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

# Voice

> Configure how your agent sounds and how it listens.

This section is about how your agent speaks and listens – the TTS voice it uses, how it handles audio, what it does mid-conversation, and how it transcribes what callers say.

It is **not** about how customers reach your agent. For that, see [Phone](/voice-channel/introduction) (Numbers and Web Calling) and [Chat](/messaging-channel/introduction).

<Tip>
  [Raven](/behavior/models/raven) produces responses that sound natural when spoken aloud. Recommended for any voice deployment.
</Tip>

## What lives here

<CardGroup cols={2}>
  <Card title="Agent Voice" icon="user" href="/voice-channel/agent">
    Pick the TTS voice and tune stability, clarity, and speed.
  </Card>

  <Card title="Voice library" icon="list" href="/voice-channel/voice-library">
    Browse and compare voices across providers (ElevenLabs, Cartesia, Hume, and more).
  </Card>

  <Card title="Choosing a good voice" icon="ear-listen" href="/voice-channel/choosing-a-good-voice">
    Match voice to brand, audience, and industry.
  </Card>

  <Card title="Multi-voice" icon="users" href="/voice-channel/multi-voice">
    Use multiple voices in a single project.
  </Card>

  <Card title="Voice configuration" icon="gear" href="/voice-channel/advanced/call-settings">
    Greeting audio, disclaimer playback, model selection, safety filters, and call handling.
  </Card>

  <Card title="Response control" icon="sliders" href="/voice-channel/advanced/response-control">
    Translations, pronunciations, and stop keywords.
  </Card>

  <Card title="Audio management" icon="volume-high" href="/voice-channel/audio-library">
    Audio playback and recording settings.
  </Card>

  <Card title="Speech recognition" icon="microphone" href="/voice-channel/advanced/speech-recognition">
    ASR settings – how the agent transcribes what callers say.
  </Card>
</CardGroup>

## How to think about it

There are four concerns, and they're configured separately:

1. **How it sounds** – Agent voice, voice library, multi-voice, custom voice. Picking a TTS voice and tuning it.
2. **How it behaves in a call** – Voice configuration: greeting, disclaimer, model selection, safety filters, call handling.
3. **How it listens** – Speech recognition (ASR) settings.
4. **How it phrases things** – Response control: translations, pronunciations, stop keywords.

Start with [Choosing a good voice](/voice-channel/choosing-a-good-voice), then configure the voice in [Agent Voice](/voice-channel/agent), and tune call-runtime behavior in [Voice configuration](/voice-channel/advanced/call-settings).

<div className="full-only">
  ## Programmatic voice configuration

  You can also configure voices programmatically using the [voice class](/tools/classes/voice) inside functions – for example, selecting a voice based on conversation context, caller preferences, or other runtime variables.
</div>

## Voice conversation style guide

These guidelines help your voice agent sound natural rather than robotic. They focus on the linguistic patterns that make spoken conversations feel human.

### Social presence markers

Natural conversation includes patterns that acknowledge conversational history and participants. These contribute to a sense of collaboration rather than rote routine-following.

**Use progressive tense for active collaboration:**

* "I'm not seeing any accounts under that phone number..." conveys active collaboration
* "I don't see any accounts" sounds too definitive

**Reference shared context implicitly** – don't restate what both parties already know:

* "How about Wednesday instead?" (not "How about Wednesday instead of Tuesday?")
* "In that case, how does Saturday at 2:30 sound?" (not "Since you said you prefer weekends...")

**Vary confirmationals** – use a mix of "Great," "Okay," "Perfect," and "Sure" rather than repeating the same one.

**Use conversational datives** for a collaborative feel:

* "Could you read **me** your account number?" rather than "Could you read your account number aloud?"
* "Can you log into your account **for me**?" rather than "Can you log into your account?"

**Use face-saving past tense** when referencing a user's request:

* "When **were** you trying to come in?" rather than "When are you trying to come in?"

### Avoid over-explaining

LLMs tend to justify every action in a way humans don't. Most of the time, the important information and the request can be formed into a single sentence:

* "No problem, what's your account number?" rather than "To check for outages, I'll need to look up your account. Could you tell me your account number?"

### Walkthrough conversations

When giving multi-turn walkthroughs, don't end every step with "let me know when you've done that." Provide the instruction and wait – the user will confirm on their own.

## Related

<CardGroup cols={2}>
  <Card title="Phone" icon="phone" href="/voice-channel/introduction">
    Voice transports – let customers reach your agent over the phone (Numbers) or from your website (Web Calling).
  </Card>

  <Card title="Chat" icon="message" href="/messaging-channel/introduction">
    Add a text-based chat widget to your website.
  </Card>
</CardGroup>