Audio
GA
Proprietary
Sonic 3
Low-latency real-time voice agents
Release2025-10
Context—
Max output—
ParametersUndisclosed
Local / VRAMAPI only
LicenseProprietary
Overview
Sonic 3 is a model in the Audio category from Cartesia. It was released in 2025-10. The vendor is based in US. Best for: Low-latency real-time voice agents.
Notes: Positioning from the vendor site; specs, access and pricing can change — verify before production use.
Strengths
- Very low latency
- Voice cloning
- Streaming
Limits
- API-first
- English-centric
Specifications
| Vendor | Cartesia |
|---|---|
| Category | Audio |
| Release | 2025-10 |
| Status | GA |
| License | Proprietary |
| Commercial use | Not specified |
| Input modalities | Text |
| Output modalities | Audio |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | No |
| API access | Yes |
| Pricing | Usage-based API |
| Confidence | Medium |
| Vendor country | US |
| Vendor type | Media lab |
Pricing & hardware
Usage-based API
API-only: local GPU memory is not applicable. API access is available.