> ## 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.

<AgentInstructions>

## Submitting Feedback

If you encounter incorrect, outdated, or confusing documentation on this page, submit feedback:

POST https://docs.poly.ai/feedback

```json
{
  "path": "/voice/introduction",
  "feedback": "Description of the issue"
}
```

Only submit feedback when you have something specific and actionable to report.

</AgentInstructions>

# Overview

> Configure your agent's voice settings

Configure how your agent sounds. Choose a TTS voice (ElevenLabs, Cartesia, Hume, and others) and adjust stability, clarity, and speed. Found in **Channels > Voice**.

<Tip>
  [Raven](/agent-settings/raven) produces responses that sound natural when spoken aloud – recommended for voice deployments.
</Tip>

## Key considerations

* **Accent and region** – match the voice to your caller base
* **Tone** – calm and authoritative vs. warm and conversational, depending on context
* **Stability** – higher = more predictable; lower = more natural variation between turns

Start with [Choosing a good voice](./choosing-a-good-voice), then configure in [Agent Voice](./agent).

## Voice pages

<CardGroup cols={2}>
  <Card title="Agent Voice" icon="user" href="./agent">
    Select a voice and fine-tune stability, clarity, and other parameters for your agent and disclaimer voices.
  </Card>

  <Card title="Voice library" icon="list" href="./voice-library">
    Browse, preview, and compare all available voices across providers.
  </Card>

  <Card title="Choosing a good voice" icon="ear-listen" href="./choosing-a-good-voice">
    Best-practice guidelines for matching voice to your brand, audience, and industry.
  </Card>

  <Card title="Multi-voice" icon="users" href="./multi-voice">
    Assign multiple voices to simulate a team of agents in a single project.
  </Card>

  <div className="full-only">
    <Card title="Add a voice" icon="plus" href="./add-a-new-voice">
      Configure voices programmatically using provider classes.
    </Card>
  </div>

  <Card title="Custom voice" icon="microphone-lines" href="./custom-voice-request">
    Request a brand-exclusive cloned voice (enterprise).
  </Card>

  <Card title="Voice configuration" icon="gear" href="./voice-configuration">
    Configure greeting audio, disclaimer playback, and call handling settings.
  </Card>
</CardGroup>

<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 pages

<CardGroup cols={3}>
  <Card title="Choosing a good voice" icon="ear-listen" href="/voice/choosing-a-good-voice">
    Best practices for matching voice to your brand and audience
  </Card>

  <Card title="Response control" icon="sliders" href="/response-control/introduction">
    Fine-tune translations, stop keywords, and pronunciations
  </Card>

  <Card title="Audio management" icon="volume-high" href="/audio-management/introduction">
    Configure audio playback and recording settings
  </Card>
</CardGroup>