> ## 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.

# Speech Stack

> The speech layer for your agent - whether users call by phone or connect from a browser or app.

## What the Speech Stack Does

The Speech Stack gives your agent voice. It handles everything between the user's audio and your agent's text logic.

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

<CardGroup cols={2}>
  <Card title="Phone / Telephony" icon="phone">
    Users dial a phone number. Unpod handles SIP, PSTN, number provisioning, and routing. No carrier account or SIP trunk needed.
  </Card>

  <Card title="Browser / App" icon="monitor-smartphone">
    Users connect from a web app or mobile app via the Unpod Web SDK. Same speech pipeline - no phone number required.
  </Card>
</CardGroup>

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

<Frame>
  <img src="https://mintcdn.com/unpodai/9OLw2S-v9psMSqik/images/diagrams/unpod-voice-stack.svg?fit=max&auto=format&n=9OLw2S-v9psMSqik&q=85&s=68d4f631702c1116700d8fcf23480f1f" alt="Unpod voice stack diagram showing phone, browser, and mobile entrypoints flowing through the managed speech layer into your AgentRunner and dialog machine." width="1672" height="941" data-path="images/diagrams/unpod-voice-stack.svg" />
</Frame>

<Steps>
  <Step title="User connects">
    Via a phone number (PSTN/SIP) or directly from a browser/app using the Web SDK.
  </Step>

  <Step title="Speech pipeline runs">
    Unpod transcribes audio (STT), detects turn end (VAD + endpointing), and handles barge-in interruptions. Your agent gets clean text.
  </Step>

  <Step title="Your agent responds">
    The Unpod orchestrator dispatches the session to your `AgentRunner`. Your entrypoint runs, your dialog machine produces a text reply.
  </Step>

  <Step title="Reply synthesised">
    Unpod converts the reply to speech (TTS) and streams it back to the user.
  </Step>

  <Step title="Session ends">
    Transcript, metrics, and recording are stored and queryable via the management API.
  </Step>
</Steps>

***

## Core Building Blocks

<CardGroup cols={2}>
  <Card title="Voice Profiles" icon="waveform" href="/speech-stack/voice-profiles">
    Choose STT and TTS providers. Pre-built profiles or custom combinations with automatic failover.
  </Card>

  <Card title="Speech Pipe" icon="bot" href="/speech-stack/pipes">
    Bundle a voice profile, recording settings, and connection attachments, then point the pipe at your agent.
  </Card>

  <Card title="Phone Numbers" icon="phone" href="/speech-stack/numbers">
    Provision numbers directly or bring your own. Attach to a Speech Pipe for inbound calls.
  </Card>

  <Card title="SDK Setup" icon="code" href="/speech-stack/agent-runner">
    Install `unpod`, run your `AgentRunner`, and accept sessions from any source.
  </Card>
</CardGroup>

***

## Quickstart Paths

| I want to...           | Start here                                                                                                   |
| ---------------------- | ------------------------------------------------------------------------------------------------------------ |
| Handle phone calls     | [Telephony Quickstart](/get-started/first-phone-call) - provision a number and attach it to your Speech Pipe |
| Add voice to a web app | [Web SDK Quickstart](/get-started/first-phone-call#web-app) - embed the Unpod Web SDK in your frontend       |
| Connect both           | Start with telephony, then add the Web SDK - same Speech Pipe, two entry points                              |

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Quickstart" icon="bolt" href="/get-started/first-phone-call">
    End-to-end: agent running and accepting sessions in under 10 minutes.
  </Card>

  <Card title="SuperDialog Integration" icon="layers" href="/speech-stack/level-up-superdialog">
    Drive conversations with structured flows and tools.
  </Card>
</CardGroup>