MongoDB - Build AI That Scales
Mini toolsSonic 3.5
By Cartesia
Sonic 3.5 is Cartesia’s text-to-speech model for real-time voice agents, support calls, assistants, and conversational speech generation. It is designed for expressive, natural delivery with sub-90 ms latency, native support for 42 languages, clean audio, and faithful transcript following. It also handles structured speech such as order numbers, phone numbers, IDs, emails, and context-dependent English heteronyms without extra preprocessing. The stable snapshot listed by Cartesia is sonic-3.5-2026-05-04, released on 04-05-2026.
New
Multimodal
Gen 3
Overview
Sonic 3.5 is Cartesia’s fastest and most natural text-to-speech model, built for low-latency conversational voice generation across 42 languages.
About Cartesia
Industry:
Artificial Intelligence
Company Size:
91
Location:
Daly City, California, US
Website:
cartesia.ai
Tools using Sonic 3.5
No tools found for this model yet.
Last updated: June 16, 2026
