Text to Speech Model

HeyGen Voice Turbo

Text to Speech by HeyGen

Start Building with HeyGen Voice Turbo View All Models

Publisher

HeyGen

TypeText to Speech

Context Window5,000 tokens

ReleasedOctober 2026

Price$0.005/request

Provider

WaveSpeed

SPEECHFASTVOICE CLONING

Try HeyGen Voice Turbo →

Ready to build with HeyGen Voice Turbo?

Get Started Free

Resources

Documentation & links

Official Website

→

Configuration

Parameters & options

VoiceSelect

A HeyGen voice. Ignored when a reference recording is given.

Default: Jonah

JonahNadineTabithaSorenElowenVincentJocelynMarielleCorinneLucianKieranHughNoelleBramEwanIonaCecilySimonWestonFelicityGarethRoryMeredithSabrina

Reference AudioAudio URL

A recording of one speaker to clone in place of a HeyGen voice. Only its first 3 minutes are used.

LanguageSelect

The language of the text. Detected from the text when unset.

DetectArabicBelarusianBulgarianCatalanChineseCroatianCzechDanishDutchEnglishFinnishFrenchGermanGreekHebrewHindiHungarianIndonesianItalianJapaneseKoreanMacedonianMalayPersianPolishPortugueseRomanianRussianSerbianSlovakSlovenianSpanishSwedishTagalogTamilThaiTurkishUkrainianVietnamese

ExpressivenessNumber

How expressive the delivery is, from 0 to 1.

Default: 1Range: 0–1 (step 0.1)

Related models