HeyGen

This page is auto-generated from model configurations. Last updated: 2026-11-09.

This reference lists all available HeyGen audio generation models and their parameters. Use these parameter names when calling the Generation API.

• HeyGen Voice
• HeyGen Voice Turbo

---

HeyGen Voice

HeyGen Voice text-to-speech — natural speech in 39 languages with 24 library voices or an instant clone from a reference clip.

Model ID: model_heygen-voice

Capabilities: txt2audio

LLM Markdown: https://app.scenario.com/api/models/model_heygen-voice/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
text	string	Yes	-	-	-	-	The text to speak. Max 5,000 characters.
voice	string	No	Jonah	-	-	Jonah, Nadine, Tabitha, Soren, Elowen, Vincent, Jocelyn, Marielle, Corinne, Lucian, Kieran, Hugh, Noelle, Bram, Ewan, Iona, Cecily, Simon, Weston, Felicity, Gareth, Rory, Meredith, Sabrina	HeyGen library voice. Ignored when a reference audio is set.
audio	file	No	-	-	-	-	Recording of a single speaker to clone instead of using a library voice (up to 3 minutes).
language	string	No	-	-	-	``, ar, be, bg, ca, cs, da, de, el, en, es, fa, fi, fr, he, hi, hr, hu, id, it, ja, ko, mk, ms, nl, pl, pt, ro, ru, sk, sl, sr, sv, ta, th, tl, tr, uk, vi, zh	Language of the text. Detected from the text when empty.
expressivenessBoost	number	No	1	0	1	-	How expressive the delivery is.

HeyGen Voice Turbo

HeyGen Voice Turbo — the fast, low-cost HeyGen text-to-speech tier, with 24 library voices or an instant clone from a reference clip in 39 languages.

Model ID: model_heygen-voice-turbo

Capabilities: txt2audio

LLM Markdown: https://app.scenario.com/api/models/model_heygen-voice-turbo/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
text	string	Yes	-	-	-	-	The text to speak. Max 5,000 characters.
voice	string	No	Jonah	-	-	Jonah, Nadine, Tabitha, Soren, Elowen, Vincent, Jocelyn, Marielle, Corinne, Lucian, Kieran, Hugh, Noelle, Bram, Ewan, Iona, Cecily, Simon, Weston, Felicity, Gareth, Rory, Meredith, Sabrina	HeyGen library voice. Ignored when a reference audio is set.
audio	file	No	-	-	-	-	Recording of a single speaker to clone instead of using a library voice (up to 3 minutes).
language	string	No	-	-	-	``, ar, be, bg, ca, cs, da, de, el, en, es, fa, fi, fr, he, hi, hr, hu, id, it, ja, ko, mk, ms, nl, pl, pt, ro, ru, sk, sl, sr, sv, ta, th, tl, tr, uk, vi, zh	Language of the text. Detected from the text when empty.
expressivenessBoost	number	No	1	0	1	-	How expressive the delivery is.