#connect ETIMEDOUT 38.104.135.210:443
1 messages · Page 1 of 1 (latest)
Thanks for asking your question. Please be sure to reply with as much detail as possible so the community can assist you efficiently.
-# If you haven't done so, ensure your Discord and Github profiles are linked to Deepgram so you can earn points to redeem on cool stuff just by being active!
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 programming language you are working in (e.g. JavaScript, Python).
- The deepgram product you are using (e.g Speech to Text, Agent API)
programming language - NodeJS
deepgram product - Speech to Text
@thorny reef Started this thread
Do you have some request IDs where this happened?
ab189c14-1fd4-4e86-a823-a6ba148ab74e
@thorny reef
thanks. raising with our team now
Thanks
@vital panther can you let me know what AZs you're connecting from?
Can you let me know what AZs you're connecting from? We are investigating an issue that has also been reported by others, but we're only just starting to connect the dots
Our servers are in aws us-east-1 @thorny reef
My day ends here but I will update you tomorrow
@vital panther I have posted in the original thread but to let you know here to, we believe this is just a US-east issue. my colleague has reached out to our ISP, and in the meantime made some changes we hope will improve the situation in the short term
Thanks. Will monitor on our side and report here.
@thorny reef Alongside this we have observed 1 more issue. The first transcript is always delayed by 2-3 seconds in case of streaming and it also started happening around the same time.
@thorny reef Can you check this?
any updates here? @thorny reef
have you noticed any more timeouts?
Not timeouts but first transcript is always delayed by 5 seconds in case of streaming @thorny reef
5 seconds seems longer than we’d expect. There can be a small delay after connection, as we require a certain amount of audio context to accurately transcribe the most recent words (as well as selecting the right models, etc)
Can you provide some logging and a reproduction?
Hey there @vital panther~! Did you forget about this thread? Let us know if you still need help!
It is mostly happening with all requests with initial delay
@vital panther can you raise each issue in a new thread, I missed this because it had already been marked as answered once we addressed the timeouts
when did the latency increase start? 10/03/2025?