403 INSUFFICIENT_PERMISSIONS on prerecorded /v1/listen with Nova 3 — Playground works, API says “Project does not have access to the requested model” #1599
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.
-
request_id : 019de3d2-cce4-7e60-9b43-67e122c235b6 |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Category: General help
Summary
When calling the pre-recorded Speech-to-Text API (
POST https://api.deepgram.com/v1/listen) from our backend using the official Java SDK (deepgram-java-sdk0.3.0), we consistently receive HTTP 403 with:err_code:INSUFFICIENT_PERMISSIONSerr_msg:Project does not have access to the requested model.The same Deepgram account can use Nova 3 successfully in the official web UI / Playground, so we’re trying to understand whether this is an entitlement / project scoping issue for API keys, or a model string / query parameter mismatch between the dashboard and the SDK-generated request.
Environment
com.deepgram:deepgram-java-sdk0.3.0POST /v1/listen(JSON body with remote audio URL)model=NOVA3(all caps; note documentation typically showsnova-3/nova-3-general)Request (sanitized)
Beta Was this translation helpful? Give feedback.
All reactions