-
Notifications
You must be signed in to change notification settings - Fork 3.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
openai api audio.transcriptions.create
not working when response format is not json
#1035
Closed
1 task done
Labels
Comments
Thanks for reporting! We would appreciate a PR from the community fixing this within the Otherwise, we'll try to get to it when we can. |
1 task
zakriaalgopane
added a commit
to zakriaalgopane/openai-python
that referenced
this issue
Feb 5, 2024
…rmat is not json Fixes openai#1035
@rattrayalex I would like to work on this, could you please assign this to me |
Go for it! |
1 task
@rattrayalex, could you see my solution? |
Thanks @aurishhammadhafeez, I've merged your PR so this will be fixed in the next release, |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Confirm this is an issue with the Python library and not an underlying OpenAI API
Describe the bug
If you specify
--response-format
to a format other than json (likesrt
orvtt
), theopenai api audio.transcriptions.create
command will fail with errorTo Reproduce
OPENAI_API_KEY=<YOUR_API_KEY> openai api audio.transcriptions.create -f 1.m4a --response-format vtt
I can also reproduce this using
python:3.12
Docker image.Code snippets
No response
OS
macOS
Python version
Python 3.11.6
Library version
v1.6.1
The text was updated successfully, but these errors were encountered: