Thinking Machines' Native Interaction Models: TML-Interaction-Small 276B-A12B Advances Realtime Voice

[AINews] Thinking Machines' Native Interaction Models - TML-Interaction-Small 276B-A12B - advances SOTA Realtime Voice and kills standard VAD

Thinking Machines released TML-Interaction-Small, a 276B-parameter MoE model with 12B active parameters, and the post says it advances realtime voice through 200ms time-aligned microturns, encoder-free early fusion for audio and images under 200ms, and benchmark wins over GPT-Realtime-2 and Gemini 3.1-Flash.

Why it matters: HKR-H/K/R all pass: TML-Interaction-Small gives architecture, active parameters, 200ms interaction, and named rivals. Benchmarks still need replication, but a real-time voice SOTA claim is same-day material.