Voices & models

Two choices shape how your agent sounds and thinks: its voice and its model. Both are set per agent on the agent form and can be changed any time.

Voices

English — Deepgram Aura-2

English agents speak with Deepgram Aura-2 — natural, low-latency voices. There are 41 options (25 female, 16 male), including British, Australian, Filipino, and southern-accented voices:

Voice	Gender	Character
Thalia	Female	Recommended — clear, confident. A safe default for any business.
Amalthea	Female	Filipino accent — engaging, natural.
Andromeda	Female	Casual, expressive. Pre-selected on new agents.
Asteria	Female	Clear, confident.
Athena	Female	Calm, smooth.
Aurora	Female	Cheerful, expressive.
Callista	Female	Clear, energetic.
Cora	Female	Smooth, melodic.
Cordelia	Female	Approachable, warm.
Delia	Female	Casual, friendly.
Electra	Female	Professional, engaging.
Harmonia	Female	Empathetic, clear.
Helena	Female	Caring, natural.
Hera	Female	Smooth, warm.
Iris	Female	Cheerful, positive.
Janus	Female	Southern accent — smooth.
Juno	Female	Natural, engaging.
Luna	Female	Friendly, natural.
Minerva	Female	Positive, friendly.
Ophelia	Female	Expressive, enthusiastic.
Pandora	Female	British accent — smooth, calm.
Phoebe	Female	Energetic, warm.
Selene	Female	Expressive, engaging.
Theia	Female	Australian accent — expressive, polite.
Vesta	Female	Natural, expressive.
Apollo	Male	Confident, comfortable.
Arcas	Male	Natural, smooth.
Aries	Male	Warm, energetic.
Atlas	Male	Enthusiastic, confident.
Draco	Male	British accent — warm, approachable.
Hermes	Male	Expressive, engaging.
Hyperion	Male	Australian accent — caring, warm.
Jupiter	Male	Expressive, knowledgeable.
Mars	Male	Smooth, patient.
Neptune	Male	Professional, patient.
Odysseus	Male	Calm, smooth.
Orion	Male	Approachable, comfortable.
Orpheus	Male	Professional, clear.
Pluto	Male	Smooth, calm.
Saturn	Male	Knowledgeable, confident.
Zeus	Male	Deep, trustworthy.

Arabic — Saudi dialect

Agents whose language is Arabic (Saudi) — and the Arabic side of a multilingual agent — speak with Saudi-dialect ElevenLabs voices:

Voice	Gender	Character
Maryam	Female	Recommended — calm, warm.
Ahmed	Male	Conversational.
Mohammed	Male	Smooth.

Choosing a voice:

Match the brand and audience — a spa and a law firm want different energy.
Listen before you commit. Use the agent’s share link and have a short call; tone reads differently spoken than on paper.
All Aura-2 voices are fast, so within the English catalogue voice choice doesn’t change latency — pick purely on feel.

Models

The model is the agent’s reasoning engine. Faster models reply quicker; more capable ones reason better.

Model	Speed	Strengths	Use it when
GPT-4.1 Mini	Fast	Reliable instruction-following + action-calling (booking, etc.)	Default for almost everyone.
GPT-4.1 Nano	Fastest	Lowest latency/cost	Simple Q&A agents; test booking/actions first — it’s less reliable at them.
GPT-4o Mini	Fast	Solid all-rounder	A good alternative to 4.1 Mini.
GPT-4o	Moderate	Most capable reasoning	Complex, multi-step conversations where quality matters more than speed.

Start with GPT-4.1 Mini. It’s the best balance of fast turns and dependable actions, and it’s tuned for prompt-cached, low-latency responses. Only move to GPT-4o if you genuinely need deeper reasoning, or to Nano if the agent is simple and you want maximum speed.

Latency — what actually makes a call feel fast

A natural conversation feels instant when each turn is well under a second. The biggest lever is the model’s time-to-first-token — which is exactly why the default is a fast model and why prompts are structured for caching. You can see the real breakdown for any call in Observability (the latency waterfall).

If turns feel slow:

Make sure you’re on GPT-4.1 Mini (or Nano for simple agents).
Keep the instructions short and let Knowledge carry the facts.
Check the latency waterfall to see whether it’s the model or an action (e.g. a slow calendar) that’s costing time.

Configure your agent