Deepgram
Optimal Audio Chunk Size for Nova-3 #1476
-
|
Hi, I noticed that the documentation for Flux indicates that 80ms audio chunks are best for both audio and latency - is there a similar guideline for nova-3? Can't seem to find any documentation indicating anything. (Speech to text streaming) |
Beta Was this translation helpful? Give feedback.
Replies: 4 comments
-
|
Thanks for asking your question. Please be sure to reply with as much detail as possible so the community can assist you efficiently. |
Beta Was this translation helpful? Give feedback.
-
|
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. |
Beta Was this translation helpful? Give feedback.
-
|
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?
|
Beta Was this translation helpful? Give feedback.
-
|
Nova-3 is a bit less sensitive to varying chunk sizes, which is why we don't call it out explicitly like we do with Flux. 20-100ms chunks are great. over 200ms and you may start to see increases in latency, in particular around endpointing (depending on your endpointing value).
|
Beta Was this translation helpful? Give feedback.
Nova-3 is a bit less sensitive to varying chunk sizes, which is why we don't call it out explicitly like we do with Flux. 20-100ms chunks are great. over 200ms and you may start to see increases in latency, in particular around endpointing (depending on your endpointing value).