Cartesia Launches Sonic-3.5 TTS and Ink-2 STT Models for Real-Time Voice AI

S-1.25%
SONIC-1.77%
According to Beating, AI voice startup Cartesia announced the launch of Sonic-3.5 and Ink-2, forming a unified real-time voice agent technology stack. Sonic-3.5 handles text-to-speech with 90-millisecond first-token latency and supports 42 languages. Ink-2 delivers speech-to-text with 3.6% word error rate and native turn detection based on semantic understanding rather than silence duration alone. Both models integrate through a single API with bidirectional streaming to minimize transmission delays.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments