Transcription models available - Question on gpt-4o-transcribe gpt-4o-mini-transcribe gpt-4o-transcribe-diarize

API
, , , ,
1

We are using this API GitHub - openai/openai-dotnet: The official .NET library for the OpenAI API · GitHub

To date we have exposed STT model

  • GPT4o Transcribe
  • GPT4o mini Transcribe
  • Whisper

We are having issues with the GPT4o Transcribe

Error:

Transcription stopped working: HTTP 403 (invalid_request_error: model_not_found) Project `*******` does not have access to model `gpt-4o-transcribe`

Questions:

Are they deprecated? If yes, no problem I just want to know what I can offer. But then why are they still listed?

image
image1359×580 72.3 KB

Whisper - works - I will keep. But I want to give options:

Can I use this? GPT-4o Transcribe Diarize Model | OpenAI API

My Lead developer tells me that gpt-4o-transcribe-diarize is not available in the API.

Can someone help me pl - thanks so much

1 Like
2

Hi!

These models are not deprecated. I also did a quick test that I can use these models using the latest version of the OpenAi .Net library. The most likely explanations for the HTTP 403 ... Project ... does not have access to model ... error are:

  • the wrong API key is loaded at runtime
  • the key belongs to a different OpenAI project
  • an explicit OpenAI-Project header points to the wrong project

You can check the API keys, permissions and project access via the platform:

2 Likes
3

Dear @vb Thanks so much

You are correct - I retested everything now and it works 100%. Also generated a fresh key to double check. All is good and these models are still available.

About this “gpt-4o-transcribe-diarize” GPT-4o Transcribe Diarize Model | OpenAI API we will run another check because we noticed some recent changes.

Ill get back to you with the results - thanks so much! Cheers

1 Like
4

@vb

About this “gpt-4o-transcribe-diarize” GPT-4o Transcribe Diarize Model | OpenAI API

The problem is that the API doesn’t allow setting response format to “ddiarized_json” which is needed for this model.
There’s an open issue about this here https://github.com/openai/openai-dotnet/issues/869

Seems like the required “chunking_strategy” is not currently supported by the SDK and we get HTTP 400 (invalid_request_error: invalid_value)
Parameter: chunking_strategy
chunking_strategy is required for diarization models

This shows that there is active work ongoing.

Guess I will wait and watch… If you happen to have any additional news, do not hesitate and let me know.

Thanks so much Dears