Deepgram API not returning complete transcripts

[ks233ever]

We have noticed that many of our response transcripts being returned via the Deepgram API only contain a small portion of the expected transcript. E.g. 45 minute files are returning just 15 minutes of transcription. The majority is missing. I have confirmed programmatically that the files being sent via the API are in fact ~45mins. However, within the UI logs, the requests show only ~15mins in audio length. I'm not sure what is happening on the Deepgram side to only read in a small portion of the audio file. Clients are receiving incomplete transcripts, so this is an urgent issue for us. Here is an example request id to debug on your end: b3dc923a-70bf-4119-89d8-9aa84e44105b.

We are seeing this happen around 30% of the time. It is heavily impacting our business. For your engineer's reference, please see the screenshot containing the python code (using deepgram-sdk==2.4.0) that we are using to pass files to your API:

Please advise on how to get back up and running again. Thanks!

[ks233ever]

Posting here for others who may run into this issue, as it took me a little to figure out how to pass context-length.

This was solved (so far no more issues, fingers crossed) by updating to deepgram sdk 3.7.7 and replacing my original code with the attached snippet:

from deepgram import (
DeepgramClient,
PrerecordedOptions,
)