Home
Catalogs
Models 4,400
Sonic 3.5 Sonic 3.5 is Cartesia’s fastest and most natural text-to-speech model,…

Multimodal model

Sonic 3.5

Sonic 3.5 is Cartesia’s fastest and most natural text-to-speech model, built for low-latency conversational voice generation across 42 languages.

Cartesia Multimodal Open weights

Type: Multimodal
Weights: Open

More from Cartesia

5

Ink 2 Multimodal

Ink 2 is Cartesia’s speech-to-text model for voice agents, optimized for streaming transcription, semantic en…
Sonic-3.6 Audio

Sonic is a real time text to speech model that generates natural, expressive speech from text. It supports vo…

About Cartesia

1

cartesia.ai