Flux

Speech recognition for voice agents: alongside the transcript the model decides when a turn ended and handles interruptions via tunable thresholds. Available as flux-general-en and the ten-language flux-general-multi.

многоязычный вариант выведен в общий доступ в апреле 2026

Understands

audio

Produces

text

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.