Skip to content
Adoptiv

AI Voice Agent

A voice agent offered calls from a queue the way a person is, answering inbound DIDs and qualifying outbound campaigns from one configuration. What lifts it past a script reader is that it writes to the record while the call is still up.

Voice agent: Front desk

may write
Agent type
Opens with

Good morning, you have reached Meridian. Who were you after?

May read
Look the caller upRead what happened beforeUse the company profileUse the answer list
May write
Create a contactUpdate a contactRaise a taskOpen a dealTag the contactSend a text
Hands over
May transferescalates lowQueue: Support - EMEA
Guardrails
caps at 3:00can be interruptedanswers around the clock
Model, voice and speech engines are set behind the record
Writing is the half that is off until you turn it on, one grant at a time. An agent that may tag but may not create is a deliberate setting, not a limitation, and it is the setting most floors start on.
0
tools the model can call mid-conversation
0
stages between a caller speaking and an answer
0
configuration behind both directions

Product figures from the platform’s own defaults - not customer averages

The mechanism

How it works.

01

It is offered the call

An inbound DID rings it the way a queue rings a person, and an outbound campaign hands it a connect the same way. One configuration covers both directions, and the call stays where it was placed.

02

Hear, decide, answer

Voice activity detection marks the end of a turn, streaming speech to text puts it into words, a model with tool use reads the conversation so far and chooses what to do, and text to speech says it. The audio runs on the same media path as every other call.

03

Four tools are the difference

It can transfer to a queue, set a disposition code, capture a field onto the lead, or end the call. Each of those is a write made while the call is up, not a summary assembled afterwards, which is the line between this and a menu with better prose.

04

The trail you already read

Captured fields land on the record during the conversation, the disposition is one of the codes your people pick from, and every session keeps its full transcript for review call by call.

Where it sits

Two moments in every call.

Every call passes through the same seven. AI Voice Agent is the lit ones, and everything either side of it is a different page in this category.

  1. 01
    Number

    the line it arrives on or leaves from

  2. 02
    Route

    where the call is sent and to whom

  3. 03
    Dial

    placing it, and how many at once

  4. 04
    Connect

    the moment a person picks up

  5. 05
    Talk

    while the conversation is happening

  6. 06
    Wrap

    the code, the notes, the next step

  7. 07
    Record

    what is kept, and where it is kept

The specifics.

8 facts
Tools
transfer(queue), set_disposition(code), capture_field(key, value), end_call
Pipeline
Voice detection, streaming speech to text, a model with tool use, then speech
Direction
One configuration answers inbound DIDs and qualifies outbound campaigns
Handover
Warm transfer to a person on a queue, carrying the transcript and the fields
Fields
Written onto the lead mid-call, under keys you name when you build it
Setup
Greeting, objective, the questions it asks, the fields it captures, and the voice
Not quoted
No latency figure, language count, carrier name or accuracy rate is published
Not the same as
A menu that reads options and waits for a keypress is the auto-attendant. This one holds a conversation and writes while it does

Outbound & Compliance

See ai voice agent on your own floor.

Thirty minutes, your numbers and your data. We will set ai voice agent up live and you can decide from the thing itself rather than from this page.

14-day trial · no card · migration included