Cartesia Sonic-3
Low-latency, ultra-realistic voice model, served in partnership with Cartesia.
About model
Cartesia Sonic-3 converts text to speech with high expressiveness and naturalness. Its key strength lies in voice quality and low-latency synthesis. Suitable for developers requiring fast, high-fidelity speech generation.
API usage
Endpoint:
Related models
- Model providerCartesia
- TypeAudio
- Main use casesText-to-Speech
- DeploymentServerless
- Endpoint
- Context lengthUnlimited
- Price
$65.00 / 1M characters
- Input modalitiesText
- Output modalitiesAudio
- ReleasedJanuary 11, 2026
- External link
- CategoryAudio