—Glossary
AI voice agent
An AI voice agent is software that holds spoken phone conversations, using speech recognition, a language model and speech synthesis to understand callers and act on their requests.
An AI voice agent is software that talks with people over the phone. It listens, works out what the caller wants, replies in a natural voice, and can take actions such as booking an appointment or updating a record. It can answer inbound calls or place outbound ones.
How it works
A voice agent runs a loop on every turn of the conversation:
- Speech recognition turns the caller's words into text.
- A large language model reads the text, along with its instructions and business information, and decides what to say or do next.
- Tools connected through APIs let it act: check a calendar, look up an order, create a CRM contact.
- Speech synthesis turns the reply into audio.
Speed matters. Callers notice pauses, so the whole loop has to finish quickly for the call to feel natural.
How it works in a business
Inbound, a voice agent usually acts as an AI receptionist. Outbound, it can call back web leads, confirm appointments or run reminder calls.
Outbound calls carry legal duties. In a declaratory ruling released on February 8, 2024 (FCC 24-17), the FCC confirmed that AI-generated voices count as "artificial" voices under the TCPA. These calls therefore need the called party's prior express consent unless an emergency purpose or exemption applies.
How it relates to Worcia
Voice agents are part of two Worcia services: Concierge, its AI receptionist, which answers calls, and Cadenza, its lead follow-up system, which handles outbound follow-up. For the legal side, read Are AI phone calls legal?
Sources
- Implications of Artificial Intelligence Technologies on Protecting Consumers from Unwanted Robocalls and Robotexts, Declaratory Ruling (FCC 24-17). Federal Communications Commission, February 8, 2024.