Cartesia launches Sonic 3.6: 44-language TTS model with sub-90ms latency
emmanuelvivier · x · 2026-08-20
Cartesia has released Sonic-3.6, the latest version of its real-time text-to-speech model. It ranks #1 on both Artificial Analysis speech leaderboards (1283 Elo on Provider Voice, 1123 on Controlled Voice). Built on state space models instead of Transformers, the model features sub-90ms time-to-first-audio latency and supports 44 languages. It is available via a beta API with no open-source weights.
More from Models
- Opus 5.5 value may end the habit of using the top model for everything — adonis_singh · 2026-10-16
- Peter Yang: Opus 5.5 Still Struggles to Hold Its Ground When Pushed Back — petergyang · 2026-10-16
- Robot Startup Ditches VLAs for Frontier LLMs in a Customer Deployment — ihorbeaver · 2026-10-16
- Musk amplifies user claim that Grok's computer use is fast enough to skip a Codex subscription — elonmusk · 2026-10-16
- PhoneLLM launches open voice-AI models with sub-100ms latency, tops PhoneBench at 83% — charles_irl · 2026-10-16
- Transluce vets: a year of neuron autointerp work still can't explain complex behaviors — aryaman2020 · 2026-10-16