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.
More from Infra
- Inside Microsoft's massive Outlook outage: what broke and why fixes took so long — tomwarren · 2026-11-18
- Kimi K3.1 Pro DSpark model card: 2.5B draft, 5.57 acceptance length on GSM8K — vllm_project · 2026-11-18
- vLLM ships DSpark draft model for Kimi K3.1 Pro with up to 30% higher acceptance length — vllm_project · 2026-11-18
- Anthropic's S-1 Shows Only 25% of Compute Goes to Inference — Sparking a Bear Case — toptickcrypto · 2026-11-18
- LanceDB Raises $57.5M Series B for AI-Native Multimodal Data Stack — pzakin · 2026-11-18
- Multi-Branch Transformer scales LLMs via parallel branches, saving up to 1.26x training compute — KyeGomezB · 2026-11-18