Standard voices vs OpenAI voices

A guide to all available voice types in Text to Speech: OpenAI voices, standard MiniMax voices and Custom Voices.

Written By Umakhan Magomedov

Last updated 4 days ago

Text to Speech offers two groups of voices: OpenAI voices and standard MiniMax voices. Each group has different characteristics, language support and pricing.


OpenAI voices

OpenAI voices are synthetic voices with distinct personality descriptions. They work best for English content and support voice instructions to adjust tone and style.

Name

Gender

Character

Alloy

Neutral

Balanced, versatile

Ash

Male

Soft, conversational

Ballad

Male

Melodic, musical

Coral

Female

Warm, friendly

Echo

Male

Clear, confident

Fable

Male

British, storyteller

Nova

Female

Energetic, youthful

Onyx

Male

Deep, authoritative

Sage

Male

Wise, calm

Shimmer

Female

Soft, lyrical

OpenAI voices support voice instructions: on the Voice tab, type a short description of how the voice should sound. For example: "Speak at a slow pace, with a warm and friendly tone."


Standard MiniMax voices

Standard MiniMax voices are multilingual and cover a wide range of languages. They work well for content in languages other than English.

Name

Gender

Vivian

Female

Serena

Female

Ono Anna

Female

Sohee

Female

Uncle Fu

Male

Dylan

Male

Eric

Male

Ryan

Male

Aiden

Male


Which to choose

Use case

Recommended

Why

English content, voiceover, narration

OpenAI voices

Natural-sounding English, controllable style

Multilingual content

Standard MiniMax

Broad language coverage

Sound like a specific person

Custom Voices

Voice cloned from your own recording

ℹ️ You can preview any voice by selecting it in the Voice tab and tapping the play icon next to the voice name before generating.


Frequently asked questions

Related articles