On-prem streaming STT latency — 8 kHz telephony, Finalize + endpointing

[bdc-001]

We use self-hosted Deepgram from a Go voice bot over WebSocket /v1/listen:

sample_rate=8000, encoding=linear16, interim_results=true, endpointing=300 (configurable)
We also send {"type":"Finalize"} when our VAD detects end-of-speech
KeepAlive every 5s

Goal: minimize latency

What do you recommend for on-prem to cut latency—model choice (Nova-2 vs Nova-3/Flux), endpointing vs Finalize, and any query params we should enable for telephony (utterance_end_ms, vad_events, etc.)?

[deepgram-community[bot]]

Thanks for asking your question. Please be sure to reply with as much detail as possible so the community can assist you efficiently.
_{Consider joining our Discord community for more opportunity to engage with your fellow Deepgram users. You can earn points which can be redeemed for cool stuff by being active in our communities!}

[deepgram-community[bot]]

Hey there! It looks like you haven't connected your GitHub account to your Deepgram account. You can do this at https://community.deepgram.com - being verified through this process will allow our team to help you in a much more streamlined fashion.

[deepgram-community[bot]]

It looks like we're missing some important information to help debug your issue. Would you mind providing us with the following details in a reply?

• The deepgram product you are using (e.g Speech to Text, Agent API)
• A request ID that triggered your error or issue.