API Reference
Start typing to search…

Text-to-Speech — Starfish

post
https://api.heygen.com/v1/audio/text_to_speech

Generate a speech audio file from any text input using a specified voice, powered by HeyGen's Starfish model.

Body Params
string
required

Text to synthesize into audio (1–5000 characters)

string
required

Voice ID from GET /v1/audio/voices

string
enum

"text" for plain text, "ssml" for SSML markup including break tags for pauses

Allowed:
string

Speed multiplier (0.5–2.0)

string

Base language code (e.g. "en", "pt", "zh"). Auto-detected from text when omitted

string

BCP-47 locale tag for accent/regional control (e.g. "en-US", "pt-BR"). When provided, language is inferred from the locale if not set explicitly

Response

Updated about 2 months ago

Language
Credentials
Header
Response 
Click Try It! to start a request and see the response here! Or choose an example:
application/json
Updated about 2 months ago