Skip to main content
The words matter, but so does the delivery. The same sentence can sound warm or robotic depending on the voice and the pacing. Here’s what you get to choose.

​
The voice

You pick a voice from a catalogue, the way you’d cast a person for a role. Each voice has its own sound and feel. Try a few out loud before you settle. The right voice depends on your audience and your brand, there’s no single “best” one.

​
Speaking speed

This is how fast the agent talks. Normal speed is 1. Lower is slower and calmer, higher is quicker.
  • Slow down for older audiences, or anything with numbers and details.
  • Speed up only a little, if at all. Fast talkers are hard to trust.
A little secret: 1.1 tends to sound the most human. We can’t fully explain why. It just does.

​
Expressiveness

This controls how much the voice varies its tone, its “expressiveness.” A little variation sounds alive. Too much sounds theatrical. A middle setting is usually the safe, natural choice.

​
Language

You set the language the agent listens and speaks in, like US English. You can even give it a list of languages, and it will handle callers in more than one.

​
Background sound

By default the call is clean and quiet. If you want, you can add a light background, like a soft call center or coffee shop ambience, so it feels less sterile. This is optional. When in doubt, leave it off.

​
Noise handling

Real phone calls are noisy. There’s a setting that cleans up background noise so the agent hears the caller clearly. If people are calling from cars and cafes, turn on stronger noise handling. If your calls are usually clean, you can keep it light.

​
Do / Don’t

  • Do listen to the agent out loud before going live. Your ear will catch things the settings page won’t.
  • Do match the pace to your audience, slower for detail heavy calls.
  • Don’t crank expressiveness to the top. Natural beats dramatic.
  • Don’t add a busy background sound. If it’s distracting to you, it’s distracting to the caller.