Wonderful runs in-house voice models on Together AI at 274ms first sentence

togethercompute · x · 2026-11-18

Wonderful, the enterprise AI OS (raised $800M+, 35+ markets), builds its own multilingual voice models for underserved languages and runs them on NVIDIA GPUs via Together AI: 274ms time-to-first-sentence at production concurrency, 100% uptime, zero human interaction for scaling/weight rollouts/blue-green tests, EU-only data residency. Together uses the case to pitch its Polymorphic Inference/Compiler stack and announces on-demand B200 clusters.

Original post →

More from Infra

Infra channel →