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

# How a call flows

> What runs between the caller audio and your agent text - whether users dial a number or connect from a browser or app.

## What runs the call

Unpod gives your agent voice. It handles everything between the user's audio and your agent's text logic. The Speech Stack is the developer surface of the [Calling Engine](https://docs.unpod.ai/telephony/concepts/calling-engine.md) - one channel in the Talk layer of the [Core Engine](https://docs.unpod.ai/get-started/core-concepts.md).

Your agent receives plain text. It returns plain text. The Speech Stack handles everything else: transcription, synthesis, VAD, barge-in detection, endpointing, and transport.

***

## Two Ways Users Connect

> [card] Phone / Telephony
>
> Users dial a phone number. Unpod handles SIP, PSTN, number provisioning, and routing. No carrier account or SIP trunk needed.

> [card] Browser / App
>
> Users connect from a web app or mobile app - same speech pipeline, no phone number required. Today browser sessions run via the hosted Playground; the embeddable `@unpod/web-sdk` is not yet published on npm.

Both paths run through the same managed speech pipeline (STT, TTS, VAD, barge-in). Your agent code is identical regardless of how the user connects.

***

## How Audio Flows

Unpod voice stack

Caller

PhonePSTN, dials a numberBrowserWebRTC / WebSocketMobile appSession token

audio

Unpod runs

Number & carrierUnpod rails, or your trunkSpeech inSTT + VAD, from the voice profileOrchestratorTurns, barge-in, dispatchSpeech outTTS, streamed to the caller

text turnreply text

You run

AgentRunnerRegisters over WSSYour brainDialogMachine, LLM, any PythonTools & APIsYour systems

Unpod runs itYou run itOutside bothAudio never reaches your side. The bridge carries text in, text out.

**1. User connects**

Via a phone number (PSTN/SIP), or from a browser/app (via the hosted Playground today; Web SDK not yet published).

**2. Speech pipeline runs**

Unpod transcribes audio (STT), detects turn end (VAD + endpointing), and handles barge-in interruptions. Your agent gets clean text.

**3. Your agent responds**

The Unpod orchestrator dispatches the session to your `AgentRunner`. Your entrypoint runs, your dialog machine produces a text reply.

**4. Reply synthesised**

Unpod converts the reply to speech (TTS) and streams it back to the user.

**5. Session ends**

Transcript, metrics, and recording are stored and queryable via the management API.

***

## Core Building Blocks

> [card] [Voice Profiles](https://docs.unpod.ai/agent-sdk/voice-profiles.md)
>
> Choose STT and TTS providers. Pre-built profiles or custom combinations with automatic failover.

> [card] [Agents](https://docs.unpod.ai/speech-stack/agents.md)
>
> One `agent_id`, one brain, N voices. Say the brain out loud - a playbook, a prompt, your own runner, or your own endpoint.

> [card] [Phone Numbers](https://docs.unpod.ai/speech-stack/numbers.md)
>
> Provision numbers directly or bring your own. Attach to an agent for inbound calls.

> [card] [AgentRunner & Sessions](https://docs.unpod.ai/agent-sdk/agent-runner.md)
>
> Install `unpod`, run your `AgentRunner`, and accept sessions from any source.

***

## Quickstart Paths

| I want to... | Start here |
| - | - |
| Place your first call | [Quickstart](https://docs.unpod.ai/home/quickstart.md) - six SDK calls, a Prompt brain, nothing to deploy |
| Run my own brain on calls | [Run Your Own Brain](https://docs.unpod.ai/agent-sdk/quickstart.md) - an AgentRunner serving inbound and outbound |
| Add voice to a web app | [Realtime](https://docs.unpod.ai/telephony/streaming/unpod-speech-quickstart.md) - browser sessions via the hosted Playground today (Web SDK not yet published) |

***

## Next Steps

> [card] [Quickstart](https://docs.unpod.ai/home/quickstart.md)
>
> A named agent, a number, a live call - six SDK calls, one file.

> [card] [Run a SuperDialog agent](https://docs.unpod.ai/speech-stack/level-up-superdialog.md)
>
> Drive conversations with structured flows and tools.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.