What stt model are you using <@U0881N0M3PS> ?
# agents
s
What stt model are you using @flaky-beard-91685 ?
f
deepgram
s
from livekit.plugins import deepgram session = AgentSession( stt=deepgram.STTv2( model="flux-general-en", eager_eot_threshold=0.4, ), # ... llm, tts, etc. ) I use this And it's really good
Not the inference
f
I'm also not using the inference, also I can see you are using the
STTv2
the
flux
supported but we are just fine with
nova-3
and for all those days it was working fine I don't know what happened since last day, both our telephony agent and the web agent started showing this behaviour.
s
I'd say maybe try debugging with other models Just to see what the issue is