Skip to main content
Soniox TTS v1 is a real-time, low-latency text-to-speech model with 60 supported languages. Voices are referenced by name. Pass the voice_id from the tables below as the voice field in your request.
Set the optional language field to the matching ISO code for the language you want to synthesize. Default voice is Adrian, default language is en.

Supported languages

Slovenian

Afrikaans

Albanian

Azerbaijani

Basque

Belarusian

Bengali

Bosnian

Bulgarian

Catalan

Chinese

Czech

Dutch

English

Estonian

French

German

Greek

Gujarati

Hebrew

Hindi

Indonesian

Italian

Kannada

Korean

Latvian

Lithuanian

Macedonian

Malay

Marathi

Norwegian

Persian

Polish

Portuguese

Punjabi

Romanian

Russian

Serbian

Slovak

Spanish

Swedish

Tagalog

Telugu

Arabic

Croatian

Danish

Finnish

Galician

Hungarian

Japanese

Kazakh

Malayalam

Swahili

Tamil

Thai

Ukrainian

Urdu

Turkish

Vietnamese

Welsh