Cartesia Releases Sonic-3.6 TTS, Toping AI Audio Benchmarks After Architecture Rebuild
HazyResearch · x · 2026-08-28
Cartesia announced the general availability of Sonic-3.6, their new TTS model. It ranked #1 on AI Audio benchmarks during preview and graduated to GA in a week due to positive feedback. The team rebuilt the architecture from the ground up instead of tuning the existing paradigm, surpassing their previous best model in two months.
Related event: Cartesia's Sonic-3.6 TTS Launches, Topping Voice and Audio Leaderboards(5 posts)→
More from Multimodal
- 28MB Gaussian splat of Stonehenge lets you walk inside the stones in a browser — willeastcott · 2026-08-28
- Midjourney Prompt for 'Forgotten Ceremony' Imagery — tisch_eins · 2026-08-28
- Meta's Muse Image available on fal: Agentic planning & correction — giffmana · 2026-08-28
- Seeking local TTS tools for generating unique, non-cloned voices — TastesLikeOwlbear · 2026-08-28
- Audio.cpp 0.7: 62 model families, new Arena UI for comparison — Acceptable-Cycle4645 · 2026-08-28
- Alibaba's Wan3.0-Video Available on DeepInfra with 1080P Audio/Video Support — gharik · 2026-08-28