Trending storyDeveloping

Adventists AI open-sources Sophon-Realtime v1 full-duplex voice model

1 article1 sourcesince Nov 9Last article 12h ago · Nov 9, 8:00 AM ET

Overview

AISummary of 1 article

Adventists AI has open-sourced Sophon-Realtime v1, a full-duplex voice model, on ModelScope under the Apache-2.0 license, according to a ModelScope post on X. The model keeps listening while the user talks and replies about 0.4 seconds after they stop, and it can laugh, sigh and clear its throat.

The post reports 82.8 on VoiceBench and 81.8% on Big Bench Audio, which it says ranks first among open full-duplex models. It also reports 48% Pass@1 on Full-Duplex-Bench v3 tool calling, ahead of Grok at 43%. These figures come from the post and have not been independently verified.

Written by AI from the articles below · updated Nov 9, 4:14 PM ET

Check the sources:

Latest developmentNov 9, 8:00 AM ET

Adventists AI open-sources Sophon-Realtime v1 full-duplex voice model

Article timeline

The articles in this story. Times are ET.

Nov 9

8:00 AM
ModelScope@ModelScope2022Official
Adventists AI open-sources Sophon-Realtime v1 full-duplex voice model
AIAdventists AI open-sources Sophon-Realtime v1 on ModelScope, a full-duplex voice model that keeps listening while the user talks and replies about 0.4 seconds after they stop. The model can laugh, sigh, and clear its throat, and it scores 82.8 on VoiceBench and 81.8% on Big Bench Audio, ranking first among open full-duplex models. Its weights are released under Apache-2.0, and it reaches 48% Pass@1 on Full-Duplex-Bench v3 tool calling, ahead of Grok at 43%.

Heat Trend

Current comparable heat: 7
Peak comparable heat: 8Nov 9, 5:00 PM ET
Change in past 24 hours: –

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.