Cartesia Models by Cartesia

CartesiaProprietary

2 models2026

Last refreshed 2026-08-27. Next refresh: weekly.

ResearcherCartesia

LicenseProprietary

Commercial useCommercial use: conditional

Models2

Released2026

About

Cartesia speech models for real-time text-to-speech and speech-to-text through the Cartesia API.

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view

Use when the workload needs audio.

2026-08audio

Ink 2Current

Use when the workload needs speech recognition and audio.

2026-07speech recognitionaudio

Current Cartesia variants with use-when guidance and lifecycle status
Model	Use when	Released	Signals	Status
Sonic 3.6	Use when the workload needs audio.	2026-08	audio	Current
Ink 2	Use when the workload needs speech recognition and audio.	2026-07	speech recognitionaudio	Current

2 release groups

2026-08

1 current

audio

Current

2026-07

1 current

speech recognitionaudio

Current

Cartesia model specifications comparison
Model	Released
Sonic 3.6	2026-08
Ink 2	2026-07

Sonic 3.6

Ink 2