Model Family
Cartesia
State-space-model TTS provider focused on ultra-low-latency real-time voice.
Definition
Cartesia builds Sonic, a state-space-model-based text-to-speech engine optimised for streaming latency under 100ms — important for live voice agents. The SSM backbone delivers high-quality audio at lower compute than diffusion or transformer TTS.
Common use cases
- Voice agents
- Real-time TTS
- Call centres