Subscribe

MOSS-Live

MOSI Intelligence and OpenMOSS released MOSS-Live, a full-duplex real-time voice system that ranks first on six full-duplex metrics against GPT-Live-1 and Doubao SeedDuplex.

MOSS-Live pairs a foreground model that listens, manages turn-taking and speaks with a background model that handles reasoning, tool calls and longer tasks. The two share memory, context and task state through a coordination layer, so the conversation continues while a task runs. It also supports live video, screen sharing and streaming interpretation.

Date
Friday 13 November 2026
Lab
MOSI.AI
Kind
model
Access
closed API

Figures

MeasureValueMeasured by
Responds to speech not directed at it2%
lower is better; GPT-Live-1 68%, Doubao SeedDuplex 75%
company
Cuts in during user pause1.44%
GPT-Live-1 10.37%, Doubao SeedDuplex 14.29%
company
Correctly ignores irrelevant interruptions68%
vs 21% and 13% for the two rivals
company
Holds course through brief acknowledgments98.17%company
τ-Voice multi-turn task score57.93%
behind GPT-Live-1 at 67.68%, ahead of Doubao at 17.38%
company
Big-Bench Audio88.40%
below Doubao at 90.50%
company
FDB v3 tool use success51%
tied with Doubao SeedDuplex, GPT-Live-1 45%
company

Figures are vendor-published and sample sizes and uncertainty estimates were not disclosed. Available in an online playground and a WebSocket realtime API as moss-live-1.0; a GitHub repo exists, but weights availability was not confirmed.

Sources

  1. pandaily.com/mosi-openmoss-moss-live-full-duplex-evaluation-gpt-live-doubao-seedduplex

This record was checked against its sources on 14 November 2026. How we check

Read the daily brief for 13 November 2026