> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orbit.devotel.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction to voice AI agents

> What a Devotel Orbit voice AI agent is, how a spoken call moves through the stack, and the shortest path to answering or placing your first agent-handled phone call.

A voice AI agent answers or places real phone calls and carries the
conversation end to end — greeting the caller, understanding speech,
deciding what to do next, speaking back, and calling your tools when it
needs data or an action. Build it once and it handles inbound calls to
your numbers, outbound outreach you dispatch from the API, and live
handoff to a human when the conversation needs one.

This page introduces the concept and the pieces a voice agent is made
of, then points you to the shortest path for your first call. Everything
it references ships in the product today.

## What a voice agent is

A voice agent is a regular [Orbit agent](/agents/overview) whose channel
of work is the phone. On [create](/agents/creating-agents) you attach a
system prompt, optional knowledge bases, and the tools it may call; the
runtime takes it from there. There is no separate "voice SDK" to wire —
the phone call lands on the Orbit [voice](/channels/voice) pillar and
the agent answers it.

What changes for voice is timing. The caller hears delays, so every
turn has to complete in well under a second of speaking time and the
agent must handle being interrupted. The Orbit voice runtime manages
barge-in and turn-taking for you; your prompt and tools stay the same as
for a text agent.

## How a call moves through the stack

Each spoken turn passes through a managed media pipeline:

```
Caller audio → speech-to-text → agent reasoning (system prompt +
memory + tools) → text-to-speech → caller
```

Orbit runs the whole pipeline behind a single voice endpoint — you
never provision a speech service or a separate AI vendor yourself. From
(step 1 of the [Voice quickstart](/voice/quickstart)) the four stages
resolve on production-grade providers, and the agent's reasoning runs on
the same runtime that powers text agents, so [conversation
flows](/agents/conversation-flows), [memory](/agents/memory-plane), and
[tool calls](/agents/handoff-targets) behave the way you already know.

The call itself — from ringing to hangup — follows a deterministic state
machine (queued → initiated → ringing → answered → completed or a
failure outcome). Read [Voice call
lifecycle](/concepts/voice-call-lifecycle) once and every webhook you
receive will make sense.

## Inbound: the agent answers your number

For inbound, you route a phone number you own to the agent. Every caller
to that number is greeted and served by the agent. The shortest end-to-end
walkthrough is the [Voice quickstart](/voice/quickstart) — claim a trial
number, attach your agent, and call it from any phone.

## Outbound: the agent dials a list

For outbound, you request a call over `POST /voice/calls` with an
`agent_id`. The dial is placed only after the recipient's compliance
gates pass — quiet hours, do-not-call, and AI-voice consent run before
anything rings, and a rejected call is never billed. For more than a
handful of recipients you run a dialer campaign rather than per-call API
dials. See [Outbound calls with an AI voice
agent](/voice/ai-agent-outbound-calls) for the request schema and error
matrix.

## Human handoff when the conversation needs one

A voice agent is not a dead end — you can let a caller reach a person,
or have the agent escalate on its own when its confidence or policy
says so. The full transfer flow, including warm handoff to a specific
queue or colleague, is covered in [AI agent
handback](/voice/ai-agent-handback). Set the targets the agent is
allowed to reach in [handoff targets](/agents/handoff-targets).

## Where to go next

* [**Voice quickstart**](/voice/quickstart) — claim a number, attach an
  agent, place your first call in minutes.
* [**Creating agents**](/agents/creating-agents) — prompt, tools, and
  knowledge bases.
* [**Model selection**](/agents/model-selection) and
  [**cost controls**](/agents/cost-controls) — pick latency-appropriate
  models and cap spend per run.
* [**Guardrail effectiveness**](/agents/guardrail-effectiveness) and
  [**voice eval runs**](/agents/voice-eval-runs) — test the agent against
  recorded and simulated speech before pointing a real number at it.
* [**Live monitor**](/agents/live-monitor) and [human-in-the-loop
  oversight](/agents/human-in-the-loop-oversight) — watch production
  calls and intervene.

When you're past the introduction, the [AI agents
overview](/agents/overview) page indexes everything else the agent
runtime can do; the voice-specific state machine lives under [Voice call
lifecycle](/concepts/voice-call-lifecycle).