LanguageOH-SO
cartesia

Sonic-3.5

#5

cartesia · v3.5 · 8× · zuletzt 30. Juni 2026

25
Momentum

Sonic-3.5 is a text-to-speech model by Cartesia optimized for real-time speech generation in voice agents. The model is recognized as a leading streaming TTS solution and stands out for its speed, precise pronunciation, and natural speech delivery.

Momentum trend
01.04.30.06.

Features

LatenzOptimiert für niedrige Latenz in Echtzeit-TTS
StimmqualitätElo-Rating 1218 auf Speech Arena
Unterstützte Sprachen42 Sprachen

Sources (8)