for your team.

Try for Free Contact Sales