Models / Cartesia

Cartesia

Deploy the latest Cartesia Sonic models on Together AI. Expressive, ultra-low-latency text-to-speech with real-time streaming, purpose-built for production voice agents.

Why Cartesia on Together AI?

Designed for production workloads that need 
consistent performance and operational control.

Ultra-low-latency, expressive speech

Cartesia's Sonic models deliver expressive, ultra-low-latency text-to-speech purpose-built for voice agents. They support real-time WebSocket streaming for the lowest-latency applications.

One co-located voice stack

Serve text-to-speech alongside your LLM and speech-to-text inside a single Together AI cluster, keeping end-to-end voice latency under 500ms and your pipeline on one platform.

Enterprise-ready from day one

SOC 2 Type II certified, HIPAA compliant, and deployed on US-based infrastructure. Full model ownership with no data retention by default.

Meet the Cartesia family

Explore top-performing models across text, image, video, code, and voice.

Audio

Cartesia Sonic 3.5

Audio

Cartesia Sonic-3

Audio

Cartesia Sonic-2

Deployment options

Run models using different deployment options depending on latency needs, traffic patterns, and infrastructure control.

  • Serverless Inference

  • Provisioned 
Throughput

  • Dedicated Model 
Inference

  • Dedicated Container 
Inference

Serverless Inference

A fully managed real-time or batch inference API with access to dozens of the most popular AI models.

Best for

Variable or unpredictable traffic

Rapid prototyping and iteration

Cost-sensitive or early-stage production workloads

Provisioned 
Throughput

Reserved token capacity with SLA guarantees. Priced in PTUs, a normalized throughput unit. 

Best for

Production workloads

Reliability guarantees

Predictable pricing

Dedicated Model 
Inference

An inference endpoint backed by reserved, isolated compute resources and Together AI inference research.

Best for

Predictable or steady traffic

Latency-sensitive applications

High-throughput production workloads

Dedicated Container 
Inference

Run inference with your own engine and model on fully-managed, scalable infrastructure.

Best for

Generative media models

Non-standard runtimes

Custom inference pipelines