Controllability and Security
Full Model Training Hours
100000
High-Fidelity Speech Synthesis
In-Person Conversation Translation
Language and Accent Variants
No App Needed for Invitees
No Need for Human Interpreter
Open Source Model Training Hours
40000
Real-Time Translation Speed
Slight delay
Sample Rate for Audio Output
24000
Speech to Speech Translation
Supported Languages
عربيDeutschEnglishEspañolFrançaisIndonesia日本語한국인РусскийแบบไทยTiếng ViệtPortuguêsPolskiУкраїнська简体中文繁体中文
Supports Daily Life, Travel, and Business
ImmigrantsTravelersBusiness
Supports Multiple Languages
150
Total Supported Languages
150
Voice Customization Options