# Voice and turn-taking

> Make an agent sound human by writing for the ear and tuning how it takes turns.

Source: https://docs.vlayers.ai/build/voice

Kind: How-to guide

## What you'll learn

How to write lines that sound natural when spoken, and how to tune interruptions and pauses. Both are settings you control; neither needs a better model.

## Prerequisites

- An agent you can call. See [Your first voice agent](https://docs.vlayers.ai/build/first-voice-agent).

## The default models

Every call runs a speech-to-text, LLM, text-to-speech pipeline. The defaults:

| Stage | Default |
|---|---|
| Speech-to-text | Deepgram Nova-3 |
| LLM | OpenAI gpt-4o, with an Anthropic fallback |
| Text-to-speech | Cartesia Sonic (Inworld as an alternative) |

You can change them per workspace, with your own provider keys, or per agent.

## Step 1: Write for the ear

Everything you type is spoken aloud. Left alone, a model writes prose: correct, complete and robotic. Show it examples of what you want instead of asking it to "be conversational".

```text
Written (reads badly out loud)
  "I have verified that access point AP-CEDAR-204 is back online
   with a signal strength of -57 dBm."

Spoken (what you want)
  "Okay, good news... your Wi-Fi box just came back up, and the
   signal's looking strong."
```

## Step 2: Control the pace with punctuation

Punctuation is your only timing control, and the one you need.

```text
Use an ellipsis where a person would pause:
  "Alright... give me one second while I pull that up."

Short sentences. One idea each.
And it's fine to start a sentence with And, But or So.

One light filler per turn, never stacked:
  "Okay, so... let me take a look."
```

> **Warning:** Do not use SSML. Tags such as break or emotion tags are not supported and are read out or mangled. An ellipsis is your pause.

## Step 3: Say numbers, dates and ids like a person

This one habit does more for realism than anything else:

| Written | Spoken |
|---|---|
| Ticket TKT-5001 | "ticket five thousand one" |
| -57 dBm | "a strong signal" |
| 90 seconds | "about a minute and a half" |
| 2026-07-30 | "this Thursday" |
| +14155550100 | read one digit at a time |

## Step 4: Tune turn-taking

Two behaviours, tuned together: how easily the caller can interrupt (barge-in), and how long the agent waits after the caller stops before it speaks (end of turn). Set them in **Capabilities → Voice & turn-taking**:

| Preset | Behaviour | Use it for |
|---|---|---|
| **Patient caller** | Waits out pauses mid-thought; small words like "mm-hm" do not cut the agent off. | Older or distressed callers, anyone reading a number off a screen. |
| **Fast-paced line** | Any word interrupts; a quick end of turn. | Dispatch desks, expert users. |
| **Announcements only** | The agent cannot be interrupted while speaking. | Confirmations and compliance lines that must be heard in full. |

In the [voice agent SDK](https://docs.vlayers.ai/developers/sdks/voice-agents), the same settings are on the agent:

```ts
speech: {
  interruption: { minWords: 2, minDuration: 600 },
  endpointing: { minDelay: 900, maxDelay: 4000 }
}
```

`minWords: 2` means "mm-hm" does not cut the agent off, but "wait, stop" does. `minDelay` is how long silence must last before the caller's turn counts as over.

## Test it

Judge it by ear, on a real call: a transcript tells you nothing about pacing. Call the agent, interrupt it on purpose, and pause mid-sentence to see whether it waits. See [Testing](https://docs.vlayers.ai/build/testing).

## Common problems

| Problem | Fix |
|---|---|
| The agent talks over the caller, or asks again while they are thinking | Move towards **Patient caller**. |
| The agent feels asleep | Move towards **Fast-paced line**. |
| A proper noun comes out wrong | Speech-to-text guesses at unusual names. Confirm important values back to the caller instead of acting on one hearing. |

## Next steps

- [Testing](https://docs.vlayers.ai/build/testing): Hear the agent before customers do.
- [Playbooks](https://docs.vlayers.ai/build/playbooks): Write instructions a goal-driven step can follow.