18 August 2026
Cartesia releases multilingual text-to-speech model Sonic-3.6
- Cartesia, a speech synthesis startup, launched Sonic-3.6 in beta testing with support for 44 languages.
- The model ranks highest on Artificial Analysis voice leaderboards, a benchmark ranking text-to-speech systems.
How it was covered
The Rundown AIRowan Cheung
Cartesia launched Sonic-3.6 in beta, a text-to-speech model covering 44 languages that tops Artificial Analysis voice leaderboards.