Open-source full-duplex voice model Sophon-Realtime v1 beats Grok on tool calling
bdsqlsz · x · 2026-11-10
Adventists AI open-sourced Sophon-Realtime v1 on ModelScope under Apache-2.0: a full-duplex voice model that keeps listening while you talk, answers 0.4s after you stop, and cuts off instantly when interrupted. It laughs, sighs and clears its throat contextually. It ranks #1 among open full-duplex models on VoiceBench (82.8) and Big Bench Audio (81.8%), and scores 48% Pass@1 on Full-Duplex-Bench v3 tool calling, ahead of Grok's 43%.
More from Multimodal
- AI-built 3D desert game world editor demo stuns with "They can build now?" — jasonkneen · 2026-11-10
- MiniMax H3-Image enters early access with 16-reference-image precision — SarahAnnabels · 2026-11-10
- Disney partners with Adobe Firefly to build brand-safe custom AI tools — The Decoder · 2026-11-10
- GPT-image 2.6 'brandshaped typography' prompt turns brand text into logo shapes — aziz4ai · 2026-11-10
- SplatAnything debuts: feed-forward 3DGS reconstruction that generalizes to arbitrary scenes — _akhaliq · 2026-11-10
- Fluffy coffee-sipping dragon AI art makes the rounds — azed_ai · 2026-11-10