Endpointing feature query

[candid walrus]

I have enabled endpointing feature, but I want to keep utterance end ms value less than 1000, does that work?

[red echo]

Hi @candid walrus. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

[jolly ore]

Hey there! This channel allows you to ask Kapa.ai for assistance. But it looks like you haven't connected your Discord profile to your Deepgram account yet. You can do so at https://community.deepgram.com - by doing so, you'll be able to ask questions in #1115960287183511643 if you need human assistance!

[red echo]

---

No, setting the utterance_end_ms value to less than 1000 will not work. The UtteranceEnd feature is based on word timings, and since interim results (which UtteranceEnd relies on) are typically produced about once every second, you cannot specify utterance_end_ms values below 1000 ms. Attempting to do so will result in an error, such as a rejected WebSocket connection with HTTP 400. For silence detection under 1000 ms, you should use the endpointing feature instead, which is based on audio silence rather than word timings Minimum utterance_end_ms Utterance End Limitations of Endpointing.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: