Open-Source Full-Duplex Speech Model Sophon-Realtime Released

Adventists AI open-sourced Sophon-Realtime v1, a full-duplex speech model with a 32B-parameter brain that listens, decides when to respond in 0.4s, and replies with emotional tone, under Apache-2.0 license.

2026-11-10 ~ 2026-11-10 · 2 related posts

• Open-source full-duplex voice model Sophon-Realtime v1 beats Grok on tool calling — bdsqlsz · 2026-11-10
• Open full-duplex voice model Sophon-Realtime tops open benchmarks, Apache-2.0 with tone-aware speech — pmttyji · 2026-11-10